OSGR: Observation-Support Graph Reasoning for Earth Observation Question Answering
Organizations: Georgia State University
Abstract
Answering geographic queries over Earth observation (EO) archives requires solving a joint retrieval-and-derivation problem under strict spatiotemporal constraints. Existing LLM agents fail to ground observation items or suffer from search-space explosion. We propose OSGR, a two-stage framework that factorizes this search into offline symbolic concept deduction and online Relation-Conditioned Grounding. OSGR leverages an offline Observation-Support Graph to deduce valid target-to-result support paths at the concept level, and applies spatiotemporal compatibility kernels to instantiate grounded observation-item sets. On Earth-Bench and DisasterM3-Reason, OSGR improves GPT-4o accuracy from 49.3% to 63.7% while reducing the execution-step ratio from 2.9 to 2.5.
Figures & tables
| Method | ECR | EOR | EPM | TFA | SFA | RGA | Eff. 1 | Acc. |
|---|---|---|---|---|---|---|---|---|
| Closed-Source LLMs | ||||||||
| Direct LLM (GPT-4o) | 56.1 | 27.4 | 22.6 | 25.4 | 22.5 | 20.2 | 0.4 | 21.4 |
| ReAct Agent (GPT-4o) | 58.7 | 35.2 | 32.4 | 68.1 | 69.3 | 63.9 | 3.8 | 43.6 |
| GeoGraphRAG (GPT-4o) | 64.4 | 33.5 | 32.1 | 67.9 | 72.1 | 68.7 | 3.6 | 48.8 |
| Earth-Agent (GPT-4o-mini) | 53.6 | 43.7 | 32.9 | 54.5 | 79.4 | 57.3 | 2.0 | 46.4 |
| Earth-Agent (GPT-4o) | 61.3 | 44.1 | 33.7 | 57.6 | 78.5 | 69.3 | 2.9 | 49.3 |
| Variant | ECR | EOR | EPM | TFA | SFA | RGA | Eff. 1 | Acc. |
|---|---|---|---|---|---|---|---|---|
| w/o support graph | 46.2 | 33.8 | 29.4 | 67.2 | 80.6 | 52.9 | 4.7 | 43.9 |
| w/o relation-conditioned grounding | 73.4 | 50.7 | 40.0 | 58.8 | 59.4 | 61.3 | 3.7 | 53.2 |
| Full OSGR | 70.6 | 52.3 | 41.1 | 78.2 | 84.6 | 80.7 | 2.5 | 63.7 |
| Method | Avg. Acc. | BDC | DRE |
|---|---|---|---|
| Closed-Source LLMs | |||
| Direct LLM (GPT-4o) | 28.5 | 28.1 | 29.4 |
| ReAct Agent (GPT-4o) | 36.0 | 35.6 | 36.8 |
| GeoGraphRAG (GPT-4o) | 43.1 | 43.2 | 42.8 |
| Earth-Agent (GPT-4o) | 46.2 | 46.6 | 45.2 |
| OSGR (GPT-4o) | 50.1 8.4% | 49.8 6.9% | 50.7 12.2% |
Geospatial Reasoning
Geospatial reasoning studies how AI interprets locations, maps, spatial relationships, and Earth-observation data to answer questions and make decisions.
See all 79 papers