Geo-OLM: Enabling Sustainable Earth Observation Studies with Cost-Efficient Open Language Models&State-Driven Workflows

2025-04-06

AI Summary

Large language models (LLMs) such as GPT-4o show promise for geospatial assistance in Earth observation and climate monitoring, but their high API costs and computational demands hinder sustainable deployment. Method: This paper proposes a state-driven LLM inference paradigm—the first to decouple task workflows from tool invocation—built upon a lightweight open-source LLM (<7B parameters), augmented with tool-integrated agents, on-the-fly LLM fine-tuning (OLM), collaborative execution, and a geospatial-specific evaluation benchmark. Contribution/Results: Experiments demonstrate a 32.8% improvement in query completion rate over the best open-source baseline, achieving 90% of GPT-4o’s performance while reducing per-inference cost from $500–$1,000 to under $10—a >99% reduction. The approach establishes a new paradigm for low-cost, high-performance, and reproducible geospatial automation.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Geospatial Copilots hold immense potential for automating Earth observation (EO) and climate monitoring workflows, yet their reliance on large-scale models such as GPT-4o introduces a paradox: tools intended for sustainability studies often incur unsustainable costs. Using agentic AI frameworks in geospatial applications can amass thousands of dollars in API charges or requires expensive, power-intensive GPUs for deployment, creating barriers for researchers, policymakers, and NGOs. Unfortunately, when geospatial Copilots are deployed with open language models (OLMs), performance often degrades due to their dependence on GPT-optimized logic. In this paper, we present Geo-OLM, a tool-augmented geospatial agent that leverages the novel paradigm of state-driven LLM reasoning to decouple task progression from tool calling. By alleviating the workflow reasoning burden, our approach enables low-resource OLMs to complete geospatial tasks more effectively. When downsizing to small models below 7B parameters, Geo-OLM outperforms the strongest prior geospatial baselines by 32.8% in successful query completion rates. Our method performs comparably to proprietary models achieving results within 10% of GPT-4o, while reducing inference costs by two orders of magnitude from $500-$1000 to under $10. We present an in-depth analysis with geospatial downstream benchmarks, providing key insights to help practitioners effectively deploy OLMs for EO applications.

Problem

• High costs of large models hinder sustainable Earth observation studies
• Open language models underperform in geospatial tasks without optimization
• Balancing performance and cost in geospatial AI workflows is challenging

Innovation

• State-driven LLM reasoning for task progression
• Cost-efficient open language models deployment
• Tool-augmented geospatial agent for sustainability