1.北京师范大学地理科学学部,北京 100875
2.北京师范大学文理学院,广东 珠海 519087
3.北京师范大学未来技术学院,广东 珠海 519087
4.深圳市罗湖外语实验学校,广东 深圳 518004
罗登楠(1997—),男,博士研究生,主要从事土地退化研究。E-mail:luodn@mail.bnu.edu.cn
唐杰(1992—),男,博士,副研究员,主要从事土壤侵蚀机理研究。E-mail:jietang@bnu.edu.cn
收稿:2026-02-05,
修回:2026-03-17,
录用:2026-03-23,
网络首发:2026-07-06,
纸质出版:2026-10-28
移动端阅览
罗登楠,唐杰,谢云,等.东北黑土区农田切沟侵蚀敏感性模型构建与跨流域适用性验证[J].水土保持学报,2026,40(5):104-114.
Luo Dengnan, Tang Jie, Xie Yun, et al. Modeling gully erosion susceptibility on cropland in Northeast China's black soil region: A cross-watershed assessment[J]. Journal of Soil and Water Conservation,2026,40(5):104-114.
罗登楠,唐杰,谢云,等.东北黑土区农田切沟侵蚀敏感性模型构建与跨流域适用性验证[J].水土保持学报,2026,40(5):104-114. DOI: 10.13870/j.cnki.stbcxb.2026.05.010. CSTR: 32310.14.stbcxb.2026.05.010.
Luo Dengnan, Tang Jie, Xie Yun, et al. Modeling gully erosion susceptibility on cropland in Northeast China's black soil region: A cross-watershed assessment[J]. Journal of Soil and Water Conservation,2026,40(5):104-114. DOI: 10.13870/j.cnki.stbcxb.2026.05.010. CSTR: 32310.14.stbcxb.2026.05.010.
目的
2
针对东北黑土区日益严重的切沟侵蚀问题,利用机器学习模型开展沟蚀风险的精准识别研究及在黑土区不同地理单元下的跨流域泛化能力研究,为制定差异化的水土流失防治策略及保障国家粮食安全提供科学依据与决策支持。
方法
2
以鹤北流域和双山流域为研究区,其中鹤北流域用于模型跨流域适用性验证,双山流域为训练区,构建跨流域预测范式。首先,通过文献计量法筛选出文献中使用最多的随机森林(RF)、支持向量机(SVM)和逻辑回归(LR)3种模型;然后,基于地形、水文及人类活动等15个因子构建预测模型,并采用跨流域特大降雨年后验证的方法,系统评估模型性能与跨流域适用性。
结果
2
1)随机森林模型表现最优(AUC为0.96),中等敏感等级以上的区域面积占比达78.7%;2)基于2019年与2021年2次特大降雨年的新增切沟验证表明,新增切沟与高风险区吻合区域面积超过52.0%;3)集水区面积、距河流距离与河网密度是核心驱动因子,人类活动与自然因子的交互作用显著促进切沟发育。
结论
2
通过引入跨流域建模和极端事件验证机制,研究结果可为东北黑土区切沟防治与土地可持续管理提供科学依据。
Objective
2
This study aims to accurately identify gully erosion susceptibility in the black soil region of northeast China using machine learning models. A primary focus is placed on evaluating the cross-watershed transferability of these models, thereby providing a robust scientific basis and decision support for developing conservation strategies and ensuring national food security.
Methods
2
In response, this paper constructs a cross-watershed prediction framework based on the Hebei and Shuangshan watersheds. The Shuangshan watershed served as the training set, while the Hebei watershed was designated for validating the model′s applicability across different catchments. First, three widely used models-Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR)were selected based on a bibliometric analysis. Subsequently, gully erosion susceptibility models were established based on 15 factors, including topography, hydrology, and human activities. Their performance and transferability were validated via post-hoc validation under cross-watershed extreme rainfall years.
