Sun Yuan, Wang Denghui, Li Lei, Ning Rongsheng, Yu Shuili, Gao Naiyun
State Key Laboratory of Pollution Control and Resource Reuse, College of Environmental Science and Engineering, Tongji University, Shanghai, 200092, China.
State Key Laboratory of Pollution Control and Resource Reuse, College of Environmental Science and Engineering, Tongji University, Shanghai, 200092, China; Shanghai Institute of Pollution Control and Ecological Security, Shanghai 200092, China.
Water Res. 2024 Dec 1;267:122546. doi: 10.1016/j.watres.2024.122546. Epub 2024 Sep 29.
Quantitative estimation is a key and challenging issue in water quality monitoring. Remote sensing technology has increasingly demonstrated its potential to address these challenges. Remote sensing imagery, combined with retrieval algorithms such as empirical band ratio methods, analytical bio-optical models, and semi-empirical three-band models, enables efficient, large-scale, real-time acquisition of water quality distribution characteristics, overcoming the limitations of traditional monitoring methods. Furthermore, artificial intelligence (AI), with its powerful autonomous learning capabilities and ability to solve complex problems, can deal with the nonlinear relationships between different spectral bands' apparent optical properties and various water quality parameter concentrations. This review provides a comprehensive overview of remote sensing applications in retrieving concentrations of nine water quality parameters, ranging from traditional methods to AI-based approaches. These parameters include chlorophyll-a (Chl-a), phycocyanin (PC), total suspended matter (TSM), colored dissolved organic matter (CDOM) and five non-optically active constituents (NOACs). Finally, it discusses five major issues that need further research in the application of remote sensing technology and AI in water quality monitoring. This review aims to provide researchers and relevant management departments with a potential roadmap and information support for innovative exploration in automated and intelligent water quality remote sensing monitoring.
水质监测中的定量估算既是关键问题，也是一项具有挑战性的任务。遥感技术已日益展现出应对这些挑战的潜力。遥感影像结合经验波段比值法、分析性生物光学模型和半经验三波段模型等反演算法，能够高效、大规模、实时地获取水质分布特征，克服了传统监测方法的局限性。此外，人工智能凭借其强大的自主学习能力和解决复杂问题的能力，能够处理不同光谱波段的表观光学特性与各种水质参数浓度之间的非线性关系。本文综述全面概述了遥感技术在反演九种水质参数浓度方面的应用，涵盖从传统方法到基于人工智能的方法。这些参数包括叶绿素a（Chl-a）、藻蓝蛋白（PC）、总悬浮物（TSM）、有色溶解有机物（CDOM）以及五种非光学活性成分（NOACs）。最后，本文讨论了在水质监测中应用遥感技术和人工智能时需要进一步研究的五个主要问题。本综述旨在为研究人员和相关管理部门提供一份潜在的路线图以及信息支持，助力其在水质遥感自动监测和智能监测方面进行创新性探索。
