Remote Sensing of Particle Absorption Coefficient of Pigments Using a Two-Stage Framework Integrating Optical Classification and Machine Learning

Authors:
Open Access
Publisher website
Google Scholar
Abstract
The particle absorption coefficient of pigments (aph(λ)), a critical indicator of phytoplankton spectral absorption properties, is essential for bio-optical models and water quality monitoring. To enhance the accuracy of aph(λ) retrieval in complex aquatic environments, this study proposes a novel two-stage framework integrating optical classification and machine learning regression. Focusing on inland waters—key areas for eutrophication monitoring—we first developed an intelligent clustering method combining Kernel Principal Angle-based Component (KPAC) dimensionality reduction and Chameleon Swarm Algorithm (CSA)-optimized k-medoids to classify water bodies into four optical types based on hyperspectral reflectance features. Subsequently, an XGBoost regression model with L1-norm feature selection was applied to inversely derive aph(440), aph(555), aph(675), and aph(709) for each class. Experimental results demonstrated that optical classification significantly improved inversion accuracy: the determination coefficients R2 all exceeded 0.9 in classified datasets, with RMSE reduced by up to 93.1% compared to unclassified scenarios. This indicates that the strategy based on optical classification and regression inversion can effectively enhance the accuracy of pigment particle absorption coefficient inversions. In summary, this study, with the central objective of accurately measuring the pigment particle absorption coefficient, successfully developed a comprehensive set of optical classification and regression inversion methods applicable to various aquatic environments. This new scientific approach and powerful tool provide a means for monitoring and interpreting the pigment particle absorption characteristics in water bodies using remote sensing technology.
Funding Information
  • Hubei Provincial Environmental Protection Research Project (2022HB-01, 2025AFB981, 2024SKL011, 202203AC100001, ZSY/YG-JA(2024)012, 42101384, 2022M723535, SMK202205)
  • Hubei Provincial Natural Science Foundation Program (2022HB-01, 2025AFB981, 2024SKL011, 202203AC100001, ZSY/YG-JA(2024)012, 42101384, 2022M723535, SMK202205)
  • Key Laboratory of Lake and Watershed Science for Water Security (2022HB-01, 2025AFB981, 2024SKL011, 202203AC100001, ZSY/YG-JA(2024)012, 42101384, 2022M723535, SMK202205)
  • Key R&D Program of Yunnan Province, China (2022HB-01, 2025AFB981, 2024SKL011, 202203AC100001, ZSY/YG-JA(2024)012, 42101384, 2022M723535, SMK202205)
  • Danjiangkou Reservoir Hyperspectral Remote Sensing Water Quality Monitoring System Hyperspectral Water Quality Monitoring Platform Construction Project (2022HB-01, 2025AFB981, 2024SKL011, 202203AC100001, ZSY/YG-JA(2024)012, 42101384, 2022M723535, SMK202205)
  • National Natural Science Foundation of China (2022HB-01, 2025AFB981, 2024SKL011, 202203AC100001, ZSY/YG-JA(2024)012, 42101384, 2022M723535, SMK202205)
  • China Postdoctoral Science Foundation (2022HB-01, 2025AFB981, 2024SKL011, 202203AC100001, ZSY/YG-JA(2024)012, 42101384, 2022M723535, SMK202205)
  • Open Project of State Key Laboratory of Urban Water Resource and Environment, Harbin Institute of Technology (2022HB-01, 2025AFB981, 2024SKL011, 202203AC100001, ZSY/YG-JA(2024)012, 42101384, 2022M723535, SMK202205)

This publication has 38 references indexed in Scilit: