EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The impact of rainfall and slope on hillslope runoff and erosion depending on machine learning

Naichang Zhang, Zhaohui Xia, Peng Li, Qitao Chen, Ganggang Ke, Fan Yue, Yaotao Xu, Tian Wang

Frontiers in Environmental Science · 24.04.2025 · 13

DOI: 10.3389/fenvs.2025.1580149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Environmental Science, online erschienen am 24.04.2025. Verfasst von Naichang Zhang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Soil erosion is a critical issue faced by many regions around the world, especially in the purple soil hilly areas. Rainfall and slope, as major driving factors of soil erosion, pose a significant challenge in quantifying their impact on hillslope runoff and sediment yield. While existing studies have revealed the effects of rainfall intensity and slope on soil erosion, a comprehensive analysis of the interactions between different rainfall types and slope is still lacking. To address this gap, this study, based on machine learning methods, explores the effects of rainfall type, rainfall amount, maximum 30-min rainfall intensity (I30), and slope on hillslope runoff depth (H) and erosion-induced sediment yield (S), and unveils the interactions among these factors.

Methods

The K-means clustering algorithm was used to classify 43 rainfall events into three types: A-type, B-type, and C-type. A-type is characterized by long duration, large rainfall amounts, and moderate intensity; B-type by short duration, small rainfall amounts, and high intensity; and C-type is intermediate between A-type and B-type. The Random Forest (RF) algorithm was employed to assess the impacts of these factors on runoff and sediment yield, along with a feature importance analysis.

Results

The results show that rainfall amount has the most significant impact on runoff and sediment yield. Under different rainfall types, the ranking of the effects of rainfall amount and I30 on H and S is as follows: rainfall amount (C>A>B), I30 (A>B>C). The impact of slope follows a trend of first increasing and then decreasing, with varying degrees of influence on H and S depending on the rainfall type.

Discussion

The novelty of this study lies in combining machine learning techniques to systematically evaluate, for the first time, the interactions between rainfall type and slope and their impact on hillslope runoff and sediment yield in purple soil hilly areas. This research not only provides a theoretical basis for soil erosion control but also offers scientific support for the precise prediction and management of soil conservation measures in purple soil regions.

Zitieren

APA

Zhang, N., Xia, Z., Li, P., Chen, Q., Ke, G., Yue, F., Xu, Y., & Wang, T. (2025). The impact of rainfall and slope on hillslope runoff and erosion depending on machine learning. Frontiers in Environmental Science, 13. https://doi.org/10.3389/fenvs.2025.1580149

Vancouver

Zhang N, Xia Z, Li P, Chen Q, Ke G, Yue F, et al. The impact of rainfall and slope on hillslope runoff and erosion depending on machine learning. Frontiers in Environmental Science. 2025;13. doi:10.3389/fenvs.2025.1580149

BibTeX
@article{Zhang2025,
  author = {Zhang, Naichang and Xia, Zhaohui and Li, Peng and Chen, Qitao and Ke, Ganggang and Yue, Fan and Xu, Yaotao and Wang, Tian},
  title = {The impact of rainfall and slope on hillslope runoff and erosion depending on machine learning},
  journal = {Frontiers in Environmental Science},
  year = {2025},
  volume = {13},
  doi = {10.3389/fenvs.2025.1580149}
}
Kostenlos starten →