DeepEarth is a self-supervised, multi-modal, spatio-temporal GeoAI model for global environmental intelligence and optimization.
DeepEarth learns by jointly reconstructing masked multi-modal datasets (as seen above). It uses a novel space-time positional encoder, Earth4D, especially for earth observation data (as seen below).
-
December 22, 2025
10x faster. Following state-of-the-art Earth4D experiments by Brandon Voelker on small batches, Lance Legel sped up small batch processing by 10x. See commit and CUDA code. -
December 19, 2025
Supercomputing award. US DOE National Energy Research Scientific Computing Center has awarded a DeepEarth team with supercomputing access in 2026 through EESSD. -
December 2, 2025
Peer-reviewed presentation in top venue. Accepted to the 2026 World Modeling Workshop at the Mila Quebec AI Institute, alongside keynote talks by Yoshua Bengio and Yann LeCun. See paper. -
November 17, 2025
99% parameter reduction, 4× speedup. Earth4D with learned hash probing tested on an ecological benchmark demonstrates spectacular accuracy with 5M parameters. See code. -
November 16, 2025
23% error reduction in space-time encoder. Lance Legel and Qin Huang implemented learned hash probing in Earth4D, achieving state-of-the-art R² on an ecological forecasting benchmark. See commit. -
October 29, 2025
Predicting risk of fires. Qin Huang, Brandon Voelker, and Lance Legel presented on simulating live fuel moisture content through NSF's Institute for Geospatial Understanding. See event. -
October 27, 2025
Battle-hardened (x, y, z, t) AI. For our spatio-temporal multi-resolution hash encoding, we've fixed a numerical bug in NVIDIA's CUDA kernels based on profiling of hash collisions. -
September 30, 2025
Presentation at top AI lab. Thanks to the Allen Institute for AI for hosting a 1 hour talk with scientists pioneering AI foundation models for the planet. See video and slides. -
August 8, 2025
NSF summer school program. NSF funded a week-long "Spatial AI for Disaster Resilience" summer school program in Boulder, Colorado. 5 PhD students researched and developed DeepEarth. See demos. -
June 23, 2025
Workshop in Chicago. NSF funded a 3 hour workshop on DeepEarth in Chicago for a "GeoAI for Sustainability" conference. 3 professors, 5 postdocs, and 2 PhD students contributed. See slides.
DeepEarth is an open source project for solving intelligence across the planet 🌎. We aspire to help solve major sustainability challenges including climate resilience and biodiversity.
Collaborators welcomed! Contact Lance Legel at lance@ecodash.ai or submit an issue/PR here.
For further details, see papers: