EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Data-Driven Multi-Objective Optimization for Balancing Agricultural Productivity and Ecological Conservation in the Peiqiao River Watershed

Shuifeng Zhang, Yu Gao, Xin Liu, Yiqian Cang, Yang Zhang, Zheyan Gu

Data · 2026-10-30 · 11 (11) · 287

DOI: 10.3390/data11110287 ↗

At a glance

Journal article in Data, published online on 2026-10-30. Written by Shuifeng Zhang and 5 co-authors. 73 references. The full text is freely available (open access, CC BY 4.0). Funded by: Fundamental Research Funds for the Central Universities, Social Science Foundation of Jiangsu Province, Innovative and Entrepreneurial Doctor Program of Jiangsu Province, China.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

The sustainable management of agricultural watersheds requires reconciling agricultural productivity with ecological conservation, particularly in data-scarce regions. This study develops a data-driven multi-objective optimization framework (MOOF) for cultivated land use in the Peiqiao River watershed, a tributary of the Yangtze River. A comprehensive dataset was compiled, including high-resolution land use, soil physicochemical properties from 270 field-sampled cores, meteorological and hydrological records (2018–2023), and agricultural cost–benefit statistics. These data drove a coupled simulation system comprising the AnnAGNPS model for sediment and nutrient loads and an Economic Benefit Evaluation Model (EBEM) for net returns under various land-use configurations. A Multi-flip Tabu Search Algorithm (MTSA) iteratively linked simulation outputs with a penalty-constrained multi-objective function. Under predefined policy constraints and expert weights, the optimization identified a relative Pareto-improving land-use configuration rather than a global optimum. Sediment, total nitrogen, and total phosphorus loads decreased by 4.06%, 1.52%, and 1.74%, respectively, while economic benefit increased by 12.08% (from 32.75 to 36.71 million yuan). However, the TN and TP reductions are smaller than the calibrated model error and should be interpreted as indicative. The framework offers a managerial synergy pathway for green growth under ecological constraints in data-scarce agricultural watersheds.

Funding

  • Fundamental Research Funds for the Central Universities
  • Social Science Foundation of Jiangsu Province
  • Innovative and Entrepreneurial Doctor Program of Jiangsu Province, China
  • National Key R&D Program of China
  • Jiangsu Higher Education Institutions ‘Qinglan Project’

Cite

APA

Zhang, S., Gao, Y., Liu, X., Cang, Y., Zhang, Y., & Gu, Z. (2026). Data-Driven Multi-Objective Optimization for Balancing Agricultural Productivity and Ecological Conservation in the Peiqiao River Watershed. Data, 11(11), 287. https://doi.org/10.3390/data11110287

Vancouver

Zhang S, Gao Y, Liu X, Cang Y, Zhang Y, Gu Z. Data-Driven Multi-Objective Optimization for Balancing Agricultural Productivity and Ecological Conservation in the Peiqiao River Watershed. Data. 2026;11(11):287. doi:10.3390/data11110287

BibTeX
@article{Zhang2026,
  author = {Zhang, Shuifeng and Gao, Yu and Liu, Xin and Cang, Yiqian and Zhang, Yang and Gu, Zheyan},
  title = {Data-Driven Multi-Objective Optimization for Balancing Agricultural Productivity and Ecological Conservation in the Peiqiao River Watershed},
  journal = {Data},
  year = {2026},
  volume = {11},
  number = {11},
  pages = {287},
  doi = {10.3390/data11110287}
}
Start for free →