Guo et al. (2026) Genetic programming for modeling water-energy-environment coupled systems: taking the upper Yangtze River basin as an example

Identification

• Journal: Journal of Hydrology
• Year: 2026
• Date: 2026-06-18
• Authors: Jun Guo, Taixin Zhang, Chao Wang, Zhongzheng He, Yue Wang, Jiahao Lu, Hui Qin
• DOI: 10.1016/j.jhydrol.2026.135885

Research Groups

• School of Infrastructure Engineering, Nanchang University (China)
• Key Laboratory of Poyang Lake Environment and Resources Utilization, Ministry of Education (China)
• School of Geography and Environment, Jiangxi Normal University (China)
• China Institute of Water Resources and Hydropower Research (China)
• Changjiang River Scientific Research Institute (China)
• School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology (China)

Short Summary

This study proposes a genetic programming-based modelling approach for water-energy-environment coupled systems, demonstrating its effectiveness in the Upper Yangtze River Basin.

Objective

• Investigate the performance of genetic programming (GP) in modeling water-energy-environment coupled systems compared to system dynamics (SD) and mainstream data-driven methods.

Study Configuration

• Spatial Scale: The Upper Yangtze River Basin, China.
• Temporal Scale: 23 years (1998–2020).

Methodology and Data

• Models used: Genetic Programming (GP), System Dynamics (SD), and 10 mainstream data-driven methods (including deep learning models).
• Data sources: Hydrological and socio-economic data for the Upper Yangtze River Basin.

Main Results

• The GP model achieved comparable accuracy to SD while avoiding complex mathematical derivations.
• Deep learning models suffered from severe over-fitting under small-sample conditions.
• Periodic and trend operators showed significant variable specificity with no universal pattern.

Contributions

• This study provides a practical alternative for WPE system modelling in data-scarce regions, balancing modelling accuracy and operability.
• The results offer scientific guidance for method selection in watershed management applications.

Funding

• This research was funded by the Key Laboratory of Poyang Lake Environment and Resources Utilization (Ministry of Education), China.

Citation

@article{Guo2026Genetic,
  author = {Guo, Jun and Zhang, Taixin and Wang, Chao and He, Zhongzheng and Wang, Yue and Lu, Jiahao and Qin, Hui},
  title = {Genetic programming for modeling water-energy-environment coupled systems: taking the upper Yangtze River basin as an example},
  journal = {Journal of Hydrology},
  year = {2026},
  doi = {10.1016/j.jhydrol.2026.135885},
  url = {https://doi.org/10.1016/j.jhydrol.2026.135885}
}