OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation
By: Henry Herzog , Favyen Bastani , Yawen Zhang and more
Potential Business Impact:
Helps track Earth changes better with smart AI.
Earth observation data presents a unique challenge: it is spatial like images, sequential like video or text, and highly multimodal. We present OlmoEarth: a multimodal, spatio-temporal foundation model that employs a novel self-supervised learning formulation, masking strategy, and loss all designed for the Earth observation domain. OlmoEarth achieves state-of-the-art performance compared to 12 other foundation models across a variety of research benchmarks and real-world tasks from external partners. When evaluating embeddings OlmoEarth achieves the best performance on 15 out of 24 tasks, and with full fine-tuning it is the best on 19 of 29 tasks. We deploy OlmoEarth as the backbone of an end-to-end platform for data collection, labeling, training, and inference of Earth observation models. The OlmoEarth Platform puts frontier foundation models and powerful data management tools into the hands of non-profits and NGOs working to solve the world's biggest problems. OlmoEarth source code, training data, and pre-trained weights are available at $\href{https://github.com/allenai/olmoearth_pretrain}{\text{https://github.com/allenai/olmoearth_pretrain}}$.
Similar Papers
EarthMind: Towards Multi-Granular and Multi-Sensor Earth Observation with Large Multimodal Models
CV and Pattern Recognition
Helps computers understand planet pictures better.
Geo-OLM: Enabling Sustainable Earth Observation Studies with Cost-Efficient Open Language Models & State-Driven Workflows
Machine Learning (CS)
Makes Earth-watching AI cheaper and smarter.
The Transparent Earth: A Multimodal Foundation Model for the Earth's Subsurface
Machine Learning (CS)
Maps Earth's hidden layers from many clues.