Optimizing Rice Crop Manager Odisha: AI-Driven Yield Prediction to compliment Extension using legacy data
Rice cultivation (Oryza sativa) requires precise crop and soil management, making optimized nutrient recommendations essential for improving productivity. To address this, the Rice Crop Manager (RCM)—a web-based tool developed by the International Rice Research Institute (IRRI)—was deployed to assis...
| Autores principales: | , |
|---|---|
| Formato: | Conference Paper |
| Lenguaje: | Inglés |
| Publicado: |
International Rice Research Institute
2024
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/172516 |
| _version_ | 1855527888961404928 |
|---|---|
| author | Gakhar, Shalini Bharti, Preeti |
| author_browse | Bharti, Preeti Gakhar, Shalini |
| author_facet | Gakhar, Shalini Bharti, Preeti |
| author_sort | Gakhar, Shalini |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Rice cultivation (Oryza sativa) requires precise crop and soil management, making optimized nutrient recommendations essential for improving productivity. To address this, the Rice Crop Manager (RCM)—a web-based tool developed by the International Rice Research Institute (IRRI)—was deployed to assist farmers in making data-driven decisions. RCM collects farmer input data to generate tailored recommendations on planting schedules, irrigation, and weed control. Since its inception in 2015 in Odisha, India, it has provided over 300,000 recommendations across 31 districts, offering valuable insights into varietal preferences, agricultural trends, and socio-demographic patterns. To leverage legacy data effectively, machine learning algorithms have been integrated into RCM to identify key factors influencing crop outcomes and assist in estimating target yields. These models are extensively trained to predict yield and evaluate performance using metrics such as R², root mean square error (RMSE), and mean absolute error (MAE). The insights generated through RCM not only highlight the most widely grown rice varieties and annual sowing trends but also explore critical dimensions such as gender roles and youth participation in agriculture. Future expansions of RCM aim to enhance farmer engagement through chatbot development, enabling real-time interaction and decision-making support. Additionally, the system's architecture facilitates automated, data-driven recommendations, benefiting multiple stakeholders and contributing to greater agricultural productivity. |
| format | Conference Paper |
| id | CGSpace172516 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| publisher | International Rice Research Institute |
| publisherStr | International Rice Research Institute |
| record_format | dspace |
| spelling | CGSpace1725162025-01-31T02:07:58Z Optimizing Rice Crop Manager Odisha: AI-Driven Yield Prediction to compliment Extension using legacy data Gakhar, Shalini Bharti, Preeti digital technology production systems yields yield forecasting artificial intelligence rice data collection Rice cultivation (Oryza sativa) requires precise crop and soil management, making optimized nutrient recommendations essential for improving productivity. To address this, the Rice Crop Manager (RCM)—a web-based tool developed by the International Rice Research Institute (IRRI)—was deployed to assist farmers in making data-driven decisions. RCM collects farmer input data to generate tailored recommendations on planting schedules, irrigation, and weed control. Since its inception in 2015 in Odisha, India, it has provided over 300,000 recommendations across 31 districts, offering valuable insights into varietal preferences, agricultural trends, and socio-demographic patterns. To leverage legacy data effectively, machine learning algorithms have been integrated into RCM to identify key factors influencing crop outcomes and assist in estimating target yields. These models are extensively trained to predict yield and evaluate performance using metrics such as R², root mean square error (RMSE), and mean absolute error (MAE). The insights generated through RCM not only highlight the most widely grown rice varieties and annual sowing trends but also explore critical dimensions such as gender roles and youth participation in agriculture. Future expansions of RCM aim to enhance farmer engagement through chatbot development, enabling real-time interaction and decision-making support. Additionally, the system's architecture facilitates automated, data-driven recommendations, benefiting multiple stakeholders and contributing to greater agricultural productivity. 2024-11-11 2025-01-30T13:41:29Z 2025-01-30T13:41:29Z Conference Paper https://hdl.handle.net/10568/172516 en Open Access application/pdf International Rice Research Institute Gakhar, Shalini and Preeti Bharti (2024). Optimizing Rice Crop Manager Odisha: AI-Driven Yield Prediction to compliment Extension using legacy data. Presented at the ISSAAS-JSTA Joint Congress, ISSAAS in 2024 and Beyond: Agricultural Science for Sustainable Development in Southeast Asia, 9-11 November 2024. CGIAR Research Initiative on Digital Innovation, the International Rice Research Institute. 24 p. |
| spellingShingle | digital technology production systems yields yield forecasting artificial intelligence rice data collection Gakhar, Shalini Bharti, Preeti Optimizing Rice Crop Manager Odisha: AI-Driven Yield Prediction to compliment Extension using legacy data |
| title | Optimizing Rice Crop Manager Odisha: AI-Driven Yield Prediction to compliment Extension using legacy data |
| title_full | Optimizing Rice Crop Manager Odisha: AI-Driven Yield Prediction to compliment Extension using legacy data |
| title_fullStr | Optimizing Rice Crop Manager Odisha: AI-Driven Yield Prediction to compliment Extension using legacy data |
| title_full_unstemmed | Optimizing Rice Crop Manager Odisha: AI-Driven Yield Prediction to compliment Extension using legacy data |
| title_short | Optimizing Rice Crop Manager Odisha: AI-Driven Yield Prediction to compliment Extension using legacy data |
| title_sort | optimizing rice crop manager odisha ai driven yield prediction to compliment extension using legacy data |
| topic | digital technology production systems yields yield forecasting artificial intelligence rice data collection |
| url | https://hdl.handle.net/10568/172516 |
| work_keys_str_mv | AT gakharshalini optimizingricecropmanagerodishaaidrivenyieldpredictiontocomplimentextensionusinglegacydata AT bhartipreeti optimizingricecropmanagerodishaaidrivenyieldpredictiontocomplimentextensionusinglegacydata |