Fall armyworm Remote sensing

Users Edited Disease:
    • --- /tmp/diffy20211209-943388-tj224m 2021-12-09 07:10:32.833423516 +0000
    • +++ /tmp/diffy20211209-943388-1ip05bw 2021-12-09 07:10:32.833423516 +0000
    • @@ -1 +0,0 @@
    • -PRISE_CABI
    • --- /tmp/diffy20211209-943388-zmxlii 2021-12-09 07:10:32.841423570 +0000
    • +++ /tmp/diffy20211209-943388-1dfp400 2021-12-09 07:10:32.841423570 +0000
    • @@ -1,9 +0,0 @@
    • -<p>CABI recently announced a system for forecasting the <a href="http://edexme.com">risk of pest </a>outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • -
    • -<p>It is not clear from the media attention what the earth observations are. What satellites are being used.&nbsp;There is a document <a href="http://www.iapetus.ac.uk/wp-content/uploads/2018/10/IAP2-18-14_CEH_White.pdf">here</a> about the project.&nbsp; The project says it will use&nbsp; &quot;environmental data from Earth Observation&nbsp;validated by the consortium (e.g. land surface temperature and rainfall), pest phenology data across three different countries (Kenya, Zambia and Ghana) and crowdsourced observations.&quot;</p>
    • -
    • -<p>There are a number of satellites that measure ground temperature and moisture. But since no details have been provided we cannot speculate.&nbsp;</p>
    • -
    • -<p>It is worth stressing that there is no current evidence that PRISE can predict FAW.&nbsp;</p>
    • -
    • -<p>[December 4th, 2018- this needs community editing]</p>

    Edited by Rimnoma Serge Ouedraogo at January 12, 2021 19 : 56 : 08

    • --- /tmp/diffy20211209-943388-10zj4u7 2021-12-09 07:10:32.849423624 +0000
    • +++ /tmp/diffy20211209-943388-1vzhc0e 2021-12-09 07:10:32.849423624 +0000
    • @@ -1 +0,0 @@
    • -Introduction
    • --- /tmp/diffy20211209-943388-kfjogy 2021-12-09 07:10:32.853423651 +0000
    • +++ /tmp/diffy20211209-943388-10dvsge 2021-12-09 07:10:32.853423651 +0000
    • @@ -1,9 +0,0 @@
    • -<p><b>Remote sensing</b>&nbsp;is the acquisition of information about an object or phenomenon without making physical contact with the object and thus in contrast to on-site observation, especially the Earth. Remote sensing is used in numerous fields, including geography, land surveying and most Earth Science disciplines (for example, hydrology, ecology,&nbsp;&nbsp;meteorology, oceanography, glaciology, geology); it also has military, intelligence, commercial, economic, planning, and humanitarian applications.</p>
    • -
    • -<p>In this last case remote sensing has been suggested to be useful to track fall armyworm in Africa.&nbsp;</p>
    • -
    • -<p>In current usage, the term &quot;remote sensing&quot; generally refers to the use of satellite- or aircraft-based sensor technologies to detect and classify objects on Earth. Aircraft can include drones.&nbsp;</p>
    • -
    • -<p>The goal of this page is to enable practitioners&nbsp;in remote sensing of FAW to share success and failures. It is important that we do this collectively to avoid wasted efforts and to pool resources.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by Rimnoma Serge Ouedraogo at January 12, 2021 19 : 56 : 08

    • --- /tmp/diffy20211209-943388-j104gr 2021-12-09 07:10:32.865423732 +0000
    • +++ /tmp/diffy20211209-943388-pm8pdm 2021-12-09 07:10:32.865423732 +0000
    • @@ -1 +0,0 @@
    • -Introduction
    • --- /tmp/diffy20211209-943388-193akhm 2021-12-09 07:10:32.869423759 +0000
    • +++ /tmp/diffy20211209-943388-1i5nmyy 2021-12-09 07:10:32.869423759 +0000
    • @@ -1,9 +0,0 @@
    • -<p><b>Remote sensing</b>&nbsp;is the acquisition of information about an object or phenomenon without making physical contact with the object and thus in contrast to on-site observation, especially the Earth. Remote sensing is used in numerous fields, including geography, land surveying and most Earth Science disciplines (for example, hydrology, ecology,&nbsp;&nbsp;meteorology, oceanography, glaciology, geology); it also has military, intelligence, commercial, economic, planning, and humanitarian applications.</p>
    • -
    • -<p>In this last case remote sensing has been suggested to be useful to track fall armyworm in Africa.&nbsp;</p>
    • -
    • -<p>In current usage, the term &quot;remote sensing&quot; generally refers to the use of satellite- or aircraft-based sensor technologies to detect and classify objects on Earth. Aircraft can include drones.&nbsp;</p>
    • -
    • -<p>The goal of this page is to enable practitioners&nbsp;in remote sensing of FAW to share success and failures. It is important that we do this collectively to avoid wasted efforts and to pool resources.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by chen at October 2, 2020 09 : 03 : 03

    • --- /tmp/diffy20211209-943388-a03deh 2021-12-09 07:10:32.877423813 +0000
    • +++ /tmp/diffy20211209-943388-100a7pt 2021-12-09 07:10:32.877423813 +0000
    • @@ -1 +0,0 @@
    • -PRISE_CABI
    • --- /tmp/diffy20211209-943388-1ymgqk7 2021-12-09 07:10:32.881423840 +0000
    • +++ /tmp/diffy20211209-943388-1cyxsba 2021-12-09 07:10:32.881423840 +0000
    • @@ -1,9 +0,0 @@
    • -<p>CABI recently announced a system for forecasting the <a href="http://edexme.com">risk of pest </a>outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • -
    • -<p>It is not clear from the media attention what the earth observations are. What satellites are being used.&nbsp;There is a document <a href="http://www.iapetus.ac.uk/wp-content/uploads/2018/10/IAP2-18-14_CEH_White.pdf">here</a> about the project.&nbsp; The project says it will use&nbsp; &quot;environmental data from Earth Observation&nbsp;validated by the consortium (e.g. land surface temperature and rainfall), pest phenology data across three different countries (Kenya, Zambia and Ghana) and crowdsourced observations.&quot;</p>
    • -
    • -<p>There are a number of satellites that measure ground temperature and moisture. But since no details have been provided we cannot speculate.&nbsp;</p>
    • -
    • -<p>It is worth stressing that there is no current evidence that PRISE can predict FAW.&nbsp;</p>
    • -
    • -<p>[December 4th, 2018- this needs community editing]</p>

    Edited by chen at October 2, 2020 09 : 03 : 03

    • --- /tmp/diffy20211209-943388-n6atwo 2021-12-09 07:10:32.893423921 +0000
    • +++ /tmp/diffy20211209-943388-1n84z8v 2021-12-09 07:10:32.893423921 +0000
    • @@ -1 +0,0 @@
    • -PRISE_CABI
    • --- /tmp/diffy20211209-943388-x0h4v0 2021-12-09 07:10:32.897423948 +0000
    • +++ /tmp/diffy20211209-943388-18b7kma 2021-12-09 07:10:32.897423948 +0000
    • @@ -1,9 +0,0 @@
    • -<p>CABI recently announced a system for forecasting the <a href="http://edexme.com">risk of pest </a>outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • -
    • -<p>It is not clear from the media attention what the earth observations are. What satellites are being used.&nbsp;There is a document <a href="http://www.iapetus.ac.uk/wp-content/uploads/2018/10/IAP2-18-14_CEH_White.pdf">here</a> about the project.&nbsp; The project says it will use&nbsp; &quot;environmental data from Earth Observation&nbsp;validated by the consortium (e.g. land surface temperature and rainfall), pest phenology data across three different countries (Kenya, Zambia and Ghana) and crowdsourced observations.&quot;</p>
    • -
    • -<p>There are a number of satellites that measure ground temperature and moisture. But since no details have been provided we cannot speculate.&nbsp;</p>
    • -
    • -<p>It is worth stressing that there is no current evidence that PRISE can predict FAW.&nbsp;</p>
    • -
    • -<p>[December 4th, 2018- this needs community editing]</p>

    Edited by chen at October 2, 2020 09 : 02 : 57

    • --- /tmp/diffy20211209-943388-otj6y4 2021-12-09 07:10:32.909424030 +0000
    • +++ /tmp/diffy20211209-943388-wog3cw 2021-12-09 07:10:32.909424030 +0000
    • @@ -1 +0,0 @@
    • -Introduction
    • --- /tmp/diffy20211209-943388-17vuk95 2021-12-09 07:10:32.913424056 +0000
    • +++ /tmp/diffy20211209-943388-8o4i4z 2021-12-09 07:10:32.913424056 +0000
    • @@ -1,9 +0,0 @@
    • -<p><b>Remote sensing</b>&nbsp;is the acquisition of information about an object or phenomenon without making physical contact with the object and thus in contrast to on-site observation, especially the Earth. Remote sensing is used in numerous fields, including geography, land surveying and most Earth Science disciplines (for example, hydrology, ecology,&nbsp;&nbsp;meteorology, oceanography, glaciology, geology); it also has military, intelligence, commercial, economic, planning, and humanitarian applications.</p>
    • -
    • -<p>In this last case remote sensing has been suggested to be useful to track fall armyworm in Africa.&nbsp;</p>
    • -
    • -<p>In current usage, the term &quot;remote sensing&quot; generally refers to the use of satellite- or aircraft-based sensor technologies to detect and classify objects on Earth. Aircraft can include drones.&nbsp;</p>
    • -
    • -<p>The goal of this page is to enable practitioners&nbsp;in remote sensing of FAW to share success and failures. It is important that we do this collectively to avoid wasted efforts and to pool resources.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by chen at October 2, 2020 09 : 02 : 57

