文献类型：期刊文献

英文题名：Application of Artificial Intelligence in Ecosystem Services Research: Current Status, Challenges, and Prospects

作者：Han, Huiqing Yuan, Xiaosong Zhang, Yingjia Jian, Yuanju

通信作者：Han, HQ[1]

机构：[1]Guizhou Inst Technol, Coll Architecture & Urban Planning, Guiyang 550025, Peoples R China

第一机构：贵州理工学院

通信机构：corresponding author), Guizhou Inst Technol, Coll Architecture & Urban Planning, Guiyang 550025, Peoples R China.|贵州理工学院;

年份：2025

卷号：18

期号：4

起止页码：589-602

外文期刊名：CONTEMPORARY PROBLEMS OF ECOLOGY

收录：;Scopus(收录号：2-s2.0-105012627925);WOS:【SCI-EXPANDED(收录号:WOS:001546486000008)】；

基金：This work was supported by the Guizhou provincial science and technology project (ZK[2023]018), the Natural Science Research Project of Education Department of Guizhou Province (KY[2021]075) and the Humanities and Social Science research project of Guizhou Education Department (2022GBzd004).

语种：英文

外文关键词：Artificial intelligence; ecosystem services; remote sensing data; decision support; data integration; ecological restoration

摘要：The application of artificial intelligence (AI) in ecosystem services (ES) research has made significant progress, particularly in ecological monitoring, assessment, and decision support. As technology continues to evolve, AI exhibits great potential in remote sensing data processing, ecosystem model optimization, and data integration. Through automated classification and trend analysis, AI can efficiently monitor the spatiotemporal variations of ES, thereby enhancing the precision of ecosystem management. Moreover, by integrating big data and the Internet of Things, AI has diversified ES assessments, enabling the effective integration of information from various data sources to support ecological conservation and resource management. AI's advantage in ecological monitoring lies in its ability to capture environmental changes in real-time using intelligent algorithms, ensuring the continuous stability of ES and providing scientific foundations for ecological restoration and sustainable management. In decision support systems, AI optimization algorithms can enhance environmental governance by offering precise decision-making, thus improving ecosystem management efficiency. However, AI still faces challenges in ES research, such as data quality, model adaptability, and interpretability. Future research should focus on the integration of AI with ecological management practices, improving the interpretability of AI models, and addressing their generalizability issues. Interdisciplinary collaboration will be a key pathway for the advancement of AI in ES research, promoting its applications in global environmental governance and ecological restoration.