PROBES snapshot: Vision2Biomass, quantifying crop residue retention

This one-page brief, developed by the Digital Transformation Accelerator (DTA) team at the Alliance of Bioversity International and CIAT, is based on the Vision2Biomass probe led by Patil Mukund, Senior Scientist - Soil Physics at ICRISAT. The probe explores how computer vision and machine learning can be used to estimate crop residue and biomass from field images, supporting more accurate and scalable monitoring of residue management practices. By automating visual assessment, the approach aims to reduce reliance on manual measurements and improve the availability of timely data for climate-smart agriculture and sustainable land management. Implemented as an early-stage, safe-to-fail experiment, the probe focuses on understanding the accuracy, feasibility, and limitations of image-based biomass estimation in real-world conditions. The brief synthesizes early insights to inform future development and potential integration of computer vision tools within CGIAR research and monitoring systems.