94% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Environ. Sci.
Sec. Soil Processes
Volume 13 - 2025 | doi: 10.3389/fenvs.2025.1580149
This article is part of the Research TopicSoil and Water Loss and Environmental EffectsView all 9 articles
The Impact of Rainfall and Slope on Hillslope Runoff and Erosion Depending on Machine Learning
Provisionally accepted- 1PowerChina Northwest Engineering Corporation Limited,, Xi'an, Shanxi, China
- 2Xi'an University of Technology, Xi'an, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
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-minute rainfall intensity (I30), and slope on hillslope runoff depth (H) and erosion-induced sediment yield (S), and unveils the interactions among these factors. 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. 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. 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.
Keywords: Purple soil1, random forest2, Clustering algorithm3, Slope scale4, Soil erosion5
Received: 20 Feb 2025; Accepted: 08 Apr 2025.
Copyright: © 2025 Zhang, Xia, Li, Chen, Ke, Yue, Xu and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Peng Li, Xi'an University of Technology, Xi'an, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.