释放ChatGPT在探测轨道碳观测卫星-3捕获的XCO热点方面的潜力。

Unlocking the potential of ChatGPT in detecting the XCO hotspot captured by orbiting carbon observatory-3 satellite.

作者信息

Hwang Young-Seok, Schlueter Stephan, Pradhan Biswajeet, Um Jung-Sup

机构信息

Data Solution Business Team, HANCOM InSpace, Daejeon, 34126, Korea.

Department of Mathematics, Natural and Economic Sciences, Ulm University of Applied Sciences, 89075, Ulm, Germany.

出版信息

Sci Rep. 2025 Aug 7;15(1):28969. doi: 10.1038/s41598-025-13240-8.

DOI:10.1038/s41598-025-13240-8

PMID:40775428

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12332174/

Abstract

This study assesses the practical implications of ChatGPT's ability to identify hotspots by comparing its performance to Geographical Information System (GIS) software in detecting CO sources and sinks observed by the Orbiting Carbon Observatory-3 (OCO-3) satellite. ChatGPT exhibited performance comparable to ArcGIS in both z-score statistics and spatial distribution patterns of XCO hot and cold spots. The results generated by ChatGPT showed a strong correlation with ArcGIS-generated hotspots, demonstrating a z-score correlation coefficient of R²=0.82 and a cosine similarity score of 0.90. As multimodal artificial intelligence becomes more prevalent in earth monitoring, ChatGPT is expected to be a valuable tool for identifying CO emission patterns, particularly for users who lack specialized GIS expertise. These findings establish a significant benchmark for ChatGPT's potential in this field, offering a novel approach to identifying area-wide spatial patterns of CO emissions compared to conventional GIS software.

摘要

本研究通过将ChatGPT识别热点的能力与地理信息系统（GIS）软件在检测轨道碳观测卫星-3（OCO-3）观测到的一氧化碳源和汇方面的性能进行比较，评估了其实际意义。在XCO热点和冷点的z分数统计和空间分布模式方面，ChatGPT表现出与ArcGIS相当的性能。ChatGPT生成的结果与ArcGIS生成的热点显示出很强的相关性，z分数相关系数R² = 0.82，余弦相似度得分0.90。随着多模态人工智能在地球监测中变得越来越普遍，ChatGPT有望成为识别一氧化碳排放模式的宝贵工具，特别是对于缺乏专业GIS专业知识的用户。这些发现为ChatGPT在该领域的潜力建立了一个重要基准，与传统GIS软件相比，提供了一种识别区域范围内一氧化碳排放空间模式的新方法。