Artificial Intelligence

Artificial Intelligence for Real-World Challenges

Degas is transforming how Earth Observation Data is used. Our Large Geospatial Model (LGM) turns satellite imagery into actionable intelligence for agriculture, government monitoring and insurance, with applications extending into many other industries, enabling better decisions, faster and at lower cost.

Why it matters

The LGM overcomes the traditional limitations of remote sensing: instead of slow, fragmented, and expensive analyses, we deliver insights that are scalable, consistent, and continuously improving, making it possible for farmers, governments, and industries to act faster, reduce risks, and create lasting impact for the people they serve.. Our AI learns from massive volumes of imagery and drastically reduces the need for ground-truth data, making it possible to apply state-of-the-art models in any geography quickly and efficiently.

Our first breakthrough came with Degas 100M, a foundation model trained on millions of satellite images from the Sentinel-2 constellation. Benchmarking showed that our model outperformed NASA/IBM’s Prithvi across all major tasks in the PhilEO benchmark, including land cover classification and segmentation. See our paper.

But agriculture is not static. Farms evolve over time, and good decisions require a memory of the past. That’s why we built the first large-scale model designed to process five years of historical satellite data. Trained on over half a million long time-series, our model adapts seamlessly to a range of agricultural tasks—from predicting yield to mapping crop cycles, using deep temporal context.

Applying technology to solve global challenges

Detecting floods
in Japan

In partnership with the Remote Sensing Technology Center (RESTEC) of Japan, Degas developed a model capable of identifying flood-affected areas in real time. Tested during the heavy rains in Aichi Prefecture in June 2023, the system achieved over 80% accuracy using the emergency mode of Japan-owned ALOS-2, allowing for rapid governmental response. This innovation shows how our technology can support disaster response efforts, helping communities and governments act faster and save lives when extreme weather strikes.

Protecting cassava in Thailand

Cassava is a vital crop for millions of families in Asia and Africa, but it is under constant threat from Cassava Mosaic Disease (CMD). Working with local partners in Thailand, Degas created a detection model that uses satellite data to identify CMD outbreaks at the field level with more than 90% accuracy. This breakthrough has the potential to save millions of dollars in agricultural losses, making it possible to alert communities quickly, reduce risks, and protect livelihoods, ultimately turning science into everyday resilience.

Our edge

Degas combines boots-on-the-ground data from Farmer Financing with cutting-edge AI research. This synergy allows us to build foundation models that are not only state-of-the-art but also deeply rooted in real-world operations.
With Degas, Earth Observation becomes more than data: it becomes intelligence for resilience, growth, and sustainability.

REQUEST A DEMO