We develop novel algorithms for monitoring environmental changes and biodiversity at a global scale using remote sensing data. Our recent work includes retrieval-augmented neural fields for multi-resolution geo-embeddings (RANGE), language-driven species distribution modeling (LD-SDM), and probabilistic multimodal embedding models for ecology (ProM3E). We also work on satellite image synthesis with structured semantics (VectorSynth), fine particulate matter estimation using deep learning, and agricultural field boundary delineation at global scales. Our research spans applications from Arctic tundra monitoring to urban air quality assessment, leveraging high-resolution satellite imagery and computer vision techniques to address critical environmental challenges.