Google’s India-first AI models for agriculture are finding applications beyond India

Google is taking an India-developed approach to agricultural AI beyond the country, with two satellite-imagery models now being used by organisations working across farming, credit, water management and agricultural policy. The models, Agricultural Landscape Understanding (ALU) and Agricultural Monitoring & Event Detection (AMED), were developed by Google DeepMind to analyse agricultural landscapes and track activity using satellite imagery. Initially focused on India, their outputs are now being tested by partners in 11 countries across the Asia-Pacific and Africa. The models are available to the broader ecosystem through APIs and as a data layer on Google Earth. Google says the ALU layer has become one of the most popular layers on Google Earth globally.

ET Digital has also tracked Google's work around AI and agriculture on the ground. At the India AI Impact Summit, we covered Google's agricultural AI initiatives and their potential applications in the sector. Watch our coverage from the AI Impact Summit.

From mapping fields to supporting farmers

One of the applications is in sustainable rice cultivation. CarbonFarm is using the ALU API alongside Gemini to automate field-level insights, including mapping individual field boundaries, as part of programmes aimed at reducing the environmental impact of rice farming.


The company is targeting support for 2 million hectares of low-carbon rice by 2030. Another application is agricultural finance. Terrastack has built a spatial intelligence platform using ALU and AMED APIs that it says has mapped more than 140 million hectares of farmland. The technology is intended to reduce dependence on physical field visits and provide lenders and other agricultural stakeholders with more detailed information for decision-making.

The models are also being incorporated into state-level digital agriculture initiatives. In Telangana, the ADeX platform is using ALU and AMED as part of efforts to build digital services for the state's more than 5 million farmers. One pilot, the Krishivaas application, uses agricultural and weather data to provide localised information around crop stress, weather patterns and pest outbreaks.

AI moves into water management

Agricultural applications extend beyond individual farms. Karnataka's Water Resources Department is combining ALU and AMED with local weather, remote sensing, field observations and other datasets to improve monitoring across around 2.6 million hectares of irrigated land. The objective is to provide more granular information on crops and water productivity, supporting decisions around water management across the state's river basins.

Google is also working with the UN Food and Agriculture Organization (FAO) on geoAI4stats, an initiative that plans to incorporate ALU and AMED into the FAO's global CROPGRIDS data repository. The project is intended to improve the availability of detailed agricultural data for areas including sustainability monitoring, agricultural planning and food security.

An India-first model with a wider footprint

Alok Talekar, lead for agriculture and sustainability research at Google DeepMind and the leader of its AnthroKrishi team, said the wider adoption of the models was an extension of the team's work on targeted agricultural applications. The use cases now emerging around the models span several layers of the agricultural ecosystem, from field-level mapping and sustainable cultivation to credit, water management and government decision-making.

The development also illustrates how AI models built around India's specific agricultural requirements can find applications in other markets, particularly where fragmented farmland, limited ground-level data and the scale of agricultural operations create similar challenges. As these tools move into more countries and use cases, the focus is increasingly shifting from developing agricultural AI models to making their underlying data useful to governments, businesses and organisations working directly with farmers.