PEACE: Empowering Geologic Map Holistic Understanding with MLLMs

2025-01-10

AI Summary

Current large models exhibit limited capability in geological map understanding, hindering their application in critical domains such as natural hazard forecasting and mineral resource exploration. To address this underexplored scientific challenge, we introduce GeoMap-Bench—the first domain-specific benchmark for evaluating geological map comprehension—and propose GeoMap-Agent, the first dedicated intelligent agent for this task. GeoMap-Agent innovatively integrates three core components: hierarchical visual feature extraction, structured geological knowledge injection, and prompt-enhanced question answering, built upon a multimodal large language model foundation and augmented by a tool-integrated AI expert collaboration framework. Evaluated on GeoMap-Bench, GeoMap-Agent achieves an overall score of 0.811, substantially outperforming GPT-4o (0.369), and demonstrates significant improvements across five key capabilities: map parsing, referential understanding, spatial localization, logical reasoning, and holistic geological analysis.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: Remote Sensing / Geospatial AI
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Geologic map, as a fundamental diagram in geology science, provides critical insights into the structure and composition of Earth's subsurface and surface. These maps are indispensable in various fields, including disaster detection, resource exploration, and civil engineering. Despite their significance, current Multimodal Large Language Models (MLLMs) often fall short in geologic map understanding. This gap is primarily due to the challenging nature of cartographic generalization, which involves handling high-resolution map, managing multiple associated components, and requiring domain-specific knowledge. To quantify this gap, we construct GeoMap-Bench, the first-ever benchmark for evaluating MLLMs in geologic map understanding, which assesses the full-scale abilities in extracting, referring, grounding, reasoning, and analyzing. To bridge this gap, we introduce GeoMap-Agent, the inaugural agent designed for geologic map understanding, which features three modules: Hierarchical Information Extraction (HIE), Domain Knowledge Injection (DKI), and Prompt-enhanced Question Answering (PEQA). Inspired by the interdisciplinary collaboration among human scientists, an AI expert group acts as consultants, utilizing a diverse tool pool to comprehensively analyze questions. Through comprehensive experiments, GeoMap-Agent achieves an overall score of 0.811 on GeoMap-Bench, significantly outperforming 0.369 of GPT-4o. Our work, emPowering gEologic mAp holistiC undErstanding (PEACE) with MLLMs, paves the way for advanced AI applications in geology, enhancing the efficiency and accuracy of geological investigations.

Problem

• Geological Map Interpretation
• Super Intelligence Model Limitations
• Geological Application Restrictions

Innovation

• GeoMap-Bench
• GeoMap-Agent
• Hierarchical Information Extraction