Cheng et al. (2026) Spatiotemporal dynamics and driving mechanisms of suspended sediment concentration in the Yellow River revealed by machine learning and multi-source remote sensing

Identification

• Journal: CATENA
• Year: 2026
• Date: 2026-09-24
• Authors: Zhaolin Cheng, Yi He, Yuhang Lian
• DOI: 10.1016/j.catena.2026.110610

Research Groups

College of Urban and Environmental Sciences, Northwest University, Xi'an, China; Shaanxi Provincial Key Laboratory of Earth Surface System and Environmental Carrying Capacity, College of Urban and Environmental Sciences, Northwest University, Xi'an, China.

Short Summary

This study developed a machine learning-based remote sensing inversion model to monitor suspended sediment concentration (SSC) in the Yellow River from 1986 to 2019. The results showed a significant decline in SSC with climate and hydrological factors being primary influences.

Objective

• Investigate the spatiotemporal dynamics of suspended sediment concentration (SSC) in the Yellow River using machine learning and multi-source remote sensing technologies.
• Identify the driving mechanisms behind SSC variability in the Yellow River Basin.

Study Configuration

• Spatial Scale: The study focused on the main stream and five major tributaries in the middle reaches of the Yellow River, covering a total length of approximately 1800 km.
• Temporal Scale: The study period spanned from 1986 to 2019, allowing for an analysis of long-term SSC dynamics.

Methodology and Data

• Models used: XGBoost-based machine learning model was developed for SSC inversion, outperforming other models such as linear regression and random forest.
• Data sources: Multi-source remote sensing data from satellite platforms were utilized to develop the SSC inversion model.

Main Results

• The XGBoost-based SSC inversion model achieved an R2 of 0.78, RMSE of 1685.74 mg/L, and MAE of 967 mg/L.
• SSC in the Yellow River declined significantly between 1986 and 2019, with an annual average decrease of 75.4 mg/L, totaling a 63.6% reduction.
• Spatially, 97.39% of monitored river sections showed a decline, with 50% of these passing significance tests (p < 0.05).

Contributions

• This study provides a practical framework for remote sensing-based SSC monitoring in rivers with varying turbidity levels.
• The findings offer insights for water-sediment resource management and ecological conservation in the Yellow River Basin.

Funding

• National Natural Science Foundation of China (Grant No. 42171023)
• Shaanxi Provincial Key Laboratory of Earth Surface System and Environmental Carrying Capacity (Grant No. SKL2021001)

Citation

@article{Cheng2026Spatiotemporal,
  author = {Cheng, Zhaolin and He, Yi and Lian, Yuhang},
  title = {Spatiotemporal dynamics and driving mechanisms of suspended sediment concentration in the Yellow River revealed by machine learning and multi-source remote sensing},
  journal = {CATENA},
  year = {2026},
  doi = {10.1016/j.catena.2026.110610},
  url = {https://doi.org/10.1016/j.catena.2026.110610}
}