Results
2
1) The RF model performs optimally (AUC=0.96), with the area proportion of regions above the moderate sensitivity level reaching a total of 78.7%; 2) Verification based on newly formed gullies from two extreme rainfall years (2019 and 2021) demonstrates that the overlap between newly formed gullies and high-sensitivity areas exceeds 52.0%; 3) Catchment area, distance to rivers, and river network density are key driving factors. Furthermore, the interaction between human activities and natural factors significantly promotes gully development.
Conclusion
2
This research establishes a scientific framework for gully erosion control and sustainable land management in the black soil region of northeast China through cross-watershed modeling and validation under extreme rainfall years.
姜芸 , 王军 , 张莉 . 东北典型黑土区侵蚀沟形态及分布特征 [J]. 农业工程学报 , 2020 , 36 ( 7 ): 157 - 165 .
Jiang Yun , Wang Jun , Zhang Li . Morphology and distribution characteristics of erosion gully in the typical black soil region of northeast China [J]. Transactions of the Chinese Society of Agricultural Engineering , 2020 , 36 ( 7 ): 157 - 165 .
王文娟 , 邓荣鑫 , 张树文 , 等 . 东北典型黑土区侵蚀沟发育演化特征分析 [J]. 地理与地理信息科学 , 2019 , 35 ( 4 ): 105 - 110 .
Wang Wenjuan , Deng Rongxin , Zhang Shuwen , et al . Development evolution characteristics of gully erosion in typical black soil region of northeast China [J]. Geography and Geo-Information Science , 2019 , 35 ( 4 ): 105 - 110 .
Poesen J , Nachtergaele J , Verstraeten G , et al . Gully erosion and environmental change: Importance and research needs [J]. Catena , 2003 , 50 ( 2/3/4 ): 91 - 133 .
Gudino-Elizondo N , Biggs T , Bingner R , et al . Modelling ephemeral gully erosion from unpaved urban roads: Equifinality and implications for scenario analysis [J]. Geosciences , 2018 , 8 ( 4 ): e137 .
Rodríguez-Caballero E , Cantón Y , Chamizo S , et al . Effects of biological soil crusts on surface roughness and implications for runoff and erosion [J]. Geomorphology , 2012 , 145/146 : 81 - 89 .
Chaplot V , Brown J , Dlamini P , et al . Rainfall simulation to identify the storm-scale mechanisms of gully bank retreat [J]. Agricultural Water Management , 2011 , 98 ( 11 ): 1704 - 1710 .
Thomas J T , Iverson N R , Burkart M R , et al . Long-term growth of a valley-bottom gully, western Iowa [J]. Earth Surface Processes and Landforms , 2004 , 29 ( 8 ): 995 - 1009 .
Arabameri A , Rezaei K , Pourghasemi H R , et al . GIS-based gully erosion susceptibility mapping: A comparison among three data-driven models and AHP knowledge-based technique [J]. Environmental Earth Sciences , 2018 , 77 ( 17 ): e628 .
Pourghasemi H R , Yousefi S , Kornejady A , et al . Performance assessment of individual and ensemble data-mining techniques for gully erosion modeling [J]. Science of the Total Environment , 2017 , 609 : 764 - 775 .
Huang Donghao , Su Lin , Fan Haoming , et al . Identification of topographic factors for gully erosion susceptibility and their spatial modelling using machine learning in the black soil region of northeast China [J]. Ecological Indicators , 2022 , 143 : e109376 .
Saha S , Sarkar R , Thapa G , et al . Modeling gully erosion susceptibility in Phuentsholing, Bhutan using deep learning and basic machine learning algorithms [J]. Environmental Earth Sciences , 2021 , 80 ( 8 ): e295 .
李珊珊 , 王春梅 , 唐杰 , 等 . 东北黑土区典型小流域浅沟向切沟发育及其地形临界研究 [J]. 武汉大学学报(信息科学版) , 2026 , 51 ( 2 ): 345 - 356 .
Li Shanshan , Wang Chunmei , Tang Jie , et al . Development processes from ephemeral to permanent gullies and their critical terrain thresholds in a typical watershed of the mollisol region, northeast China [J]. Geomatics and Information Science of Wuhan University , 2026 , 51 ( 2 ): 345 - 356 .