  • Change in Description
    • --- /tmp/diffy20211209-943388-15381pf 2021-12-09 07:10:32.925424137 +0000
    • +++ /tmp/diffy20211209-943388-w8pd0q 2021-12-09 07:10:32.925424137 +0000
    • @@ -1,11 +1,11 @@
    • <p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Researchers have&nbsp;successfully identified FAW damage in large homogenous maize fields in North America from satellite images, but the challenge is to build software that can analyse satellite images to spot FAW hotspots in small and highly heterogeneous smallholder fields in&nbsp;Africa. With funding from the UKs Lottery Fund, World Bank&rsquo;s Trust Fund for Statistical Capacity Building (TFSCB), Irish Aid and the US Foundation for Food and Agriculture Research, ProvEye Ltd, an Irish company specialising in the application of AI to remote sensing, and Self Help Africa have been developing&nbsp;developing a machine learning algorithm that can detect the damage caused by the Fall Armyworm (<i>Spodoptera frugiperda</i>) to smallholder maize fields in Southern Africa in satellite images. </span></span></p>
    • <p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Government field staff collected data from 15m x 15m quadrates in geolocated sentinel pure maize fields in Malawi over three seasons, with 3-4 surveys per season. The field data was used to determine which parts of the light spectrum provided the strongest signal for FAW damage in order to develop and&nbsp;test the Random Forest-based algorithm. 15 maize plants were sampled in each quadrate and the damaged was scored on a 0-5 scale.&nbsp; A large amount of data was collected from each site to capture all the factors that could affect reflectance (maize varity, growth stage, soil type, plant population, canopy height, canopy cover, other pests and diseases, water stress, nutrient deficiencies and nutrient applications) and FAW damage levels (crop rotations, previous&nbsp;FAW infestations, neighbouring crops). The project used&nbsp;3.7m resolution, 4 band, satellite images, taken as close as possible to the time of each survey round&nbsp;sourced from Planet Labs.&nbsp;</span></span></p>
    • <p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Of the variables tested by far the most important variable for detecting FAW damage is the standard deviation of&nbsp;Near Infra Red reflectance, distantly followed by the Green Normalised&nbsp;Difference&nbsp;Vegetation Index. This was&nbsp;expected as discolouration of the green leaves of the maize plant, due to the reduction in&nbsp;chlorophyll, is one of the first indicators of FAW infestation and</span></span><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">&nbsp;the NIR band is sensitive to&nbsp;changes in chlorophyll content,&nbsp;however it was surprising that other commonly used indices for&nbsp;plant health, like NDVI,&nbsp;did not rank higher.&nbsp;</span></span></p>
    • <p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">One of the many challenges of using Machine Learning agorithms for this type of work is</span><span style="font-family:Calibri,sans-serif"><span style="font-family:&quot;Times New Roman&quot;,serif">&nbsp;that machine learning algorithms learn best when they have a more or less even number of records for each damage level.&nbsp;For an insect pest like the Fall Armyworm the data will naturally be skewed. At the beginning of the season most of the plants sampled&nbsp;will have little or no FAW damage, by mid-season there will be a more even spread of damage levels, while by the end of season most of the plants will show high levels of damage. To overcome this problem the data had to be resampled to create even data sets. The project adopted the FAW damage scale used by maize breeders&nbsp;which was, with hindsight, inappropriate for remote sensing (no satellite can detect FAW eggs!), so the damage scale data had to be&nbsp;</span></span><span style="font-family:&quot;Times New Roman&quot;,serif">merged into&nbsp;(a) presence and absence and&nbsp;(b) a simplified damage scale (1-4).</span></span></p>
    • <p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Machine Learning algorithms learn from their mistakes and after over 1,000 cycles the ProvEye algorithm can now detect&nbsp;the presence or absence of FAW damage with up to 87% accuracy. &nbsp;Using the&nbsp;simplified damage scale the level of damage can be predicted with 63-69% accuracy based on remote sensing data only, however accuracy of&nbsp;75% can be achieved when field data is included. The critical field variable is crop growth stage. At the v2-v3 stage there is considerable reflectance directly from the soil, and from the soil through the leaf, which creates &quot;noise&quot;. If the algorithm knows the crop growth stage it can compensate for this&nbsp;noise.&nbsp;</span></span></p>
    • -<p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">The success of the this &quot;proof of concept&quot; research lays the foundations for developing&nbsp;remote sensing software that can identify FAW damage hot spots at the landscape level, enabling governments to target scarce control resources on these hotspots and estimate crop losses. The success also indicates that this approach can be used to detect other crop pests and diseases that change the colour of the crop canopy, like banana bunchy top virus.&nbsp; It is important to note that t</span><span style="font-family:Calibri,sans-serif"><span style="font-family:&quot;Times New Roman&quot;,serif">he first stage of this research used maize fields identified by the survey teams. To be usable by government agronomists the software needs to be able to detect maize fields in satellite images so the next stage of the research is to use a &ldquo;Crop Mask&rdquo;, a piece of software that can detect the crop automatically. As the following paragraphs describe, this is not a simple process, but companies like OneSoil and research institutions have made considerable&nbsp;progress in developing crop masks. It is also important to note that this approach only detects crop damage&nbsp;caused by the FAW&nbsp;and cannot, like the CABI approach, make any&nbsp;predictions about where&nbsp;FAW outbreaks may occur.</span></span></span></p>
    • +<p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">The success of the this &quot;proof of concept&quot; research lays the foundations for developing&nbsp;remote sensing software that can identify FAW damage hot spots at the landscape level, enabling governments to target scarce control resources on these hotspots and estimate crop losses. The success also indicates that this approach can be used to detect other crop pests and diseases that change the colour of the crop canopy, like banana bunchy top virus.&nbsp; It is important to note that t</span><span style="font-family:Calibri,sans-serif"><span style="font-family:&quot;Times New Roman&quot;,serif">he first stage of this research used maize fields identified by the survey teams. To be usable by government agronomists the software needs to be able to detect maize fields in satellite images so the next stage of the research is to use a &ldquo;Crop Mask&rdquo;, a piece of software that can detect the crop automatically. As the following paragraphs describe, this is not a simple process, but companies like OneSoil and research institutions have made considerable&nbsp;progress in developing crop masks. It is also important to note that this approach only detects crop damage&nbsp;caused by the FAW&nbsp;and cannot, unlike the CABI approach, make any&nbsp;predictions about where&nbsp;FAW outbreaks may occur.</span></span></span></p>

    Edited by Paul Wagstaff at June 15, 2020 13 : 32 : 24

  • Change in Description
    • --- /tmp/diffy20211209-943388-xsng8q 2021-12-09 07:10:32.973424461 +0000
    • +++ /tmp/diffy20211209-943388-7r7bvt 2021-12-09 07:10:32.973424461 +0000
    • @@ -1,11 +1,11 @@
    • -<p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Researchers have&nbsp;successfully identified FAW damage in large homogenous maize fields in North America from satellite images, but the challenge is to build software that can analyse satellite images to spot FAW hotspots in small and highly heterogeneous smallholder fields in&nbsp;Africa. With funding from the UKs Lottery Fund, The World Bank&#39;s &ldquo;Collaborative Data Innovations for Sustainable Development&rdquo;&nbsp;fund, Irish Aid and the US Foundation for Food and Agriculture Research, ProvEye Ltd, an Irish company specialising in the application of AI to remote sensing, and Self Help Africa have been developing&nbsp;developing a machine learning algorithm that can detect the damage caused by the Fall Armyworm (<i>Spodoptera frugiperda</i>) to smallholder maize fields in Southern Africa in satellite images. </span></span></p>
    • +<p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Researchers have&nbsp;successfully identified FAW damage in large homogenous maize fields in North America from satellite images, but the challenge is to build software that can analyse satellite images to spot FAW hotspots in small and highly heterogeneous smallholder fields in&nbsp;Africa. With funding from the UKs Lottery Fund, World Bank&rsquo;s Trust Fund for Statistical Capacity Building (TFSCB), Irish Aid and the US Foundation for Food and Agriculture Research, ProvEye Ltd, an Irish company specialising in the application of AI to remote sensing, and Self Help Africa have been developing&nbsp;developing a machine learning algorithm that can detect the damage caused by the Fall Armyworm (<i>Spodoptera frugiperda</i>) to smallholder maize fields in Southern Africa in satellite images. </span></span></p>
    • <p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Government field staff collected data from 15m x 15m quadrates in geolocated sentinel pure maize fields in Malawi over three seasons, with 3-4 surveys per season. The field data was used to determine which parts of the light spectrum provided the strongest signal for FAW damage in order to develop and&nbsp;test the Random Forest-based algorithm. 15 maize plants were sampled in each quadrate and the damaged was scored on a 0-5 scale.&nbsp; A large amount of data was collected from each site to capture all the factors that could affect reflectance (maize varity, growth stage, soil type, plant population, canopy height, canopy cover, other pests and diseases, water stress, nutrient deficiencies and nutrient applications) and FAW damage levels (crop rotations, previous&nbsp;FAW infestations, neighbouring crops). The project used&nbsp;3.7m resolution, 4 band, satellite images, taken as close as possible to the time of each survey round&nbsp;sourced from Planet Labs.&nbsp;</span></span></p>
    • <p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Of the variables tested by far the most important variable for detecting FAW damage is the standard deviation of&nbsp;Near Infra Red reflectance, distantly followed by the Green Normalised&nbsp;Difference&nbsp;Vegetation Index. This was&nbsp;expected as discolouration of the green leaves of the maize plant, due to the reduction in&nbsp;chlorophyll, is one of the first indicators of FAW infestation and</span></span><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">&nbsp;the NIR band is sensitive to&nbsp;changes in chlorophyll content,&nbsp;however it was surprising that other commonly used indices for&nbsp;plant health, like NDVI,&nbsp;did not rank higher.&nbsp;</span></span></p>
    • <p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">One of the many challenges of using Machine Learning agorithms for this type of work is</span><span style="font-family:Calibri,sans-serif"><span style="font-family:&quot;Times New Roman&quot;,serif">&nbsp;that machine learning algorithms learn best when they have a more or less even number of records for each damage level.&nbsp;For an insect pest like the Fall Armyworm the data will naturally be skewed. At the beginning of the season most of the plants sampled&nbsp;will have little or no FAW damage, by mid-season there will be a more even spread of damage levels, while by the end of season most of the plants will show high levels of damage. To overcome this problem the data had to be resampled to create even data sets. The project adopted the FAW damage scale used by maize breeders&nbsp;which was, with hindsight, inappropriate for remote sensing (no satellite can detect FAW eggs!), so the damage scale data had to be&nbsp;</span></span><span style="font-family:&quot;Times New Roman&quot;,serif">merged into&nbsp;(a) presence and absence and&nbsp;(b) a simplified damage scale (1-4).</span></span></p>
    • <p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Machine Learning algorithms learn from their mistakes and after over 1,000 cycles the ProvEye algorithm can now detect&nbsp;the presence or absence of FAW damage with up to 87% accuracy. &nbsp;Using the&nbsp;simplified damage scale the level of damage can be predicted with 63-69% accuracy based on remote sensing data only, however accuracy of&nbsp;75% can be achieved when field data is included. The critical field variable is crop growth stage. At the v2-v3 stage there is considerable reflectance directly from the soil, and from the soil through the leaf, which creates &quot;noise&quot;. If the algorithm knows the crop growth stage it can compensate for this&nbsp;noise.&nbsp;</span></span></p>
    • <p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">The success of the this &quot;proof of concept&quot; research lays the foundations for developing&nbsp;remote sensing software that can identify FAW damage hot spots at the landscape level, enabling governments to target scarce control resources on these hotspots and estimate crop losses. The success also indicates that this approach can be used to detect other crop pests and diseases that change the colour of the crop canopy, like banana bunchy top virus.&nbsp; It is important to note that t</span><span style="font-family:Calibri,sans-serif"><span style="font-family:&quot;Times New Roman&quot;,serif">he first stage of this research used maize fields identified by the survey teams. To be usable by government agronomists the software needs to be able to detect maize fields in satellite images so the next stage of the research is to use a &ldquo;Crop Mask&rdquo;, a piece of software that can detect the crop automatically. As the following paragraphs describe, this is not a simple process, but companies like OneSoil and research institutions have made considerable&nbsp;progress in developing crop masks. It is also important to note that this approach only detects crop damage&nbsp;caused by the FAW&nbsp;and cannot, like the CABI approach, make any&nbsp;predictions about where&nbsp;FAW outbreaks may occur.</span></span></span></p>

    Edited by Paul Wagstaff at June 15, 2020 12 : 56 : 28

    • --- /tmp/diffy20211209-943388-pakw92 2021-12-09 07:10:33.013424731 +0000
    • +++ /tmp/diffy20211209-943388-1mwgisx 2021-12-09 07:10:33.013424731 +0000
    • @@ -1 +0,0 @@
    • -The problem of intercropping and weeds
    • --- /tmp/diffy20211209-943388-13r2gl 2021-12-09 07:10:33.017424759 +0000
    • +++ /tmp/diffy20211209-943388-6ysvh4 2021-12-09 07:10:33.017424759 +0000
    • @@ -1,29 +0,0 @@
    • -<p>Before proceeding to discuss how remote sensing could help in Africa to monitor and track FAW it is critical to appreciate the reality of what most smallholder farmer fields in Africa are: they are small (&lt;2ha), with irregular boundaries and with extensive polyculture and weeds. That is not to say the continent does not have regular shaped fields that are monocrop and free of weeds- but the majority are not. This presents a major challenge to remote sensing- how can the camera on a satellite tell the difference between maize versus other crops/weeds. And if it does, how can it determine if the maize has FAW?&nbsp;</p>
    • -
    • -<p>Here is a picture of a&nbsp;field in Western&nbsp;Kenya from Google maps.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p><img alt="" longdesc="Google satellite map view of Western Kenya " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/195/content_Screen_Shot_2018-12-04_at_10.06.25_PM.png" style="width: 600px; height: 408px;" /></p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>The point is the location that Dr John Chelal of Eldoret University used the PlantVillage Nuru app on December 4th 2018. Below is a picture he took from ground level&nbsp;</p>
    • -
    • -<p><img alt="" longdesc="1 month old intercropped with cassava with FAW damaged maize" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/196/content_IMG-20181204-WA0000.jpg" style="width: 300px; height: 400px;" /></p>
    • -
    • -<p>The challenge then is telling which crop is which.&nbsp;</p>
    • -
    • -<p>Below is an image of 3m resolution Planet.com from Western&nbsp;Kenya. It is not the same field but it is a field with maize and cassava, and weeds. The colors are because the analysis is an index called NDVI (normalized difference vegetation index) that is commonly used. This is going to be hard to distinguish between crops.</p>
    • -
    • -<p><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/197/content_Screen_Shot_2018-12-04_at_10.12.46_PM.png" style="width: 300px; height: 215px;" /></p>
    • -
    • -<p>Below is the same field taken with a drone at 60m captured by the Hughes Lab. Even at this much closer distance distinguishing which crop is which is hard/</p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>&nbsp;<img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/198/content_Screen_Shot_2018-12-04_at_10.16.14_PM.png" style="width: 300px; height: 330px;" /></p>
    • -
    • -<p>The issue of polyculture, weeds and irregular&nbsp;boundaries needs to be considered closely when advocating the use of remote sensing.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by Paul Wagstaff at June 15, 2020 07 : 41 : 44

    • --- /tmp/diffy20211209-943388-wl9ohh 2021-12-09 07:10:33.025424813 +0000
    • +++ /tmp/diffy20211209-943388-ks5lph 2021-12-09 07:10:33.025424813 +0000
    • @@ -1 +0,0 @@
    • -Drones
    • --- /tmp/diffy20211209-943388-czssz4 2021-12-09 07:10:33.029424839 +0000
    • +++ /tmp/diffy20211209-943388-1rcf635 2021-12-09 07:10:33.029424839 +0000
    • @@ -1,26 +0,0 @@
    • -<p>A few groups have explored the use of drones for FAW. The Hughes Lab at Penn State tested different heights&nbsp;over maize field from which human observers can detect FAW holes. They flew a Phantom&nbsp;D4 drone with a standard 4K camera. The determined that the drone had to be no more than 10m above the crop. Below are some example fields</p>
    • -
    • -<table border="1" cellpadding="1" cellspacing="1" style="width:800px;">
    • - <tbody>
    • - <tr>
    • - <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/200/content_Screen_Shot_2018-12-04_at_10.46.25_PM.png" style="width: 400px; height: 278px;" /></td>
    • - <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/201/content_Screen_Shot_2018-12-04_at_10.46.19_PM.png" style="width: 400px; height: 279px;" /></td>
    • - <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/202/content_Screen_Shot_2018-12-04_at_10.45.38_PM.png" style="width: 400px; height: 274px;" /></td>
    • - </tr>
    • - </tbody>
    • -</table>
    • -
    • -<p>&nbsp;One possible tool is a multi-spectral camera. We have flow the RedEdge camera a lot. This has 5 different bands and the data can be combined into different indices, for example, NDVI.</p>
    • -
    • -<table border="1" cellpadding="1" cellspacing="1" style="width:500px;">
    • - <tbody>
    • - <tr>
    • - <td><img alt="" longdesc="Rededge camera on drone " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/203/content_Screen_Shot_2018-12-04_at_10.50.00_PM.png" style="width: 400px; height: 324px;" /></td>
    • - <td><img alt="" longdesc="Rededge imagery by bands and the NDVI image " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/204/content_Screen_Shot_2018-12-04_at_10.49.53_PM.png" style="width: 400px; height: 268px;" /></td>
    • - </tr>
    • - </tbody>
    • -</table>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>[Editing: please add you efforts on drone work]</p>

