From Pixels to Planting Dates: Using the AgWise Remote-sensing Framework to Automate Maize Planting-date Detection
Accurate crop planting date estimates are required for understanding agricultural seasonality, forecasting yields, planning input distribution, and developing climate resilient interventions. Particularly in smallholder-dominated environments in Africa and Asia, standard field-based methods for reco...
| Autores principales: | , , |
|---|---|
| Formato: | Artículo preliminar |
| Lenguaje: | Inglés |
| Publicado: |
International Rice Research Institute
2025
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/179298 |
| _version_ | 1855517531366752256 |
|---|---|
| author | Dastidar, Payel Ghosh Srivastava, Amit Leroux, Louise |
| author_browse | Dastidar, Payel Ghosh Leroux, Louise Srivastava, Amit |
| author_facet | Dastidar, Payel Ghosh Srivastava, Amit Leroux, Louise |
| author_sort | Dastidar, Payel Ghosh |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Accurate crop planting date estimates are required for understanding agricultural seasonality, forecasting yields, planning input distribution, and developing climate resilient interventions. Particularly in smallholder-dominated environments in Africa and Asia, standard field-based methods for recording planting dates are often unreliable, labour-intensive, and spatially confined. This study uses multitemporal satellite data, vegetation index information, and smoothing algorithms to extract planting dates across Kenya and Rwanda utilising the automated remote-sensing workflow of the AgWise platform. Applied over a two-decade period (2002-2023), the approach revealed strong intra- and inter-annual trends in maize planting behaviour, capturing both stable seasonal windows and year-to-year fluctuations across diverse agricultural landscapes. The workflow ensures objective and reproducible efficient monitoring over wide geographic areas, as well as annual trend studies that span decades. This automation not only eliminates human labour and subjectivity, but it also allows for near-real-time insights necessary for policy planning, early warning systems, and adaptive crop management. |
| format | Artículo preliminar |
| id | CGSpace179298 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| publisher | International Rice Research Institute |
| publisherStr | International Rice Research Institute |
| record_format | dspace |
| spelling | CGSpace1792982025-12-28T02:02:35Z From Pixels to Planting Dates: Using the AgWise Remote-sensing Framework to Automate Maize Planting-date Detection Dastidar, Payel Ghosh Srivastava, Amit Leroux, Louise vegetation index remote sensing yield forecasting crop management maize planting date agriculture smallholders Accurate crop planting date estimates are required for understanding agricultural seasonality, forecasting yields, planning input distribution, and developing climate resilient interventions. Particularly in smallholder-dominated environments in Africa and Asia, standard field-based methods for recording planting dates are often unreliable, labour-intensive, and spatially confined. This study uses multitemporal satellite data, vegetation index information, and smoothing algorithms to extract planting dates across Kenya and Rwanda utilising the automated remote-sensing workflow of the AgWise platform. Applied over a two-decade period (2002-2023), the approach revealed strong intra- and inter-annual trends in maize planting behaviour, capturing both stable seasonal windows and year-to-year fluctuations across diverse agricultural landscapes. The workflow ensures objective and reproducible efficient monitoring over wide geographic areas, as well as annual trend studies that span decades. This automation not only eliminates human labour and subjectivity, but it also allows for near-real-time insights necessary for policy planning, early warning systems, and adaptive crop management. 2025-12 2025-12-27T12:08:48Z 2025-12-27T12:08:48Z Working Paper https://hdl.handle.net/10568/179298 en Open Access application/pdf International Rice Research Institute Dastidar, Payel Ghosh, Amit Srivastava, Louise Leroux (2025). From Pixels to Planting Dates: Using the AgWise Remote-sensing Framework to Automate Maize Planting-date Detection. International Rice Research Institute. 22 p. |
| spellingShingle | vegetation index remote sensing yield forecasting crop management maize planting date agriculture smallholders Dastidar, Payel Ghosh Srivastava, Amit Leroux, Louise From Pixels to Planting Dates: Using the AgWise Remote-sensing Framework to Automate Maize Planting-date Detection |
| title | From Pixels to Planting Dates: Using the AgWise Remote-sensing Framework to Automate Maize Planting-date Detection |
| title_full | From Pixels to Planting Dates: Using the AgWise Remote-sensing Framework to Automate Maize Planting-date Detection |
| title_fullStr | From Pixels to Planting Dates: Using the AgWise Remote-sensing Framework to Automate Maize Planting-date Detection |
| title_full_unstemmed | From Pixels to Planting Dates: Using the AgWise Remote-sensing Framework to Automate Maize Planting-date Detection |
| title_short | From Pixels to Planting Dates: Using the AgWise Remote-sensing Framework to Automate Maize Planting-date Detection |
| title_sort | from pixels to planting dates using the agwise remote sensing framework to automate maize planting date detection |
| topic | vegetation index remote sensing yield forecasting crop management maize planting date agriculture smallholders |
| url | https://hdl.handle.net/10568/179298 |
| work_keys_str_mv | AT dastidarpayelghosh frompixelstoplantingdatesusingtheagwiseremotesensingframeworktoautomatemaizeplantingdatedetection AT srivastavaamit frompixelstoplantingdatesusingtheagwiseremotesensingframeworktoautomatemaizeplantingdatedetection AT lerouxlouise frompixelstoplantingdatesusingtheagwiseremotesensingframeworktoautomatemaizeplantingdatedetection |