EUVIMEDEUVIMED entdecken
Crossref

Multigraph fusion neural network for predicting available cadmium levels in farmland soils

Ren-Jie Zhang, Shu-Fang Pan, Huai-Zeng Xing, Tian-Hao Dong, Sai-Hua Liu, Tao Xue, Fa-Xiang Tian, Hong-Yu Fu, Yun-He Xie, Xiong-Hui Ji

Environmental Pollution · 2025

DOI: 10.1016/j.envpol.2025.127225 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Pollution, 2025. Verfasst von Ren-Jie Zhang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Longping Branch, College of Biology, Hunan University, Changsha, 410125, China; Key Lab of Prevention, Control and Remediation of Soil Heavy Metal Po…. Hauptthemen laut MEDLINE: Cadmium, Soil Pollutants, Neural Networks, Computer, Environmental Monitoring. Die Arbeit nennt 69 Literaturangaben. Gefördert von: Natural Science Foundation of Hunan Province, Science and Technology Program of Hunan Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cadmium (Cd), a primary heavy metal pollutant in farmland soils, poses a significant threat to soil ecosystems and human health, developing accurate machine learning models to predict soil available Cd concentration is crucial for formulating effective remediation strategies. However, most existing models rely on the simple aggregation of multiple environmental and geographical variables to predict soil available Cd concentration, often neglecting the complex interrelationships among these variables and the spatial effects of geographic factors. In this work, a novel multigraph fusion neural network model based on the spatial relationships between sampling points and various geographic factors (elevation, mine, roads, and rivers) is proposed. By integrating multiple spatial relationship graphs, the model effectively captures the spatial effects of geographic factors on the farmland soil environment. The results demonstrate that the multigraph fusion model significantly outperforms the other models in predicting soil available Cd concentration, achieving R2 value of 0.82, RMSE value of 0.0338 mg kg-1, and MAE value of 0.0249 mg kg-1. Compared with the single-graph models and baseline models, the multigraph fusion model provides lower residual distribution range and more stable prediction performance. These findings validate the feasibility of incorporating the spatial effects of geographic factors to increase the prediction performance of soil available Cd concentration models and offer valuable analysis tools into the environmental drivers underlying the spatial heterogeneity in heavy metal contamination in farmland soils.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CadmiumSoil PollutantsNeural Networks, ComputerEnvironmental MonitoringSoilFarmsAgriculture

Stichwörter der Autor:innen

FarmlandGraphs fusionMachine learningSoil available CdSpatial effects

Substanzen

CadmiumSoil PollutantsSoil

Autor:innen und Institutionen

  • Longping Branch, College of Biology, Hunan University, Changsha, 410125, China; Key Lab of Prevention, Control and Remediation of Soil Heavy Metal Pollution, Hunan Institute of Agricultural Soil and Eco-Environment, Hun…
  • Key Lab of Prevention, Control and Remediation of Soil Heavy Metal Pollution, Hunan Institute of Agricultural Soil and Eco-Environment, Hunan Academy of Agricultural Sciences, Changsha, 410125, China; Key Laboratory of…
  • Jinan Academy of Agricultural Sciences, Jinan, 250300, China.

Förderung

  • Natural Science Foundation of Hunan Province
  • Science and Technology Program of Hunan Province
  • National Natural Science Foundation of China
  • Hunan Academy of Agricultural Sciences
  • National Key Research and Development Program of China

Zitieren

APA

Zhang, R. J., Pan, S. F., Xing, H. Z., Dong, T. H., Liu, S. H., Xue, T., Tian, F. X., Fu, H. Y., Xie, Y. H., & Ji, X. H. (2025). Multigraph fusion neural network for predicting available cadmium levels in farmland soils. Environmental Pollution. https://doi.org/10.1016/j.envpol.2025.127225

Vancouver

Zhang RJ, Pan SF, Xing HZ, Dong TH, Liu SH, Xue T, et al. Multigraph fusion neural network for predicting available cadmium levels in farmland soils. Environmental Pollution. 2025. doi:10.1016/j.envpol.2025.127225

BibTeX
@article{Zhang2025,
  author = {Zhang, Ren-Jie and Pan, Shu-Fang and Xing, Huai-Zeng and Dong, Tian-Hao and Liu, Sai-Hua and Xue, Tao and Tian, Fa-Xiang and Fu, Hong-Yu and Xie, Yun-He and Ji, Xiong-Hui},
  title = {Multigraph fusion neural network for predicting available cadmium levels in farmland soils},
  journal = {Environmental Pollution},
  year = {2025},
  doi = {10.1016/j.envpol.2025.127225}
}
Kostenlos starten →