SHI et al. (2026) A review of machine learning applications in inland and nearshore water color remote sensing: from preprocessing to object detection and parameter estimation

Identification

• Journal: Journal of Hydrology
• Year: 2026
• Date: 2026-06-29
• Authors: Jiarui SHI, Zuchuan Li, Ge Liu, Chong Fang, Zhidan Wen, Yingxin Shang, Hui Tao, Sijia Li, Qiang Wang, Zijin Wang, Kaishan Song
• DOI: 10.1016/j.jhydrol.2026.135950

Research Groups

• Northeast Institute of Geography and Agroecology, CAS, Changchun 130102, China
• University of Chinese Academy of Sciences, Beijing 100049, China
• Division of Natural and Applied Sciences, Duke Kunshan University, Suzhou 215316, China

Short Summary

This review synthesizes machine learning (ML) applications in inland and nearshore water color remote sensing, covering the full-chain workflow from preprocessing to object detection and parameter estimation. The study highlights recent progress, challenges, and emerging trends in ML-based remote sensing for water quality monitoring.

Objective

• To provide a comprehensive overview of ML applications in inland and nearshore water color remote sensing
• To identify key challenges and research gaps in the field

Study Configuration

• Spatial Scale: Global scale with focus on inland and nearshore waters
• Temporal Scale: Long-term, large-scale, and multi-scale analysis

Methodology and Data

• Models used: Machine learning (ML) techniques, including Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, Autoencoders (AE), Generative Adversarial Networks (GAN), and Transformers
• Data sources: Satellite remote sensing data from various sensors, including MODIS, Landsat, Sentinel-2

Main Results

• The study highlights the increasing adoption of ML techniques in inland and nearshore water color remote sensing
• The review identifies key challenges, including data scarcity, limited model interpretability, insufficient uncertainty quantification, and difficulties with multimodal data integration
• Emerging trends include multi-temporal data integration and incorporation of physical constraints

Contributions

• This review provides a comprehensive synthesis of ML applications in inland and nearshore water color remote sensing
• The study highlights the potential of ML techniques for improving remote sensing products and environmental monitoring in inland and coastal waters

Funding

• National Natural Science Foundation of China (Grant No. 42171292)
• Chinese Academy of Sciences (CAS) Youth Innovation Promotion Association (Grant No. 2019248)
• Duke Kunshan University Research Fund (Grant No. DKU2022001)

Citation

@article{SHI2026review,
  author = {SHI, Jiarui and Li, Zuchuan and Liu, Ge and Fang, Chong and Wen, Zhidan and Shang, Yingxin and Tao, Hui and Li, Sijia and Wang, Qiang and Wang, Zijin and Song, Kaishan},
  title = {A review of machine learning applications in inland and nearshore water color remote sensing: from preprocessing to object detection and parameter estimation},
  journal = {Journal of Hydrology},
  year = {2026},
  doi = {10.1016/j.jhydrol.2026.135950},
  url = {https://doi.org/10.1016/j.jhydrol.2026.135950}
}