    Edited by Paul Wagstaff at June 15, 2020 07 : 41 : 44

  • Change in Description
    • --- /tmp/diffy20211209-943388-5gruan 2021-12-09 07:10:33.041424921 +0000
    • +++ /tmp/diffy20211209-943388-1suzvct 2021-12-09 07:10:33.041424921 +0000
    • @@ -0,0 +1,11 @@
    • +<p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Researchers have&nbsp;successfully identified FAW damage in large homogenous maize fields in North America from satellite images, but the challenge is to build software that can analyse satellite images to spot FAW hotspots in small and highly heterogeneous smallholder fields in&nbsp;Africa. With funding from the UKs Lottery Fund, The World Bank&#39;s &ldquo;Collaborative Data Innovations for Sustainable Development&rdquo;&nbsp;fund, Irish Aid and the US Foundation for Food and Agriculture Research, ProvEye Ltd, an Irish company specialising in the application of AI to remote sensing, and Self Help Africa have been developing&nbsp;developing a machine learning algorithm that can detect the damage caused by the Fall Armyworm (<i>Spodoptera frugiperda</i>) to smallholder maize fields in Southern Africa in satellite images. </span></span></p>
    • +
    • +<p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Government field staff collected data from 15m x 15m quadrates in geolocated sentinel pure maize fields in Malawi over three seasons, with 3-4 surveys per season. The field data was used to determine which parts of the light spectrum provided the strongest signal for FAW damage in order to develop and&nbsp;test the Random Forest-based algorithm. 15 maize plants were sampled in each quadrate and the damaged was scored on a 0-5 scale.&nbsp; A large amount of data was collected from each site to capture all the factors that could affect reflectance (maize varity, growth stage, soil type, plant population, canopy height, canopy cover, other pests and diseases, water stress, nutrient deficiencies and nutrient applications) and FAW damage levels (crop rotations, previous&nbsp;FAW infestations, neighbouring crops). The project used&nbsp;3.7m resolution, 4 band, satellite images, taken as close as possible to the time of each survey round&nbsp;sourced from Planet Labs.&nbsp;</span></span></p>
    • +
    • +<p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Of the variables tested by far the most important variable for detecting FAW damage is the standard deviation of&nbsp;Near Infra Red reflectance, distantly followed by the Green Normalised&nbsp;Difference&nbsp;Vegetation Index. This was&nbsp;expected as discolouration of the green leaves of the maize plant, due to the reduction in&nbsp;chlorophyll, is one of the first indicators of FAW infestation and</span></span><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">&nbsp;the NIR band is sensitive to&nbsp;changes in chlorophyll content,&nbsp;however it was surprising that other commonly used indices for&nbsp;plant health, like NDVI,&nbsp;did not rank higher.&nbsp;</span></span></p>
    • +
    • +<p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">One of the many challenges of using Machine Learning agorithms for this type of work is</span><span style="font-family:Calibri,sans-serif"><span style="font-family:&quot;Times New Roman&quot;,serif">&nbsp;that machine learning algorithms learn best when they have a more or less even number of records for each damage level.&nbsp;For an insect pest like the Fall Armyworm the data will naturally be skewed. At the beginning of the season most of the plants sampled&nbsp;will have little or no FAW damage, by mid-season there will be a more even spread of damage levels, while by the end of season most of the plants will show high levels of damage. To overcome this problem the data had to be resampled to create even data sets. The project adopted the FAW damage scale used by maize breeders&nbsp;which was, with hindsight, inappropriate for remote sensing (no satellite can detect FAW eggs!), so the damage scale data had to be&nbsp;</span></span><span style="font-family:&quot;Times New Roman&quot;,serif">merged into&nbsp;(a) presence and absence and&nbsp;(b) a simplified damage scale (1-4).</span></span></p>
    • +
    • +<p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Machine Learning algorithms learn from their mistakes and after over 1,000 cycles the ProvEye algorithm can now detect&nbsp;the presence or absence of FAW damage with up to 87% accuracy. &nbsp;Using the&nbsp;simplified damage scale the level of damage can be predicted with 63-69% accuracy based on remote sensing data only, however accuracy of&nbsp;75% can be achieved when field data is included. The critical field variable is crop growth stage. At the v2-v3 stage there is considerable reflectance directly from the soil, and from the soil through the leaf, which creates &quot;noise&quot;. If the algorithm knows the crop growth stage it can compensate for this&nbsp;noise.&nbsp;</span></span></p>
    • +
    • +<p><span style="font-size:11.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">The success of the this &quot;proof of concept&quot; research lays the foundations for developing&nbsp;remote sensing software that can identify FAW damage hot spots at the landscape level, enabling governments to target scarce control resources on these hotspots and estimate crop losses. The success also indicates that this approach can be used to detect other crop pests and diseases that change the colour of the crop canopy, like banana bunchy top virus.&nbsp; It is important to note that t</span><span style="font-family:Calibri,sans-serif"><span style="font-family:&quot;Times New Roman&quot;,serif">he first stage of this research used maize fields identified by the survey teams. To be usable by government agronomists the software needs to be able to detect maize fields in satellite images so the next stage of the research is to use a &ldquo;Crop Mask&rdquo;, a piece of software that can detect the crop automatically. As the following paragraphs describe, this is not a simple process, but companies like OneSoil and research institutions have made considerable&nbsp;progress in developing crop masks. It is also important to note that this approach only detects crop damage&nbsp;caused by the FAW&nbsp;and cannot, like the CABI approach, make any&nbsp;predictions about where&nbsp;FAW outbreaks may occur.</span></span></span></p>

    Edited by Paul Wagstaff at June 12, 2020 09 : 50 : 09

    • --- /tmp/diffy20211209-943388-1tx0c32 2021-12-09 07:10:33.053425002 +0000
    • +++ /tmp/diffy20211209-943388-1gp4mbg 2021-12-09 07:10:33.053425002 +0000
    • @@ -1 +0,0 @@
    • -Introduction
    • --- /tmp/diffy20211209-943388-1cvqzlg 2021-12-09 07:10:33.053425002 +0000
    • +++ /tmp/diffy20211209-943388-fgh6bs 2021-12-09 07:10:33.053425002 +0000
    • @@ -1,9 +0,0 @@
    • -<p><b>Remote sensing</b>&nbsp;is the acquisition of information about an object or phenomenon without making physical contact with the object and thus in contrast to on-site observation, especially the Earth. Remote sensing is used in numerous fields, including geography, land surveying and most Earth Science disciplines (for example, hydrology, ecology,&nbsp;&nbsp;meteorology, oceanography, glaciology, geology); it also has military, intelligence, commercial, economic, planning, and humanitarian applications.</p>
    • -
    • -<p>In this last case remote sensing has been suggested to be useful to track fall armyworm in Africa.&nbsp;</p>
    • -
    • -<p>In current usage, the term &quot;remote sensing&quot; generally refers to the use of satellite- or aircraft-based sensor technologies to detect and classify objects on Earth. Aircraft can include drones.&nbsp;</p>
    • -
    • -<p>The goal of this page is to enable practitioners&nbsp;in remote sensing of FAW to share success and failures. It is important that we do this collectively to avoid wasted efforts and to pool resources.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by revyh at May 21, 2020 05 : 50 : 36

    • --- /tmp/diffy20211209-943388-10objlh 2021-12-09 07:10:33.065425082 +0000
    • +++ /tmp/diffy20211209-943388-q1oxq9 2021-12-09 07:10:33.065425082 +0000
    • @@ -1 +0,0 @@
    • -PRISE_CABI
    • --- /tmp/diffy20211209-943388-1rdpiz1 2021-12-09 07:10:33.069425110 +0000
    • +++ /tmp/diffy20211209-943388-og994z 2021-12-09 07:10:33.069425110 +0000
    • @@ -1,9 +0,0 @@
    • -<p>CABI recently announced a system for forecasting the <a href="http://edexme.com">risk of pest </a>outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • -
    • -<p>It is not clear from the media attention what the earth observations are. What satellites are being used.&nbsp;There is a document <a href="http://www.iapetus.ac.uk/wp-content/uploads/2018/10/IAP2-18-14_CEH_White.pdf">here</a> about the project.&nbsp; The project says it will use&nbsp; &quot;environmental data from Earth Observation&nbsp;validated by the consortium (e.g. land surface temperature and rainfall), pest phenology data across three different countries (Kenya, Zambia and Ghana) and crowdsourced observations.&quot;</p>
    • -
    • -<p>There are a number of satellites that measure ground temperature and moisture. But since no details have been provided we cannot speculate.&nbsp;</p>
    • -
    • -<p>It is worth stressing that there is no current evidence that PRISE can predict FAW.&nbsp;</p>
    • -
    • -<p>[December 4th, 2018- this needs community editing]</p>

    Edited by revyh at May 21, 2020 05 : 50 : 36

  • Change in Description
    • --- /tmp/diffy20211209-943388-1b73tz3 2021-12-09 07:10:33.077425164 +0000
    • +++ /tmp/diffy20211209-943388-pfdu8e 2021-12-09 07:10:33.077425164 +0000
    • @@ -1,9 +1,9 @@
    • -<p>CABI recently announced a system for forecasting the risk of pest outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • +<p>CABI recently announced a system for forecasting the <a href="http://edexme.com">risk of pest </a>outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • <p>It is not clear from the media attention what the earth observations are. What satellites are being used.&nbsp;There is a document <a href="http://www.iapetus.ac.uk/wp-content/uploads/2018/10/IAP2-18-14_CEH_White.pdf">here</a> about the project.&nbsp; The project says it will use&nbsp; &quot;environmental data from Earth Observation&nbsp;validated by the consortium (e.g. land surface temperature and rainfall), pest phenology data across three different countries (Kenya, Zambia and Ghana) and crowdsourced observations.&quot;</p>
    • <p>There are a number of satellites that measure ground temperature and moisture. But since no details have been provided we cannot speculate.&nbsp;</p>
    • <p>It is worth stressing that there is no current evidence that PRISE can predict FAW.&nbsp;</p>
    • <p>[December 4th, 2018- this needs community editing]</p>

    Edited by Dinesh at March 23, 2020 05 : 53 : 11

    • --- /tmp/diffy20211209-943388-me4aqm 2021-12-09 07:10:33.113425407 +0000
    • +++ /tmp/diffy20211209-943388-1s61brn 2021-12-09 07:10:33.113425407 +0000
    • @@ -1 +0,0 @@
    • -PRISE_CABI
    • --- /tmp/diffy20211209-943388-1g77lsg 2021-12-09 07:10:33.113425407 +0000
    • +++ /tmp/diffy20211209-943388-1tqtspc 2021-12-09 07:10:33.113425407 +0000
    • @@ -1,9 +0,0 @@
    • -<p>CABI recently announced a system for forecasting the risk of pest outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • -
    • -<p>It is not clear from the media attention what the earth observations are. What satellites are being used.&nbsp;There is a document <a href="http://www.iapetus.ac.uk/wp-content/uploads/2018/10/IAP2-18-14_CEH_White.pdf">here</a> about the project.&nbsp; The project says it will use&nbsp; &quot;environmental data from Earth Observation&nbsp;validated by the consortium (e.g. land surface temperature and rainfall), pest phenology data across three different countries (Kenya, Zambia and Ghana) and crowdsourced observations.&quot;</p>
    • -
    • -<p>There are a number of satellites that measure ground temperature and moisture. But since no details have been provided we cannot speculate.&nbsp;</p>
    • -
    • -<p>It is worth stressing that there is no current evidence that PRISE can predict FAW.&nbsp;</p>
    • -
    • -<p>[December 4th, 2018- this needs community editing]</p>