Tang Jie , Liu Gang , Xie Yun , et al . Ephemeral gullies caused by snowmelt: A ten-year study in northeastern China [J]. Soil and Tillage Research , 2021 , 212 : e105048 .
Gayen A , Pourghasemi H R , Saha S , et al . Gully erosion susceptibility assessment and management of hazard-prone areas in India using different machine learning algorithms [J]. Science of the Total Environment , 2019 , 668 : 124 - 138 .
Nagarajan R , Roy A , Vinod Kumar R , et al . Landslide hazard susceptibility mapping based on terrain and climatic factors for tropical monsoon regions [J]. Bulletin of Engineering Geology and the Environment , 2000 , 58 ( 4 ): 275 - 287 .
Conforti M , Aucelli P P C , Robustelli G , et al . Geomorphology and GIS analysis for mapping gully erosion susceptibility in the Turbolo stream catchment (northern Calabria, Italy) [J]. Natural Hazards , 2011 , 56 ( 3 ): 881 - 898 .
Arabameri A , Pradhan B , Lombardo L . Comparative assessment using boosted regression trees, binary logistic regression, frequency ratio and numerical risk factor for gully erosion susceptibility modelling [J]. Catena , 2019 , 183 : e104223 .
Garosi Y , Sheklabadi M , Conoscenti C , et al . Assessing the performance of GIS- based machine learning models with different accuracy measures for determining susceptibility to gully erosion [J]. Science of the Total Environment , 2019 , 664 : 1117 - 1132 .
Moore I D , Burch G J , MacKenzie D H . Topographic effects on the distribution of surface soil water and the location of ephemeral gullies [J]. Transactions of the ASAE , 1988 , 31 ( 4 ): 1098 - 1107 .
Kumari M , Singh C K , Bakimchandra O , et al . Geographically weighted regression based quantification of rainfall-topography relationship and rainfall gradient in central Himalayas [J]. International Journal of Climatology , 2017 , 37 ( 3 ): 1299 - 1309 .
Freeman T G . Calculating catchment area with divergent flow based on a regular grid [J]. Computers and Geosciences , 1991 , 17 ( 3 ): 413 - 422 .
Rahmati O , Tahmasebipour N , Haghizadeh A , et al . Evaluation of different machine learning models for predicting and mapping the susceptibility of gully erosion [J]. Geomorphology , 2017 , 298 : 118 - 137 .
Tang Jie , Liu Gang , Xie Yun , et al . Annual variation of ephemeral gully erosion in a cultivated catchment [J]. Geoderma , 2021 , 401 : e115166 .
Tang Jie , Liu Gang , Xie Yun , et al . Effect of topographic variations and tillage methods on gully erosion in the black soil region: A case-study from northeast China [J]. Land Degradation and Development , 2022 , 33 ( 18 ): 3786 - 3800 .
Conoscenti C , Sheshukov A Y . Regional variability of terrain index and machine learning model applications for prediction of ephemeral gullies [J]. Geomorphology , 2023 , 442 : e108915 .
Akgün A , Türk N . Mapping erosion susceptibility by a multivariate statistical method: A case study from the Ayvalık region, NW Turkey [J]. Computers and Geosciences , 2011 , 37 ( 9 ): 1515 - 1524 .
Nefeslioglu H A , Gokceoglu C , Sonmez H . An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps [J]. Engineering Geology , 2008 , 97 ( 3/4 ): 171 - 191 .
温艳茹 , 余强毅 , 杨扬 , 等 . 黑土小流域沟道分布遥感监测及主控因素研究 [J]. 农业资源与环境学报 , 2021 , 38 ( 6 ): 1074 - 1083 .
Wen Yanru , Yu Qiangyi , Yang Yang , et al . Gully distribution monitoring based remote sensing and key driving factors in the catchment scale of mollisol region [J]. Journal of Agricultural Resources and Environment , 2021 , 38 ( 6 ): 1074 - 1083 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621