The Prithvi-EO Foundation Model, a collaborative effort led by NASA and IBM, represents a significant advancement in geospatial artificial intelligence for Earth observation. Specifically, Prithvi-EO-2.0, the latest iteration, is a transformer-based model pre-trained on over seven years of multispectral satellite imagery from NASA's Harmonized Landsat and Sentinel-2 (HLS) global dataset. This extensive training, involving approximately 4.2 million samples, enables the model to perform a wide array of Earth science tasks. One of its key applications, as indicated by the original article's title, is deforestation attribution. The model can classify drivers of deforestation and aid in monitoring land use and ecosystem dynamics, offering crucial insights into environmental changes. Beyond deforestation, Prithvi-EO-2.0 supports tasks such as flood and wildfire scar mapping, crop classification, and carbon cycle analysis. Benchmarking has shown Prithvi-EO-2.0 to deliver state-of-the-art performance, outperforming previous versions and several other geospatial foundation models across various remote sensing tasks. It significantly reduces computational requirements and the need for labeled data in downstream applications, making advanced geospatial AI more accessible. The project emphasizes open science, with the model, fine-tuning workflows, and training data openly released via platforms like Hugging Face and GitHub. This commitment to transparency and accessibility fosters interdisciplinary partnerships and democratizes access to advanced geospatial AI for the global Earth science community, accelerating scientific discovery in addressing critical environmental challenges worldwide.