By Jamie Martin
A groundbreaking study by North Carolina State University merges satellite imagery and machine learning to revolutionize rice crop monitoring. This innovation aims to improve global rice farming practices, beginning with Bangladesh, the world’s third-largest rice producer.
The traditional methods for monitoring rice productivity, including manual field data collection, are labour-intensive and prone to inaccuracies. Varun Tiwari, the study’s lead researcher, explained, “It is a time-consuming and labor-intensive process.
Additionally, the method adds inaccuracies when rice yield estimates are based on only a few samples rather than data from all fields.”
Using time-series satellite imagery, researchers measured vegetation, crop water content, and soil conditions to train a machine learning model for more precise productivity estimates.
Covering data from 2002 to 2021, the model demonstrated accuracy rates of 90-92%, enabling early resource planning, such as storage and transportation infrastructure.
Bangladesh’s dependence on rice and its vulnerability to climate change make accurate yield estimates critical. “Bangladesh was the ideal place for us to begin,” Tiwari noted. The approach could be adapted for other crops and regions, providing global benefits.
This research, supported by the Gates Foundation and USAID, highlights collaboration between institutions like NC State, USDA, and the Bangladesh Rice Research Institute. The findings, published in PLOS ONE, showcase a transformative step toward sustainable farming and food security.
Photo Credit: pexels-polina-tankilevitch
Categories: National