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

作　　者：周静 刘敦龙 桑学佳 张少杰[3] 杨红娟[3] ZHOU Jing;LIU Dunlong;SANG Xuejia;ZHANG Shaojie;YANG Hongjuan(School of Software Engineering,Chengdu University of Information Technology,Chengdu 610225,China;Sichuan Provincial Engineering Research Center for Applied Software in Information Technology,Chengdu 610225,China;Institute of Mountain Hazards and Environment,Chinese Academy of Sciences,Chengdu 610041,China)

机构地区：[1]成都信息工程大学软件工程学院,四川成都610225 [2]四川省信息化应用支撑软件工程技术研究中心,四川成都610225 [3]中国科学院水利部成都山地灾害与环境研究所,四川成都610041

出　　处：《计算机与现代化》2025年第4期70-76,共7页Computer and Modernization

基　　金：国家自然科学基金青年资助项目(42001100);四川省科技计划项目(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)。

摘　　要：针对目前潜势泥石流流域识别中存在的流域划分标准不科学、非泥石流流域选取不合理以及分类模型精度不足等问题,本文提出一种结合河网密度法与自组织映射神经网络(SOM)的新方法,精确确定流域划分的最佳集水面积阈值并采用SOM生成具有代表性的非泥石流流域。在此基础上,构建一种基于KAN改进传统CNN网络架构的模型(CNNKAN),以提升潜势泥石流流域识别的准确性。实验结果表明,相比于原始的多层感知机、KAN和CNN,CNN-KAN模型识别准确率达到92.9%,且在精确率、召回率和F1分数以及AUC值上的表现均较其他模型更好。基于该模型划分的潜势泥石流流域,可作为区域内泥石流预警报的基本计算单元和重点关注区域。The identification of potential debris flow basins often faces challenges such as unscientific watershed division criteria,unreasonable selection of non-debris flow basins,and insufficient model accuracy.A method combining river network density 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 traditional 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,recall,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-KAN 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]