    Edited by test at January 27, 2020 09 : 33 : 03

    • --- /tmp/diffy20211209-943388-1cfl7br 2021-12-09 07:10:33.129425515 +0000
    • +++ /tmp/diffy20211209-943388-ra6cr2 2021-12-09 07:10:33.129425515 +0000
    • @@ -1 +0,0 @@
    • -Introduction
    • --- /tmp/diffy20211209-943388-1l17cnb 2021-12-09 07:10:33.133425542 +0000
    • +++ /tmp/diffy20211209-943388-1seb4cv 2021-12-09 07:10:33.133425542 +0000
    • @@ -1,9 +0,0 @@
    • -<p><b>Remote sensing</b>&nbsp;is the acquisition of information about an object or phenomenon without making physical contact with the object and thus in contrast to on-site observation, especially the Earth. Remote sensing is used in numerous fields, including geography, land surveying and most Earth Science disciplines (for example, hydrology, ecology,&nbsp;&nbsp;meteorology, oceanography, glaciology, geology); it also has military, intelligence, commercial, economic, planning, and humanitarian applications.</p>
    • -
    • -<p>In this last case remote sensing has been suggested to be useful to track fall armyworm in Africa.&nbsp;</p>
    • -
    • -<p>In current usage, the term &quot;remote sensing&quot; generally refers to the use of satellite- or aircraft-based sensor technologies to detect and classify objects on Earth. Aircraft can include drones.&nbsp;</p>
    • -
    • -<p>The goal of this page is to enable practitioners&nbsp;in remote sensing of FAW to share success and failures. It is important that we do this collectively to avoid wasted efforts and to pool resources.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by test at January 27, 2020 09 : 33 : 03

    • --- /tmp/diffy20211209-943388-d4l71w 2021-12-09 07:10:33.141425596 +0000
    • +++ /tmp/diffy20211209-943388-1cap1da 2021-12-09 07:10:33.141425596 +0000
    • @@ -1 +0,0 @@
    • -PRISE_CABI
    • --- /tmp/diffy20211209-943388-pomlfi 2021-12-09 07:10:33.145425623 +0000
    • +++ /tmp/diffy20211209-943388-1ufwsyj 2021-12-09 07:10:33.145425623 +0000
    • @@ -1,9 +0,0 @@
    • -<p>CABI recently announced a system for forecasting the risk of pest outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • -
    • -<p>It is not clear from the media attention what the earth observations are. What satellites are being used.&nbsp;There is a document <a href="http://www.iapetus.ac.uk/wp-content/uploads/2018/10/IAP2-18-14_CEH_White.pdf">here</a> about the project.&nbsp; The project says it will use&nbsp; &quot;environmental data from Earth Observation&nbsp;validated by the consortium (e.g. land surface temperature and rainfall), pest phenology data across three different countries (Kenya, Zambia and Ghana) and crowdsourced observations.&quot;</p>
    • -
    • -<p>There are a number of satellites that measure ground temperature and moisture. But since no details have been provided we cannot speculate.&nbsp;</p>
    • -
    • -<p>It is worth stressing that there is no current evidence that PRISE can predict FAW.&nbsp;</p>
    • -
    • -<p>[December 4th, 2018- this needs community editing]</p>

    Edited by kelvin nyongesa at August 5, 2019 08 : 50 : 15

    • --- /tmp/diffy20211209-943388-89k784 2021-12-09 07:10:33.157425704 +0000
    • +++ /tmp/diffy20211209-943388-exnv3y 2021-12-09 07:10:33.157425704 +0000
    • @@ -1 +0,0 @@
    • -The problem of intercropping and weeds
    • --- /tmp/diffy20211209-943388-18dqgs4 2021-12-09 07:10:33.157425704 +0000
    • +++ /tmp/diffy20211209-943388-znsxtp 2021-12-09 07:10:33.157425704 +0000
    • @@ -1,29 +0,0 @@
    • -<p>Before proceeding to discuss how remote sensing could help in Africa to monitor and track FAW it is critical to appreciate the reality of what most smallholder farmer fields in Africa are: they are small (&lt;2ha), with irregular boundaries and with extensive polyculture and weeds. That is not to say the continent does not have regular shaped fields that are monocrop and free of weeds- but the majority are not. This presents a major challenge to remote sensing- how can the camera on a satellite tell the difference between maize versus other crops/weeds. And if it does, how can it determine if the maize has FAW?&nbsp;</p>
    • -
    • -<p>Here is a picture of a&nbsp;field in Western&nbsp;Kenya from Google maps.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p><img alt="" longdesc="Google satellite map view of Western Kenya " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/195/content_Screen_Shot_2018-12-04_at_10.06.25_PM.png" style="width: 600px; height: 408px;" /></p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>The point is the location that Dr John Chelal of Eldoret University used the PlantVillage Nuru app on December 4th 2018. Below is a picture he took from ground level&nbsp;</p>
    • -
    • -<p><img alt="" longdesc="1 month old intercropped with cassava with FAW damaged maize" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/196/content_IMG-20181204-WA0000.jpg" style="width: 300px; height: 400px;" /></p>
    • -
    • -<p>The challenge then is telling which crop is which.&nbsp;</p>
    • -
    • -<p>Below is an image of 3m resolution Planet.com from Western&nbsp;Kenya. It is not the same field but it is a field with maize and cassava, and weeds. The colors are because the analysis is an index called NDVI (normalized difference vegetation index) that is commonly used. This is going to be hard to distinguish between crops.</p>
    • -
    • -<p><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/197/content_Screen_Shot_2018-12-04_at_10.12.46_PM.png" style="width: 300px; height: 215px;" /></p>
    • -
    • -<p>Below is the same field taken with a drone at 60m captured by the Hughes Lab. Even at this much closer distance distinguishing which crop is which is hard/</p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>&nbsp;<img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/198/content_Screen_Shot_2018-12-04_at_10.16.14_PM.png" style="width: 300px; height: 330px;" /></p>
    • -
    • -<p>The issue of polyculture, weeds and irregular&nbsp;boundaries needs to be considered closely when advocating the use of remote sensing.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by kelvin nyongesa at August 5, 2019 08 : 50 : 15

    • --- /tmp/diffy20211209-943388-1lemr7p 2021-12-09 07:10:33.165425758 +0000
    • +++ /tmp/diffy20211209-943388-9wbydc 2021-12-09 07:10:33.165425758 +0000
    • @@ -1 +0,0 @@
    • -Drones
    • --- /tmp/diffy20211209-943388-1br3uew 2021-12-09 07:10:33.169425785 +0000
    • +++ /tmp/diffy20211209-943388-11793ud 2021-12-09 07:10:33.169425785 +0000
    • @@ -1,26 +0,0 @@
    • -<p>A few groups have explored the use of drones for FAW. The Hughes Lab at Penn State tested different heights&nbsp;over maize field from which human observers can detect FAW holes. They flew a Phantom&nbsp;D4 drone with a standard 4K camera. The determined that the drone had to be no more than 10m above the crop. Below are some example fields</p>
    • -
    • -<table border="1" cellpadding="1" cellspacing="1" style="width:800px;">
    • - <tbody>
    • - <tr>
    • - <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/200/content_Screen_Shot_2018-12-04_at_10.46.25_PM.png" style="width: 400px; height: 278px;" /></td>
    • - <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/201/content_Screen_Shot_2018-12-04_at_10.46.19_PM.png" style="width: 400px; height: 279px;" /></td>
    • - <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/202/content_Screen_Shot_2018-12-04_at_10.45.38_PM.png" style="width: 400px; height: 274px;" /></td>
    • - </tr>
    • - </tbody>
    • -</table>
    • -
    • -<p>&nbsp;One possible tool is a multi-spectral camera. We have flow the RedEdge camera a lot. This has 5 different bands and the data can be combined into different indices, for example, NDVI.</p>
    • -
    • -<table border="1" cellpadding="1" cellspacing="1" style="width:500px;">
    • - <tbody>
    • - <tr>
    • - <td><img alt="" longdesc="Rededge camera on drone " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/203/content_Screen_Shot_2018-12-04_at_10.50.00_PM.png" style="width: 400px; height: 324px;" /></td>
    • - <td><img alt="" longdesc="Rededge imagery by bands and the NDVI image " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/204/content_Screen_Shot_2018-12-04_at_10.49.53_PM.png" style="width: 400px; height: 268px;" /></td>
    • - </tr>
    • - </tbody>
    • -</table>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>[Editing: please add you efforts on drone work]</p>

