Lin et al. (2026) Study on Nonlinear Driving Mechanisms of Spatiotemporal Evolution in Sanjiang Plain Wetlands Based on Explainable Learning Methods

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Remote Sensing
• Year: 2026
• Date: 2026-09-11
• Authors: Nan Lin, Yanan Lu, Ruifei Zhu, Menghong Wu, Hao Yu, Zeyue Jing, Chenglong Xu, Botao Zhang, Ranzhe Jiang
• DOI: 10.3390/rs18183132

Research Groups

• Key Laboratory of Wetland Ecology and Environment, Northeast Institute of Geography and Limnology, Chinese Academy of Sciences
• Department of Earth System Science, University of California, Irvine

Short Summary

This study integrates machine learning models to investigate the nonlinear driving mechanisms of spatiotemporal wetland evolution in the Sanjiang Plain, China. The results reveal stage-dependent patterns and shifting dominant drivers of wetland change.

Objective

• Investigate the nonlinear effects and interactions among driving mechanisms governing wetland evolution across space and time

Study Configuration

• Spatial Scale: Regional (Sanjiang Plain)
• Temporal Scale: 1990-2023 (33 years)

Methodology and Data

• Models used: Light Gradient Boosting Machine, SHapley Additive exPlanations
• Data sources: Multitemporal remote sensing data from 1990 to 2023

Main Results

• Wetland dynamics exhibited a stage-dependent pattern characterized by substantial natural-wetland loss in the early period (1990-2005), followed by partial marsh-wetland recovery and continued artificial-wetland expansion.
• Nonlinear interactions among driving factors shifted from synergistic promotion by natural factors in the early stage to inhibitory effects among natural, socioeconomic, and locational factors in the later stage.

Contributions

• This study provides a comprehensive understanding of the intrinsic processes governing wetland evolution, highlighting the importance of considering nonlinear effects and multifactor interactions.
• The results offer scientific support for regional wetland management and remote sensing monitoring.

Funding

• National Natural Science Foundation of China (Grant No. 42071023)
• Chinese Academy of Sciences Youth Innovation Promotion Association (Grant No. 2019003)

Citation

@article{Lin2026Study,
  author = {Lin, Nan and Lu, Yanan and Zhu, Ruifei and Wu, Menghong and Yu, Hao and Jing, Zeyue and Xu, Chenglong and Zhang, Botao and Jiang, Ranzhe},
  title = {Study on Nonlinear Driving Mechanisms of Spatiotemporal Evolution in Sanjiang Plain Wetlands Based on Explainable Learning Methods},
  journal = {Remote Sensing},
  year = {2026},
  doi = {10.3390/rs18183132},
  url = {https://doi.org/10.3390/rs18183132}
}