Google DeepMind has debuted AlphaEarth Foundations, an AI model that treats Earth like a living dataset, tracking crop cycles, coastlines, urban expansion, melting ice, and much, much more. The AlphaEarth Foundations team told IEEE Spectrum that one limitation in Earth observation is the inherent irregularity and sparsity of the data. In a paper posted in late July, Google DeepMind reported that AlphaEarth had a 23.9 percent lower error rate on average than competing approaches. Google DeepMind has been running tests with over 50 organizations worldwide in the last year. Google DeepMind; Google Earth EngineSchechter also pointed to examples such as the Brazilian nonprofit MapBiomas, which is now mapping environmental changes in the Amazon rainforest, and the Global Ecosystems Atlas, a program classifying unmapped ecosystems into shrublands, deserts, wetlands, and other categories.