Our Agricultural Understanding models provide field-level insights into farming land around the world, to support timely and data driven decision making.
Knowing how agricultural land is being used helps government agencies, agritech firms, researchers and NGOs make better decisions. But in practice, it’s not easy – particularly considering the 500 million smallholder farms on Earth. Each of these typically covers less than two hectares, and they tend to have small, irregular fields.
It’s slow and prohibitively costly to manually survey agricultural land while tracking dynamic crop cycles. But individual fields are the atomic units of agriculture – understanding them in detail is critical to driving impactful, targeted, and meaningful change.
Our Agricultural Understanding models generate automated, high-frequency insights into the land – like field acreage, crop diversity and nearby water sources. This turns high-resolution satellite imagery into actionable, field-level intelligence, to help power precision agriculture, guide regional policy, and strengthen global food security.
Allows stakeholders to provide specific advice relevant to individual fields, rather than issuing broad regional guidance.
Tracks seasonal crop growth using high-frequency satellite data.
Provides granular data on landscapes and field use at high confidence levels, to support better decision making.
Agriculture Landscape Understanding
The ALU model identifies individual field boundaries and sizes by acreage. Also locates other landscape elements like trees and water bodies. Includes historical data from 2011 onwards.
Agricultural Monitoring and Event Detection
The AMED model is able to identify major crops, and record historical crop data – such as sowing and harvest times. Uses publicly available data sources to generate predictions, refreshed every 15 days. Includes historical data from 2020 onwards.
Africa - ALU
Kenya, Uganda, Ghana, Rwanda, Zambia and Nigeria
APAC - ALU + AMED
India, Malaysia, Vietnam, Indonesia, Japan
We partner with governments, academic institutions and agritech firms to help them better understand how farmland is being used.
“Together, these innovations are helping us create a stronger digital foundation for agricultural services and innovation across Telangana.”
“This enables us to identify areas requiring productivity improvements and supports more informed decisions to improve water productivity and sustainable water resource management across our river basins.”
“By using Google's ALU model and Gemini, we can now measure adoption, water outcomes, and methane emission reductions. This data helps farmers adopt climate-resilient techniques while enabling outcome-based incentive programs built on trusted, verifiable results.”
“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.”
“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.”
(Agricultural Landscape Understanding only)