    Edited by Ravi Kumar at April 22, 2019 11 : 47 : 24

    • --- /tmp/diffy20211209-943388-1g6l0fb 2021-12-09 07:10:33.185425893 +0000
    • +++ /tmp/diffy20211209-943388-1c9309z 2021-12-09 07:10:33.185425893 +0000
    • @@ -1 +0,0 @@
    • -PRISE_CABI
    • --- /tmp/diffy20211209-943388-lq1mk6 2021-12-09 07:10:33.189425919 +0000
    • +++ /tmp/diffy20211209-943388-sbmxjx 2021-12-09 07:10:33.189425919 +0000
    • @@ -1,9 +0,0 @@
    • -<p>CABI recently announced a system for forecasting the risk of pest outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • -
    • -<p>It is not clear from the media attention what the earth observations are. What satellites are being used.&nbsp;There is a document <a href="http://www.iapetus.ac.uk/wp-content/uploads/2018/10/IAP2-18-14_CEH_White.pdf">here</a> about the project.&nbsp; The project says it will use&nbsp; &quot;environmental data from Earth Observation&nbsp;validated by the consortium (e.g. land surface temperature and rainfall), pest phenology data across three different countries (Kenya, Zambia and Ghana) and crowdsourced observations.&quot;</p>
    • -
    • -<p>There are a number of satellites that measure ground temperature and moisture. But since no details have been provided we cannot speculate.&nbsp;</p>
    • -
    • -<p>It is worth stressing that there is no current evidence that PRISE can predict FAW.&nbsp;</p>
    • -
    • -<p>[December 4th, 2018- this needs community editing]</p>

    Edited by Ravi Kumar at April 22, 2019 11 : 47 : 24

    • --- /tmp/diffy20211209-943388-1gup6zt 2021-12-09 07:10:33.197425974 +0000
    • +++ /tmp/diffy20211209-943388-cx5jbq 2021-12-09 07:10:33.197425974 +0000
    • @@ -1 +0,0 @@
    • -PRISE_CABI
    • --- /tmp/diffy20211209-943388-bqmohb 2021-12-09 07:10:33.197425974 +0000
    • +++ /tmp/diffy20211209-943388-k8frp0 2021-12-09 07:10:33.197425974 +0000
    • @@ -1,9 +0,0 @@
    • -<p>CABI recently announced a system for forecasting the risk of pest outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • -
    • -<p>It is not clear from the media attention what the earth observations are. What satellites are being used.&nbsp;There is a document <a href="http://www.iapetus.ac.uk/wp-content/uploads/2018/10/IAP2-18-14_CEH_White.pdf">here</a> about the project.&nbsp; The project says it will use&nbsp; &quot;environmental data from Earth Observation&nbsp;validated by the consortium (e.g. land surface temperature and rainfall), pest phenology data across three different countries (Kenya, Zambia and Ghana) and crowdsourced observations.&quot;</p>
    • -
    • -<p>There are a number of satellites that measure ground temperature and moisture. But since no details have been provided we cannot speculate.&nbsp;</p>
    • -
    • -<p>It is worth stressing that there is no current evidence that PRISE can predict FAW.&nbsp;</p>
    • -
    • -<p>[December 4th, 2018- this needs community editing]</p>

    Edited by Ravi Kumar at April 22, 2019 11 : 47 : 15

    • --- /tmp/diffy20211209-943388-1soff0v 2021-12-09 07:10:33.205426028 +0000
    • +++ /tmp/diffy20211209-943388-q2g233 2021-12-09 07:10:33.205426028 +0000
    • @@ -1 +0,0 @@
    • -Drones
    • --- /tmp/diffy20211209-943388-1dzxs1v 2021-12-09 07:10:33.209426054 +0000
    • +++ /tmp/diffy20211209-943388-1ftpw4c 2021-12-09 07:10:33.209426054 +0000
    • @@ -1,26 +0,0 @@
    • -<p>A few groups have explored the use of drones for FAW. The Hughes Lab at Penn State tested different heights&nbsp;over maize field from which human observers can detect FAW holes. They flew a Phantom&nbsp;D4 drone with a standard 4K camera. The determined that the drone had to be no more than 10m above the crop. Below are some example fields</p>
    • -
    • -<table border="1" cellpadding="1" cellspacing="1" style="width:800px;">
    • - <tbody>
    • - <tr>
    • - <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/200/content_Screen_Shot_2018-12-04_at_10.46.25_PM.png" style="width: 400px; height: 278px;" /></td>
    • - <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/201/content_Screen_Shot_2018-12-04_at_10.46.19_PM.png" style="width: 400px; height: 279px;" /></td>
    • - <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/202/content_Screen_Shot_2018-12-04_at_10.45.38_PM.png" style="width: 400px; height: 274px;" /></td>
    • - </tr>
    • - </tbody>
    • -</table>
    • -
    • -<p>&nbsp;One possible tool is a multi-spectral camera. We have flow the RedEdge camera a lot. This has 5 different bands and the data can be combined into different indices, for example, NDVI.</p>
    • -
    • -<table border="1" cellpadding="1" cellspacing="1" style="width:500px;">
    • - <tbody>
    • - <tr>
    • - <td><img alt="" longdesc="Rededge camera on drone " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/203/content_Screen_Shot_2018-12-04_at_10.50.00_PM.png" style="width: 400px; height: 324px;" /></td>
    • - <td><img alt="" longdesc="Rededge imagery by bands and the NDVI image " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/204/content_Screen_Shot_2018-12-04_at_10.49.53_PM.png" style="width: 400px; height: 268px;" /></td>
    • - </tr>
    • - </tbody>
    • -</table>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>[Editing: please add you efforts on drone work]</p>

    Edited by Ravi Kumar at April 22, 2019 11 : 47 : 15

  • Change in Description
    • --- /tmp/diffy20211209-943388-1i9rf61 2021-12-09 07:10:33.217426109 +0000
    • +++ /tmp/diffy20211209-943388-12hrzzq 2021-12-09 07:10:33.217426109 +0000
    • @@ -1,24 +1,26 @@
    • -<p>A few groups have explored the use of drones for FAW. The Hughes Lab at Penn State tested different heights&nbsp;over maize field from which human observers can detect FAW holes. They flew a Phantom&nbsp;D4 drone with standard 4K camera. The determined that the drone had to be no more than 10m above the crop. Below are some example fields</p>
    • +<p>A few groups have explored the use of drones for FAW. The Hughes Lab at Penn State tested different heights&nbsp;over maize field from which human observers can detect FAW holes. They flew a Phantom&nbsp;D4 drone with a standard 4K camera. The determined that the drone had to be no more than 10m above the crop. Below are some example fields</p>
    • <table border="1" cellpadding="1" cellspacing="1" style="width:800px;">
    • <tbody>
    • <tr>
    • <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/200/content_Screen_Shot_2018-12-04_at_10.46.25_PM.png" style="width: 400px; height: 278px;" /></td>
    • <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/201/content_Screen_Shot_2018-12-04_at_10.46.19_PM.png" style="width: 400px; height: 279px;" /></td>
    • <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/202/content_Screen_Shot_2018-12-04_at_10.45.38_PM.png" style="width: 400px; height: 274px;" /></td>
    • </tr>
    • </tbody>
    • </table>
    • -<p>&nbsp;One possible tool is a multi-spectral camera. We have flow the RedEdge camera a lot. This&nbsp;</p>
    • +<p>&nbsp;One possible tool is a multi-spectral camera. We have flow the RedEdge camera a lot. This has 5 different bands and the data can be combined into different indices, for example, NDVI.</p>
    • <table border="1" cellpadding="1" cellspacing="1" style="width:500px;">
    • <tbody>
    • <tr>
    • <td><img alt="" longdesc="Rededge camera on drone " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/203/content_Screen_Shot_2018-12-04_at_10.50.00_PM.png" style="width: 400px; height: 324px;" /></td>
    • - <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/204/content_Screen_Shot_2018-12-04_at_10.49.53_PM.png" style="width: 400px; height: 268px;" /></td>
    • + <td><img alt="" longdesc="Rededge imagery by bands and the NDVI image " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/204/content_Screen_Shot_2018-12-04_at_10.49.53_PM.png" style="width: 400px; height: 268px;" /></td>
    • </tr>
    • </tbody>
    • </table>
    • <p>&nbsp;</p>
    • +
    • +<p>[Editing: please add you efforts on drone work]</p>

    Edited by David Hughes at December 4, 2018 21 : 54 : 46

  • Change in Description
    • --- /tmp/diffy20211209-943388-1uabyl7 2021-12-09 07:10:33.265426433 +0000
    • +++ /tmp/diffy20211209-943388-18jb4rf 2021-12-09 07:10:33.265426433 +0000
    • @@ -1,24 +1,24 @@
    • <p>A few groups have explored the use of drones for FAW. The Hughes Lab at Penn State tested different heights&nbsp;over maize field from which human observers can detect FAW holes. They flew a Phantom&nbsp;D4 drone with standard 4K camera. The determined that the drone had to be no more than 10m above the crop. Below are some example fields</p>
    • -<table border="1" cellpadding="1" cellspacing="1" style="width:500px;">
    • +<table border="1" cellpadding="1" cellspacing="1" style="width:800px;">
    • <tbody>
    • <tr>
    • <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/200/content_Screen_Shot_2018-12-04_at_10.46.25_PM.png" style="width: 400px; height: 278px;" /></td>
    • <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/201/content_Screen_Shot_2018-12-04_at_10.46.19_PM.png" style="width: 400px; height: 279px;" /></td>
    • <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/202/content_Screen_Shot_2018-12-04_at_10.45.38_PM.png" style="width: 400px; height: 274px;" /></td>
    • </tr>
    • </tbody>
    • </table>
    • <p>&nbsp;One possible tool is a multi-spectral camera. We have flow the RedEdge camera a lot. This&nbsp;</p>
    • <table border="1" cellpadding="1" cellspacing="1" style="width:500px;">
    • <tbody>
    • <tr>
    • <td><img alt="" longdesc="Rededge camera on drone " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/203/content_Screen_Shot_2018-12-04_at_10.50.00_PM.png" style="width: 400px; height: 324px;" /></td>
    • <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/204/content_Screen_Shot_2018-12-04_at_10.49.53_PM.png" style="width: 400px; height: 268px;" /></td>
    • </tr>
    • </tbody>
    • </table>
    • <p>&nbsp;</p>

