Cambridge AI tool maps crops in Senegal with 84% accuracy
Researchers at the University of Cambridge used Tessera, an open-source AI model trained on satellite images, to map crops in Senegal's groundnut basin and found it achieved 84% accuracy while requiring fewer computational resources than alternative methods. In one test scenario, Tessera performed 28% better than the next-best model. The study, published on 29 September in Environmental Research: Food Systems, compared Tessera with two widely-used satellite mapping methods and Google DeepMind's AlphaEarth, finding that Tessera held up best when trained on one year's data and applied to another year without requiring new ground surveys.
