International Research and Training Center on Erosion and Sedimentation,China Institute of Water Resources and Hydropower Research,Beijing 100048,China
Objective The study explores the optimal sample density for gully erosion risk prediction in typical small watersheds of the Loess Plateau and analyzes the main feature factors influencing gully occurrence, thereby providing a reference for gully erosion prevention and control. Methods The Random Forest (RF) model combined with SHAP algorithm was used to predict gully erosion risks at sample densities of 25%, 50%, 75%, and 100% of the total gully samples, and the contributions of the dominant factors to the model output were quantified. Results The 50% sample density achieved the best predictive performance, with accuracy, precision, and Kappa coefficient reaching 0.901, 0.894, and 0.802 respectively. These values significantly exceeded those of the 25% density (0.871, 0.851, 0.743), and were higher than the 75% (0.898, 0.882, 0.795) and 100% (0.899, 0.880, 0.798) density. The AUC values were 0.924, 0.956, 0.956, and 0.959 respectively across the four densities, and the recall rates were 0.887, 0.910, 0.917, and 0.924 respectively. Notably, the 50% density showed negligible differences in AUC value and recall rate compared to the 75% and 100% densities, so it was considered the optimal choice under the premise of ensuring accuracy. Conclusion Among all influence factors, land use type contributes the most to the gully erosion risk prediction, followed by slope and planar curvature. The coupling analysis of gully erosion risk and erosion severity indicates that moderate and severe erosion may occur in low-risk areas, suggesting that the gully erosion risk levels cannot fully represent the erosion severity, which provides a reference for gully erosion assessment and prevention in watersheds with similar conditions across the Loess Plateau.
ZhangN, ZhangY, WangJ X, et al. Quantity and morphological parameters of gullies in small watersheds in the hilly-gully Loess Plateau[J]. Journal of Soil and Water Conservation, 2023,37(3):109-115.
WangH L, JiaoJ Y, TangB Z, et al. Characteristics of rill erosion and its influencing factors in slope farmland after “7·26” rainstorm in Zizhou County, Shaanxi Province[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019,35(11):122-130.
YangL H, PangG W, YangQ K, et al. Changes and influencing factors of erosion gully in Wangmaogou watershed in the last 50 years[J]. Journal of Soil and Water Conservation, 2020,34(2):64-70.
WanZ K, SongQ C, WanP Q, et al. Research progress and hotspots of gully erosion in the black soil region of northeast: Bibliometric analysis based on CiteSpace[J]. Research of Soil and Water Conservation, 2024,31(2):454-463.
[11]
SetargieT A, TsunekawaA, HaregeweynN, et al. Random Forest-based gully erosion susceptibility assessment across different agro-ecologies of the Upper Blue Nile basin, Ethiopia[J]. Geomorphology, 2023,431:108671.
[12]
JiangC C, FanW, YuN Y, et al. Spatial modeling of gully head erosion on the Loess Plateau using a certainty factor and random forest model[J]. Science of the Total Environment, 2021,783:147040.
[13]
曹文悦.基于机器学习的区域尺度沟蚀易发性评价:以元江干热河谷为例[D].昆明:云南大学,2023.
[14]
CaoW Y. Evaluation of regional scale gully erosion susceptibility based on machine learning: a case study of Yuanjiang dry-hot valley[D]. Kunming: Yunnan University, 2023.
[15]
FilhoJ P M, GuerraA J T, CruzC B M, et al. Machine learning models for the spatial prediction of gully erosion susceptibility in the piraí drainage basin, paraíba do Sul middle valley, southeast Brazil[J]. Land, 2024,13(10):1665.
[16]
HuangD H, SuL, ZhouL L, et al. Assessment of gully erosion susceptibility using different DEM-derived topographic factors in the black soil region of Northeast China[J]. International Soil and Water Conservation Research, 2023,11(1):97-111.
[17]
AboutaibF, KrimissaS, PradhanB, et al. Evaluating the effectiveness and robustness of machine learning models with varied geo-environmental factors for determining vulnerability to water flow-induced gully erosion[J]. Frontiers in Environmental Science, 2023,11:1207027.
[18]
AmiriM, PourghasemiH R, GhanbarianG A, et al. Assessment of the importance of gully erosion effective factors using Boruta algorithm and its spatial modeling and mapping using three machine learning algorithms[J]. Geoderma, 2019,340:55-69.
[19]
程军奇.近52年甘肃黄土高原极端降水事件的变化特征[D].兰州:西北师范大学,2013.
[20]
ChengJ Q. Variation characteristic of extreme precipitation in Loess Plateau of Gansu Province Region in recent 52 years[D]. Lanzhou: Northwest Normal University, 2013.
LiH, ZhuB B, BianH, et al. Temporal and spatial changes in extreme precipitation and its driving factors in the water-wind erosion crisscross region of the Loess Plateau from 1970 to 2020[J]. Arid Land Geography, 2024,47(4):539-548.
YangL J, WangC M, ZhangC M, et al. Occurrence and development of newly formed gullies under extreme rainstorm conditions using remote sensing images[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022,38(6):96-104.
ChenZ X, WangW L, KangH L, et al. Gully development characteristics of the slopes for different land-use types under extreme rainstorms[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020,36(23):77-84.
LiuH Y, DuP F, ZhaoY, et al. Characteristics of gully erosion on buckwheat field in the Loess Plateau under heavy rainfall conditions: A case study in Dingbian County, Shaanxi Province[J]. Research of Soil and Water Conservation, 2024,31(5):1-8,17.
YangB, JiaoJ Y, MaX W, et al. Investigation and analysis of typical rainstorm erosion and flood disaster on Loess Plateau in 2022[J]. Bulletin of Soil and Water Conservation, 2022,42(6):1-13.
LiuB Y, YangY, LuS J. Discriminations on common soil erosion terms and their implications for soil and water conservation[J]. Science of Soil and Water Conservation, 2018,16(1):9-16.
WangL, XuJ, DongY W. Preliminary study on morphology and stability of erosion gully in typical small watersheds of Loess Plateau[J]. Bulletin of Soil and Water Conservation, 2018,38(1):126-130.
WangW J, DengR X, ZhangS W. Preliminary research on risk evaluation of gully erosion in typical black soil area of Northeast China[J]. Journal of Natural Resources, 2014,29(12):2058-2067.
LiJ J, ChenY L, JiaoJ Y, et al. Detecting gully occurrence risks using multivariate nonlinear spatial modeling in the Lhasa River Basin of China[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022,38(17):73-82.
JiangG, XiaoS R, YangX Z, et al. Vulnerability evaluation of landslide disaster in Badong County based on machine learning[J]. Express Water Resources & Hydropower Information, 2024,45(11):48-55.
ChenC C, WuQ, ZhangZ Y, et al. Spatiotemporal change of soil erosion in the middle and lower reaches of Lancangjiang River[J]. Research of Soil and Water Conservation, 2022,29(2):11-17,30.
WangS H, WangR S, SunX Y, et al. Landslide susceptibility evaluation based on CF-CNN-LSTM model[J]. Journal of Natural Disasters, 2024,33(5):84-95.
[45]
ChenW, PanahiM, TsangaratosP, et al. Applying population-based evolutionary algorithms and a neuro-fuzzy system for modeling landslide susceptibility[J]. Catena, 2019,172:212-231.
[46]
KannangaraK K P M, ZhouW H, DingZ, et al. Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022,14(4):1052-1063.
[47]
WeiY J, LiuZ, ZhangY, et al. Analysis of gully erosion susceptibility and spatial modelling using a GIS-based approach[J]. Geoderma, 2022,420:115869.