    Edited by David Hughes at December 4, 2018 21 : 52 : 30

  • Change in Description
    • --- /tmp/diffy20211209-943388-f1d2zg 2021-12-09 07:10:33.281426541 +0000
    • +++ /tmp/diffy20211209-943388-17u52gk 2021-12-09 07:10:33.285426568 +0000
    • @@ -0,0 +1,24 @@
    • +<p>A few groups have explored the use of drones for FAW. The Hughes Lab at Penn State tested different heights&nbsp;over maize field from which human observers can detect FAW holes. They flew a Phantom&nbsp;D4 drone with standard 4K camera. The determined that the drone had to be no more than 10m above the crop. Below are some example fields</p>
    • +
    • +<table border="1" cellpadding="1" cellspacing="1" style="width:500px;">
    • + <tbody>
    • + <tr>
    • + <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/200/content_Screen_Shot_2018-12-04_at_10.46.25_PM.png" style="width: 400px; height: 278px;" /></td>
    • + <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/201/content_Screen_Shot_2018-12-04_at_10.46.19_PM.png" style="width: 400px; height: 279px;" /></td>
    • + <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/202/content_Screen_Shot_2018-12-04_at_10.45.38_PM.png" style="width: 400px; height: 274px;" /></td>
    • + </tr>
    • + </tbody>
    • +</table>
    • +
    • +<p>&nbsp;One possible tool is a multi-spectral camera. We have flow the RedEdge camera a lot. This&nbsp;</p>
    • +
    • +<table border="1" cellpadding="1" cellspacing="1" style="width:500px;">
    • + <tbody>
    • + <tr>
    • + <td><img alt="" longdesc="Rededge camera on drone " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/203/content_Screen_Shot_2018-12-04_at_10.50.00_PM.png" style="width: 400px; height: 324px;" /></td>
    • + <td><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/204/content_Screen_Shot_2018-12-04_at_10.49.53_PM.png" style="width: 400px; height: 268px;" /></td>
    • + </tr>
    • + </tbody>
    • +</table>
    • +
    • +<p>&nbsp;</p>

    Edited by David Hughes at December 4, 2018 21 : 51 : 29

  • Change in Description
    • --- /tmp/diffy20211209-943388-1q2xou1 2021-12-09 07:10:33.293426622 +0000
    • +++ /tmp/diffy20211209-943388-sz2yu1 2021-12-09 07:10:33.293426622 +0000
    • @@ -0,0 +1,9 @@
    • +<p>CABI recently announced a system for forecasting the risk of pest outbreaks. This is a collaboration between CABI and the UK Space Agency (UKSA) that aims to use a network to prevent, rather than just mitigate infestations. They said it will &quot;use a novel combination of earth observation technology, satellite positioning, and plant-pest lifecycle to deliver a science-based Pest Risk Information SErvice (PRISE) for sub-Saharan Africa. Expansive, novel crowd sourcing observations will also be established to strengthen and validate the system.&quot;&nbsp;https://www.bbc.com/news/science-environment-46370601&nbsp;</p>
    • +
    • +<p>It is not clear from the media attention what the earth observations are. What satellites are being used.&nbsp;There is a document <a href="http://www.iapetus.ac.uk/wp-content/uploads/2018/10/IAP2-18-14_CEH_White.pdf">here</a> about the project.&nbsp; The project says it will use&nbsp; &quot;environmental data from Earth Observation&nbsp;validated by the consortium (e.g. land surface temperature and rainfall), pest phenology data across three different countries (Kenya, Zambia and Ghana) and crowdsourced observations.&quot;</p>
    • +
    • +<p>There are a number of satellites that measure ground temperature and moisture. But since no details have been provided we cannot speculate.&nbsp;</p>
    • +
    • +<p>It is worth stressing that there is no current evidence that PRISE can predict FAW.&nbsp;</p>
    • +
    • +<p>[December 4th, 2018- this needs community editing]</p>

    Edited by David Hughes at December 4, 2018 21 : 39 : 56

    • --- /tmp/diffy20211209-943388-1j06hje 2021-12-09 07:10:33.301426676 +0000
    • +++ /tmp/diffy20211209-943388-8cg9zp 2021-12-09 07:10:33.301426676 +0000
    • @@ -1 +0,0 @@
    • -Introduction
    • --- /tmp/diffy20211209-943388-11uxb9m 2021-12-09 07:10:33.305426703 +0000
    • +++ /tmp/diffy20211209-943388-d1ynvz 2021-12-09 07:10:33.305426703 +0000
    • @@ -1,9 +0,0 @@
    • -<p><b>Remote sensing</b>&nbsp;is the acquisition of information about an object or phenomenon without making physical contact with the object and thus in contrast to on-site observation, especially the Earth. Remote sensing is used in numerous fields, including geography, land surveying and most Earth Science disciplines (for example, hydrology, ecology,&nbsp;&nbsp;meteorology, oceanography, glaciology, geology); it also has military, intelligence, commercial, economic, planning, and humanitarian applications.</p>
    • -
    • -<p>In this last case remote sensing has been suggested to be useful to track fall armyworm in Africa.&nbsp;</p>
    • -
    • -<p>In current usage, the term &quot;remote sensing&quot; generally refers to the use of satellite- or aircraft-based sensor technologies to detect and classify objects on Earth. Aircraft can include drones.&nbsp;</p>
    • -
    • -<p>The goal of this page is to enable practitioners&nbsp;in remote sensing of FAW to share success and failures. It is important that we do this collectively to avoid wasted efforts and to pool resources.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by David Hughes at December 4, 2018 21 : 19 : 19

    • --- /tmp/diffy20211209-943388-14928g1 2021-12-09 07:10:33.313426757 +0000
    • +++ /tmp/diffy20211209-943388-1o4ofsj 2021-12-09 07:10:33.313426757 +0000
    • @@ -1 +0,0 @@
    • -The problem of intercropping and weeds
    • --- /tmp/diffy20211209-943388-1gyl1v6 2021-12-09 07:10:33.313426757 +0000
    • +++ /tmp/diffy20211209-943388-102rs0r 2021-12-09 07:10:33.313426757 +0000
    • @@ -1,29 +0,0 @@
    • -<p>Before proceeding to discuss how remote sensing could help in Africa to monitor and track FAW it is critical to appreciate the reality of what most smallholder farmer fields in Africa are: they are small (&lt;2ha), with irregular boundaries and with extensive polyculture and weeds. That is not to say the continent does not have regular shaped fields that are monocrop and free of weeds- but the majority are not. This presents a major challenge to remote sensing- how can the camera on a satellite tell the difference between maize versus other crops/weeds. And if it does, how can it determine if the maize has FAW?&nbsp;</p>
    • -
    • -<p>Here is a picture of a&nbsp;field in Western&nbsp;Kenya from Google maps.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p><img alt="" longdesc="Google satellite map view of Western Kenya " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/195/content_Screen_Shot_2018-12-04_at_10.06.25_PM.png" style="width: 600px; height: 408px;" /></p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>The point is the location that Dr John Chelal of Eldoret University used the PlantVillage Nuru app on December 4th 2018. Below is a picture he took from ground level&nbsp;</p>
    • -
    • -<p><img alt="" longdesc="1 month old intercropped with cassava with FAW damaged maize" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/196/content_IMG-20181204-WA0000.jpg" style="width: 300px; height: 400px;" /></p>
    • -
    • -<p>The challenge then is telling which crop is which.&nbsp;</p>
    • -
    • -<p>Below is an image of 3m resolution Planet.com from Western&nbsp;Kenya. It is not the same field but it is a field with maize and cassava, and weeds. The colors are because the analysis is an index called NDVI (normalized difference vegetation index) that is commonly used. This is going to be hard to distinguish between crops.</p>
    • -
    • -<p><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/197/content_Screen_Shot_2018-12-04_at_10.12.46_PM.png" style="width: 300px; height: 215px;" /></p>
    • -
    • -<p>Below is the same field taken with a drone at 60m captured by the Hughes Lab. Even at this much closer distance distinguishing which crop is which is hard/</p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>&nbsp;<img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/198/content_Screen_Shot_2018-12-04_at_10.16.14_PM.png" style="width: 300px; height: 330px;" /></p>
    • -
    • -<p>The issue of polyculture, weeds and irregular&nbsp;boundaries needs to be considered closely when advocating the use of remote sensing.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by David Hughes at December 4, 2018 21 : 19 : 18

