As global food security challenges intensify, with an estimated 2.1 billion people experiencing food insecurity in 2025 and food production needing to rise by as much as 50% by 2050, Google DeepMind is scaling the reach of its artificial intelligence-powered agricultural tools to support more efficient farming and land management.
The company said two AI models, Agricultural Landscape Understanding (ALU) and Agricultural Monitoring & Event Detection (AMED), are helping map field boundaries and monitor agricultural activity using satellite imagery.
Originally developed to support India’s agricultural ecosystem, the models have now been shared with trusted testers in 11 countries across Asia Pacific and Africa. Their outputs are also being made freely available through APIs and Google Earth, where the ALU data layer has emerged as one of the platform’s most widely used layers globally.
The ecosystem has been leveraging these models’ outputs to build solutions that strengthen both the Indian and global agriculture sector, ranging from improved sustainable cultivation, to increased farmer access to credit, and stronger policy decision making and resource management.
- Growing sustainability of food production: CarbonFarm has used the ALU API and Gemini to automate field-level insights, especially field-level delineation, in programs that aim to reduce the environmental impact of rice cultivation. This is part of CarbonFarm’s efforts to support 2 million hectares of low-carbon rice by 2030.
- Strengthening farmer access to agri credit: Using 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. This is enabling India’s agri ecosystem to make faster and more accurate decisions that benefit farmers.
- Supporting India’s DPI for Agri: Telangana’s ADEX platform is leveraging ALU and AMED as part of its efforts to support innovations that benefit the state’s 5 million+ farmers. This includes a pilot of the state’s Krishivaas application, which generates actionable, hyperlocal advisories on crop stress, crop-specific weather patterns and localized pest outbreaks.
- Scaling digital agri infrastructure to the world: The new geoAI4stats initiative at the UN Food and Agriculture Organization (FAO), which has received support from Google.org as part of the AI Collaborative: Food Security, plans to integrate ALU and AMED into FAO’s global CROPGRIDS data repository to strengthen monitoring for agricultural sustainability.
- Strengthening water management: Karnataka’s Water Resources Department has combined ALU and AMED with localized weather and remote sensing data to strengthen dynamic water management across the state’s 2.6 million hectares of irrigated area.
Remarking on the deployment of the models’ capabilities, Alok Talekar, Lead, Agriculture and Sustainability Research, Google DeepMind, who leads the AnthroKrishi team stated: “Our AnthroKrishi team has been dedicated to supporting targeted agricultural solutions that both increase farm productivity and reduce climate impact. The growing application of our India-first AI models’ APIs to impact-focused solutions – ranging from farmer credit, to crop advisory and policy decision-making – across both the Indian and global ecosystem encourages us in our approach.
“As these models expand to support even more countries, we look forward to the immense potential they will unlock for key global priorities, from food security to agricultural resilience,” Talekar said.
As adoption continues to grow across sectors and geographies, Google and Google DeepMind’s AnthroKrishi team stay committed to providing data-driven insights and supporting a more productive, resilient, and sustainable future for the Indian and global agricultural ecosystem.
