EO-Gym supplies an executable multimodal environment and 9k-trajectory benchmark that turns Earth Observation into a tool-using, multi-step reasoning task, revealing that current VLMs struggle on temporal and cross-sensor workflows while fine-tuning lifts Pass@3 from 0.49 to 0.74.
GMES Sentinel-1 mission
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Sediment-specific ML models achieve surface soil moisture retrieval from Sentinel-1 and auxiliary data with RMSE 0.037-0.050 m³/m³ and R² up to 0.90 at a mining site.
citing papers explorer
-
EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agents
EO-Gym supplies an executable multimodal environment and 9k-trajectory benchmark that turns Earth Observation into a tool-using, multi-step reasoning task, revealing that current VLMs struggle on temporal and cross-sensor workflows while fine-tuning lifts Pass@3 from 0.49 to 0.74.
-
High Resolution Sediment-Specific Surface Soil Moisture Retrieval Using Sentinel-1 Time Series and Auxiliary Data
Sediment-specific ML models achieve surface soil moisture retrieval from Sentinel-1 and auxiliary data with RMSE 0.037-0.050 m³/m³ and R² up to 0.90 at a mining site.
- Global Offshore Wind Infrastructure: Deployment and Operational Dynamics from Dense Sentinel-1 Time Series