The optical insensitivity of non-optically active water quality parameters (NAWQPs) presents a significant challenge for remote sensing-based quantitative monitoring, which is an important tool for water quality assessment and management. Based on the analysis of the samples from Shanghai, China, it was found that the spectral morphological characteristics of the water body were obviously different under the combined effect of multiple NAWQPs. In view of this, in this paper, a machine learning method was proposed for the retrieval of urban NAWQPs by using multi-spectral scale morphological combined feature (MSMCF). The proposed method integrates both local and global spectral morphological features, and employs a multi-scale approach to enhance its applicability and stability, providing a more accurate and robust solution. To explore the applicability of the MSMCF method in retrieving urban NAWQPs, different methods were tested in terms of the retrieval accuracy and stability on the measured data and three different hyperspectral data. As can be seen from the results, the proposed method has good retrieval performance, which can be applied to hyperspectral data with different spectral resolutions with certain ability to suppress noise. Further analysis indicates that the sensitivity of each NAWQP to spectral morphological features varies. The research methods and findings in this paper can promote the development of hyperspectral and remote sensing technology in the prevention and treatment of urban water quality deterioration, and provide reference for related research.
Keywords: Hyperspectral remote sensing; Machine learning; Non-optically active water quality parameters; Spectral analysis.
Copyright © 2023 The Authors. Published by Elsevier B.V. All rights reserved.