Outputs from these have been shared with trusted testers in 11 countries across Asia Pacific and Africa. Google DeepMind’s Agricultural Landscape Understanding (ALU) and Agricultural Monitoring & Event Detection (AMED) models, initially developed to support India’s agricultural ecosystem, now power farmer credit platforms, state-level crop advisories, and data systems maintained by the United Nations Food and Agriculture Organisation. Both models use satellite imagery to map field boundaries and monitor agricultural activity. Google has made the outputs available as APIs and on Google Earth, where the ALU data layer is one of the most used layers in the world.
Using the ALU and AMED APIs, Terrastack has built a spatial intelligence platform that has mapped over 140 million hectares of farmland, reducing the need for physical field visits and helping India’s agricultural ecosystem make faster, more accurate lending decisions. In Telangana, the ADEX platform is using ALU and AMED to support innovations for the state’s more than 5 million farmers, including a pilot of the Krishivaas application, which generates hyperlocal advisories on crop stress, crop-specific weather patterns, and localised pest outbreaks. Because there is no reliable way to understand what is happening at the farm level, “Over 100 million farming households remain underserved.
Google’s ALU and AMED models have enabled us to build a spatial intelligence platform that is helping transform fragmented land, crop, and income data into actionable intelligence for every farm in India,” said Aaryan Dangi, co-founder and CEO of Terrastack. By integrating Google’s ALU and AMED datasets, we are enabling capabilities such as field boundary delineation, crop stress analysis, early warning systems, and hyperlocal advisories,” said the Information Technology, Electronics and Communications Department of the Government of Telangana. “One of the biggest challenges in agriculture is access to quality data. With ADeX, we set out to create a shared platform that Telangana’s government departments, universities, startups, and partners can build upon.
CarbonFarm has used the ALU API and Gemini to automate field-level delineation as part of programs to reduce the environmental impact of rice cultivation, supporting its goal of covering 2 million hectares of low-carbon rice by 2030.
This data helps farmers adopt climate-resilient techniques while enabling outcome-based incentive programs built on trusted, verifiable results,” said Aparna Raturi, chief operating officer of CarbonFarm. This will help countries generate better insights for agricultural planning, sustainability efforts, and food security interventions while accelerating the transformation of agri-food systems,” said Francesco Tubiello, FAO senior statistician and geoAI4Stats project lead. “By using Google’s ALU model to map individual field boundaries, enabling satellite-based verification of farming practices, and Gemini to give farmers real-time feedback as they implement water management techniques, we can now measure adoption, water outcomes, and methane emission reductions. “With support from Google.org, we are bringing together advanced AI capabilities and FAO’s agricultural expertise to strengthen agricultural data as a global public good.