计算机与现代化Issue(4)：70-76,7.DOI:10.3969/j.issn.1006-2475.2025.04.011
基于CNN-KAN的汶川地震灾区潜势泥石流流域识别方法
Identification Method for Potential Debris Flow Basins in the Wenchuan Earthquake-Affected Area Based on CNN-KAN
摘要
Abstract
The identification of potential debris flow basins often faces challenges such as unscientific watershed division crite-ria,unreasonable selection of non-debris flow basins,and insufficient model accuracy.A method combining river network den-sity with the self-organizing map(SOM)is proposed to accurately determine the optimal catchment area threshold for watershed division,with the SOM used to generate representative non-debris flow basins.A CNN-KAN model,based on an improved tradi-tional CNN architecture,is constructed to enhance identification accuracy.Experimental results indicate that the CNN-KAN model achieves a recognition accuracy of 92.9%,outperforming multilayer perceptron,KAN,and CNN models in precision,re-call,F1 score,and AUC.The identified potential debris flow basins can serve as essential computational units and focal areas for debris flow early warning in the region.关键词
汶川地震灾区/泥石流流域识别/集水面积阈值/SOM/CNN-KANKey words
Wenchuan earthquake-affected area/debris flow basin identification/catchment area threshold/SOM/CNN-KAN分类
信息技术与安全科学引用本文复制引用
周静,刘敦龙,桑学佳,张少杰,杨红娟..基于CNN-KAN的汶川地震灾区潜势泥石流流域识别方法[J].计算机与现代化,2025,(4):70-76,7.基金项目
国家自然科学基金青年资助项目(42001100) （42001100）
四川省科技计划项目(2024YFHZ0098,2023NSFSC0751) （2024YFHZ0098,2023NSFSC0751）
四川省信息化应用支撑软件工程技术研究中心开放课题(760115027,KYQN202317,KYTZ202278) （760115027,KYQN202317,KYTZ202278）
