arXiv 2501.061842025-01-10cs.CVcs.AIcs.CEcs.HCcs.MA

PEACE：利用多模态大语言模型赋能地质图整体理解

PEACE: Empowering Geologic Map Holistic Understanding with MLLMs

Microsoft Research（微软研究院）；Chinese Academy of Geological Sciences（中国地质科学研究院）；Wuhan University（武汉大学）

Yangyu Huang, Tianyi Gao, Haoran Xu, Qihao Zhao, Yang Song, Zhipeng Gui, Tengchao Lv, Hao Chen, Lei Cui, Scarlett Li, Furu Wei

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对多模态大语言模型在地质图理解上的不足，本文构建了首个评估基准GeoMap-Bench，并提出首个地质图理解智能体GeoMap-Agent，通过三大模块和AI专家组协作显著提升了性能。

摘要：

地质图作为地质科学的基础图表，为地球地下和表面的结构与组成提供了关键见解。这些图在灾害检测、资源勘探和土木工程等多个领域不可或缺。尽管意义重大，当前的多模态大语言模型（MLLMs）在地质图理解方面往往表现不足。这一差距主要源于制图综合的挑战性，包括处理高分辨率地图、管理多个关联组件以及需要领域特定知识。为量化这一差距，我们构建了GeoMap-Bench，这是首个用于评估MLLMs地质图理解能力的基准，它评估了在提取、指代、定位、推理和分析方面的全尺度能力。为弥合这一差距，我们引入了GeoMap-Agent，这是首个专为地质图理解设计的智能体，包含三个模块：分层信息提取（HIE）、领域知识注入（DKI）和提示增强问答（PEQA）。受人类科学家跨学科合作的启发，一个AI专家组充当顾问，利用多样化的工具池来全面分析问题。通过全面实验，GeoMap-Agent在GeoMap-Bench上取得了0.811的总分，显著优于GPT-4o的0.369。我们的工作，即利用MLLMs赋能地质图整体理解（PEACE），为地质学中的高级AI应用铺平了道路，提升了地质调查的效率和准确性。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。