How does Tessera work?

The model analyzes a full year of satellite images and compresses each 10-meter (33-foot) point of land into a string of numbers called an "embedding" — essentially a numerical fingerprint that captures how the land and its vegetation change over time. A simple algorithm, calibrated with just a few ground data points, can then convert those embeddings into a large-scale crop map.

This design is what makes Tessera cheap to run. Instead of requiring massive labeled datasets and heavy computation, it reuses the information embedded in freely available satellite imagery.

"With Tessera, you can train on the data you already have and extend it into the years in between, with more accurate crop information than baseline methods have ever been able to provide," Lisaius said. She added that governments, NGOs and other food security organizations can start using the technology now to produce their own crop statistics.

What did the researchers test?

The team used Tessera to map crops for 2018, 2019 and 2021, then compared it against:

• Two satellite mapping methods widely used for agricultural monitoring;
• Google DeepMind's AlphaEarth, a similar system whose underlying model is not public.

Each method was scored on accuracy, reliability, reusability and computational cost. Tessera came out on top overall. Crucially, it also held up best when trained on one year's data and applied to another year — suggesting it can keep producing maps without fresh ground surveys every season.

The current work builds on earlier published research showing that Tessera can map small fields in Austria.

What are the study's limitations?

The researchers flag two caveats. First, accuracy dropped between 2018 and 2021, a decline they believe stems from the quality of the ground survey data rather than the model itself. Second, the study did not test for secondary crops in fields where farmers grow more than one crop — a common practice that could shift the overall accuracy figures in the most diverse locations.

The comparison also covered only one region of one country, so extending the approach across West Africa and beyond remains to be demonstrated.

Is the goal perfection, or access?

For Lisaius, the point is not flawless accuracy. Tessera's real strength is who can use it.

"One of the great contributions of this technology is not that it's perfect, but that it's incredibly accessible," she said. "It's a step toward greater geospatial data democratization."

That view is echoed by humanitarian practitioners on the ground. Pierre Lucas, the WFP's representative and country director in Senegal, said:

"Reliable agricultural data is essential to anticipate food security and climate-related risks. In Senegal, WFP is working with national partners to explore how geospatial data and artificial intelligence can strengthen food security monitoring systems and support faster, more informed decision-making."

With a strong El Niño underway and rainfall patterns in West Africa under strain, tools that turn free satellite imagery into usable crop maps — without supercomputers or armies of surveyors — may arrive at exactly the right moment.