In-season crop monitoring using machine learning algorithms

The Government of Telangana is leveraging advanced technologies to enhance the accuracy and reliability of its crop estimation system. As part of this initiative, a pilot project was assigned to ICRISAT to generate high-resolution land use and land cover (LULC) maps, focusing on differentiating cult...

Descripción completa

Detalles Bibliográficos
Autores principales: Gumma, Murali K., Panjala, Pranay, Ismail, Mohammed, Kumar, Pavan, Harawa, Rebbie
Formato: Conference Paper
Lenguaje:Inglés
Publicado: CGIAR System Organization 2025
Materias:
Acceso en línea:https://hdl.handle.net/10568/180321
_version_ 1855519762968215552
author Gumma, Murali K.
Panjala, Pranay
Ismail, Mohammed
Kumar, Pavan
Harawa, Rebbie
author_browse Gumma, Murali K.
Harawa, Rebbie
Ismail, Mohammed
Kumar, Pavan
Panjala, Pranay
author_facet Gumma, Murali K.
Panjala, Pranay
Ismail, Mohammed
Kumar, Pavan
Harawa, Rebbie
author_sort Gumma, Murali K.
collection Repository of Agricultural Research Outputs (CGSpace)
description The Government of Telangana is leveraging advanced technologies to enhance the accuracy and reliability of its crop estimation system. As part of this initiative, a pilot project was assigned to ICRISAT to generate high-resolution land use and land cover (LULC) maps, focusing on differentiating cultivated, non-cultivated, and other land and crop categories. For the Kharif 2024 season, two mandals were selected for the pilot: Raghunadhapalem in Khammam district and Sirikonda in Nizamabad district. The mapping outputs were validated against official government statistics and cross-referenced with Rythu Bharosa, the state’s acre-based farmer incentive program. The analysis revealed that approximately 15 percent of uncultivated land had received benefits under the scheme, highlighting discrepancies between actual land use and scheme records. Beyond identifying overestimated areas, the study provided detailed insights into cropping patterns, crop intensity, and land utilization at the mandal level. These insights can support better targeting of agricultural support programs, optimize resource allocation, and guide procurement planning by anticipating sowing and harvest schedules, which can be effectively utilized by Village Revenue Officers (VROs) and Agriculture Extension Officers (AEOs). The pilot also demonstrated the potential of integrating high-resolution LULC data with policy frameworks to reduce errors, prevent misuse of incentives, and support evidence-based decision-making at both operational and strategic levels. Furthermore, a dedicated web portal has been developed for parcel-level, evidence-based monitoring of crop sowing and harvest dates. By linking this system with agricultural schemes, it enhances transparency, minimizes the risk of fraud, and enables more informed planning for procurement, input allocation, and timely policy interventions. Collectively, the pilot establishes a technology-driven framework that can be scaled across Telangana, strengthening crop estimation, improving resource efficiency, and ensuring that agricultural incentives reach the intended beneficiaries.
format Conference Paper
id CGSpace180321
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher CGIAR System Organization
publisherStr CGIAR System Organization
record_format dspace
spelling CGSpace1803212026-01-22T02:04:09Z In-season crop monitoring using machine learning algorithms Gumma, Murali K. Panjala, Pranay Ismail, Mohammed Kumar, Pavan Harawa, Rebbie maps cropping patterns land utilization land use and land cover maps evidence-based decision-making The Government of Telangana is leveraging advanced technologies to enhance the accuracy and reliability of its crop estimation system. As part of this initiative, a pilot project was assigned to ICRISAT to generate high-resolution land use and land cover (LULC) maps, focusing on differentiating cultivated, non-cultivated, and other land and crop categories. For the Kharif 2024 season, two mandals were selected for the pilot: Raghunadhapalem in Khammam district and Sirikonda in Nizamabad district. The mapping outputs were validated against official government statistics and cross-referenced with Rythu Bharosa, the state’s acre-based farmer incentive program. The analysis revealed that approximately 15 percent of uncultivated land had received benefits under the scheme, highlighting discrepancies between actual land use and scheme records. Beyond identifying overestimated areas, the study provided detailed insights into cropping patterns, crop intensity, and land utilization at the mandal level. These insights can support better targeting of agricultural support programs, optimize resource allocation, and guide procurement planning by anticipating sowing and harvest schedules, which can be effectively utilized by Village Revenue Officers (VROs) and Agriculture Extension Officers (AEOs). The pilot also demonstrated the potential of integrating high-resolution LULC data with policy frameworks to reduce errors, prevent misuse of incentives, and support evidence-based decision-making at both operational and strategic levels. Furthermore, a dedicated web portal has been developed for parcel-level, evidence-based monitoring of crop sowing and harvest dates. By linking this system with agricultural schemes, it enhances transparency, minimizes the risk of fraud, and enables more informed planning for procurement, input allocation, and timely policy interventions. Collectively, the pilot establishes a technology-driven framework that can be scaled across Telangana, strengthening crop estimation, improving resource efficiency, and ensuring that agricultural incentives reach the intended beneficiaries. 2025-12 2026-01-21T17:32:54Z 2026-01-21T17:32:54Z Conference Paper https://hdl.handle.net/10568/180321 en Open Access application/pdf CGIAR System Organization Gumma, Murali K,; Panjala, Pranay; Ismail, Mohammed; Kumar, Pavan; Harawa, Rebbie. 2025. In-season crop monitoring using Machine learning Algorithms. CGIAR
spellingShingle maps
cropping patterns
land utilization
land use and land cover maps
evidence-based decision-making
Gumma, Murali K.
Panjala, Pranay
Ismail, Mohammed
Kumar, Pavan
Harawa, Rebbie
In-season crop monitoring using machine learning algorithms
title In-season crop monitoring using machine learning algorithms
title_full In-season crop monitoring using machine learning algorithms
title_fullStr In-season crop monitoring using machine learning algorithms
title_full_unstemmed In-season crop monitoring using machine learning algorithms
title_short In-season crop monitoring using machine learning algorithms
title_sort in season crop monitoring using machine learning algorithms
topic maps
cropping patterns
land utilization
land use and land cover maps
evidence-based decision-making
url https://hdl.handle.net/10568/180321
work_keys_str_mv AT gummamuralik inseasoncropmonitoringusingmachinelearningalgorithms
AT panjalapranay inseasoncropmonitoringusingmachinelearningalgorithms
AT ismailmohammed inseasoncropmonitoringusingmachinelearningalgorithms
AT kumarpavan inseasoncropmonitoringusingmachinelearningalgorithms
AT harawarebbie inseasoncropmonitoringusingmachinelearningalgorithms