    • --- /tmp/diffy20211209-943388-7symq1 2021-12-09 07:10:33.325426838 +0000
    • +++ /tmp/diffy20211209-943388-1xjcly 2021-12-09 07:10:33.325426838 +0000
    • @@ -1 +0,0 @@
    • -The problem of intercropping and weeds
    • --- /tmp/diffy20211209-943388-1m9pnae 2021-12-09 07:10:33.325426838 +0000
    • +++ /tmp/diffy20211209-943388-jgcwhz 2021-12-09 07:10:33.325426838 +0000
    • @@ -1,29 +0,0 @@
    • -<p>Before proceeding to discuss how remote sensing could help in Africa to monitor and track FAW it is critical to appreciate the reality of what most smallholder farmer fields in Africa are: they are small (&lt;2ha), with irregular boundaries and with extensive polyculture and weeds. That is not to say the continent does not have regular shaped fields that are monocrop and free of weeds- but the majority are not. This presents a major challenge to remote sensing- how can the camera on a satellite tell the difference between maize versus other crops/weeds. And if it does, how can it determine if the maize has FAW?&nbsp;</p>
    • -
    • -<p>Here is a picture of a&nbsp;field in Western&nbsp;Kenya from Google maps.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p><img alt="" longdesc="Google satellite map view of Western Kenya " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/195/content_Screen_Shot_2018-12-04_at_10.06.25_PM.png" style="width: 600px; height: 408px;" /></p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>The point is the location that Dr John Chelal of Eldoret University used the PlantVillage Nuru app on December 4th 2018. Below is a picture he took from ground level&nbsp;</p>
    • -
    • -<p><img alt="" longdesc="1 month old intercropped with cassava with FAW damaged maize" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/196/content_IMG-20181204-WA0000.jpg" style="width: 300px; height: 400px;" /></p>
    • -
    • -<p>The challenge then is telling which crop is which.&nbsp;</p>
    • -
    • -<p>Below is an image of 3m resolution Planet.com from Western&nbsp;Kenya. It is not the same field but it is a field with maize and cassava, and weeds. The colors are because the analysis is an index called NDVI (normalized difference vegetation index) that is commonly used. This is going to be hard to distinguish between crops.</p>
    • -
    • -<p><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/197/content_Screen_Shot_2018-12-04_at_10.12.46_PM.png" style="width: 300px; height: 215px;" /></p>
    • -
    • -<p>Below is the same field taken with a drone at 60m captured by the Hughes Lab. Even at this much closer distance distinguishing which crop is which is hard/</p>
    • -
    • -<p>&nbsp;</p>
    • -
    • -<p>&nbsp;<img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/198/content_Screen_Shot_2018-12-04_at_10.16.14_PM.png" style="width: 300px; height: 330px;" /></p>
    • -
    • -<p>The issue of polyculture, weeds and irregular&nbsp;boundaries needs to be considered closely when advocating the use of remote sensing.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by David Hughes at December 4, 2018 21 : 19 : 13

    • --- /tmp/diffy20211209-943388-w3xm1p 2021-12-09 07:10:33.337426919 +0000
    • +++ /tmp/diffy20211209-943388-1gg80z 2021-12-09 07:10:33.337426919 +0000
    • @@ -1 +0,0 @@
    • -Introduction
    • --- /tmp/diffy20211209-943388-ql151s 2021-12-09 07:10:33.341426946 +0000
    • +++ /tmp/diffy20211209-943388-1sbfcxw 2021-12-09 07:10:33.341426946 +0000
    • @@ -1,9 +0,0 @@
    • -<p><b>Remote sensing</b>&nbsp;is the acquisition of information about an object or phenomenon without making physical contact with the object and thus in contrast to on-site observation, especially the Earth. Remote sensing is used in numerous fields, including geography, land surveying and most Earth Science disciplines (for example, hydrology, ecology,&nbsp;&nbsp;meteorology, oceanography, glaciology, geology); it also has military, intelligence, commercial, economic, planning, and humanitarian applications.</p>
    • -
    • -<p>In this last case remote sensing has been suggested to be useful to track fall armyworm in Africa.&nbsp;</p>
    • -
    • -<p>In current usage, the term &quot;remote sensing&quot; generally refers to the use of satellite- or aircraft-based sensor technologies to detect and classify objects on Earth. Aircraft can include drones.&nbsp;</p>
    • -
    • -<p>The goal of this page is to enable practitioners&nbsp;in remote sensing of FAW to share success and failures. It is important that we do this collectively to avoid wasted efforts and to pool resources.&nbsp;</p>
    • -
    • -<p>&nbsp;</p>

    Edited by David Hughes at December 4, 2018 21 : 19 : 13

  • Change in Description
    • --- /tmp/diffy20211209-943388-1n3hogi 2021-12-09 07:10:33.349427000 +0000
    • +++ /tmp/diffy20211209-943388-1ut4wcc 2021-12-09 07:10:33.349427000 +0000
    • @@ -1,13 +1,29 @@
    • <p>Before proceeding to discuss how remote sensing could help in Africa to monitor and track FAW it is critical to appreciate the reality of what most smallholder farmer fields in Africa are: they are small (&lt;2ha), with irregular boundaries and with extensive polyculture and weeds. That is not to say the continent does not have regular shaped fields that are monocrop and free of weeds- but the majority are not. This presents a major challenge to remote sensing- how can the camera on a satellite tell the difference between maize versus other crops/weeds. And if it does, how can it determine if the maize has FAW?&nbsp;</p>
    • <p>Here is a picture of a&nbsp;field in Western&nbsp;Kenya from Google maps.&nbsp;</p>
    • <p>&nbsp;</p>
    • <p><img alt="" longdesc="Google satellite map view of Western Kenya " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/195/content_Screen_Shot_2018-12-04_at_10.06.25_PM.png" style="width: 600px; height: 408px;" /></p>
    • <p>&nbsp;</p>
    • <p>The point is the location that Dr John Chelal of Eldoret University used the PlantVillage Nuru app on December 4th 2018. Below is a picture he took from ground level&nbsp;</p>
    • <p><img alt="" longdesc="1 month old intercropped with cassava with FAW damaged maize" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/196/content_IMG-20181204-WA0000.jpg" style="width: 300px; height: 400px;" /></p>
    • +
    • +<p>The challenge then is telling which crop is which.&nbsp;</p>
    • +
    • +<p>Below is an image of 3m resolution Planet.com from Western&nbsp;Kenya. It is not the same field but it is a field with maize and cassava, and weeds. The colors are because the analysis is an index called NDVI (normalized difference vegetation index) that is commonly used. This is going to be hard to distinguish between crops.</p>
    • +
    • +<p><img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/197/content_Screen_Shot_2018-12-04_at_10.12.46_PM.png" style="width: 300px; height: 215px;" /></p>
    • +
    • +<p>Below is the same field taken with a drone at 60m captured by the Hughes Lab. Even at this much closer distance distinguishing which crop is which is hard/</p>
    • +
    • +<p>&nbsp;</p>
    • +
    • +<p>&nbsp;<img alt="" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/198/content_Screen_Shot_2018-12-04_at_10.16.14_PM.png" style="width: 300px; height: 330px;" /></p>
    • +
    • +<p>The issue of polyculture, weeds and irregular&nbsp;boundaries needs to be considered closely when advocating the use of remote sensing.&nbsp;</p>
    • +
    • +<p>&nbsp;</p>

    Edited by David Hughes at December 4, 2018 21 : 19 : 05

  • Change in Description
    • --- /tmp/diffy20211209-943388-dru84n 2021-12-09 07:10:33.357427054 +0000
    • +++ /tmp/diffy20211209-943388-u6gg87 2021-12-09 07:10:33.357427054 +0000
    • @@ -0,0 +1,13 @@
    • +<p>Before proceeding to discuss how remote sensing could help in Africa to monitor and track FAW it is critical to appreciate the reality of what most smallholder farmer fields in Africa are: they are small (&lt;2ha), with irregular boundaries and with extensive polyculture and weeds. That is not to say the continent does not have regular shaped fields that are monocrop and free of weeds- but the majority are not. This presents a major challenge to remote sensing- how can the camera on a satellite tell the difference between maize versus other crops/weeds. And if it does, how can it determine if the maize has FAW?&nbsp;</p>
    • +
    • +<p>Here is a picture of a&nbsp;field in Western&nbsp;Kenya from Google maps.&nbsp;</p>
    • +
    • +<p>&nbsp;</p>
    • +
    • +<p><img alt="" longdesc="Google satellite map view of Western Kenya " src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/195/content_Screen_Shot_2018-12-04_at_10.06.25_PM.png" style="width: 600px; height: 408px;" /></p>
    • +
    • +<p>&nbsp;</p>
    • +
    • +<p>The point is the location that Dr John Chelal of Eldoret University used the PlantVillage Nuru app on December 4th 2018. Below is a picture he took from ground level&nbsp;</p>
    • +
    • +<p><img alt="" longdesc="1 month old intercropped with cassava with FAW damaged maize" src="https://s3.amazonaws.com/plantvillage-production-new/ckeditor_assets/pictures/196/content_IMG-20181204-WA0000.jpg" style="width: 300px; height: 400px;" /></p>

    Edited by David Hughes at December 4, 2018 21 : 11 : 08

  • Change in Description
    • --- /tmp/diffy20211209-943388-1sisrnu 2021-12-09 07:10:33.365427108 +0000
    • +++ /tmp/diffy20211209-943388-1g0cn42 2021-12-09 07:10:33.365427108 +0000
    • @@ -0,0 +1,9 @@
    • +<p><b>Remote sensing</b>&nbsp;is the acquisition of information about an object or phenomenon without making physical contact with the object and thus in contrast to on-site observation, especially the Earth. Remote sensing is used in numerous fields, including geography, land surveying and most Earth Science disciplines (for example, hydrology, ecology,&nbsp;&nbsp;meteorology, oceanography, glaciology, geology); it also has military, intelligence, commercial, economic, planning, and humanitarian applications.</p>
    • +
    • +<p>In this last case remote sensing has been suggested to be useful to track fall armyworm in Africa.&nbsp;</p>
    • +
    • +<p>In current usage, the term &quot;remote sensing&quot; generally refers to the use of satellite- or aircraft-based sensor technologies to detect and classify objects on Earth. Aircraft can include drones.&nbsp;</p>
    • +
    • +<p>The goal of this page is to enable practitioners&nbsp;in remote sensing of FAW to share success and failures. It is important that we do this collectively to avoid wasted efforts and to pool resources.&nbsp;</p>
    • +
    • +<p>&nbsp;</p>

    Edited by David Hughes at December 4, 2018 20 : 54 : 31

PlantVillage PlantVillage logo