多维CNN耦合的滑坡易发性评价方法  

A Multi-dimensional CNN Coupled Landslide Susceptibility Assessment Method

作　　者：赵占骜 王继周[2] 毛曦[2] 马维军[2] 路文娟[2] 何毅 高轩宇 ZHAO Zhanao;WANG Jizhou;MAO Xi;MA Weijun;LU Wenjuan;HE Yi;GAO Xuanyu(Faculty of Geomatics,Lanzhou Jiaotong University,Lanzhou 730070,China;Chinese Academy of Surveying and Mapping,Beijing 100830,China;College of Geodesy and Geomatics,Shandong University of Science and Technology,Qingdao 266590,China)

机构地区：[1]兰州交通大学测绘与地理信息学院,甘肃兰州730070 [2]中国测绘科学研究院,北京100830 [3]山东科技大学测绘与空间地理信息学院,山东青岛266590

出　　处：《武汉大学学报（信息科学版）》2024年第8期1466-1481,共16页Geomatics and Information Science of Wuhan University

基　　金：国家重点研发计划“国家大型工程智能建造数字化测绘装备研发与应用”(SQ2020YFF0426312);色东普沟无人机遥感监测及应用(AR1936)。

摘　　要：卷积神经网络(convolutional neural network,CNN)因其强大的特征提取能力被广泛应用于滑坡易发性评价。然而,随着场景多样化和高精度的需求,CNN算法不断改进,通过加深网络层次或联合其他模型来提高精度的做法往往大幅增加模型参数量和计算量,导致模型训练困难或结果过拟合,进而限制其实际应用。提出构建多维CNN耦合模型解决以上问题,通过特征图非对称聚合连结二维CNN(two-dimensional CNN,2D-CNN)和一维CNN(one-dimensional CNN,1D-CNN),维持网络深度而限制模型参数并减少计算量;利用多维卷积核参数共享捕获各滑坡影响因子不同维度及因子之间的深层耦合特征,实现特征充分利用而避免过拟合。以中国西藏自治区色东普沟为实验区,选取11种滑坡影响因子分析该地滑坡易发性。结果表明,因计算量减小,多维CNN耦合结构与参数较少的浅层2D-CNN效率相当,而比参数量近似的深层2D-CNN训练时长大幅减小,模型训练成本降低。此外,耦合模型相比独立1D-CNN和2D-CNN特征学习能力增强,模型精度提升,在测试集数据各混淆矩阵指标下拥有更高评分,进而获得了具有更高可信度的滑坡易发性评价结果。所提出的多维CNN耦合模型是一种适用于滑坡易发性评价的可靠方法,为进一步滑坡灾害监测和预防提供了新的理论指导与技术支持。Objectives:Convolutional neural network(CNN)was widely used in landslide susceptibility assessment because of its powerful feature extraction capability.However,with the demand for scene diversification and high accuracy,the algorithm of CNN was constantly improved.The practice of improving accuracy by deepening the network hierarchy or combining other models tended to increase the number of model parameters and the amount of calculation greatly,which led to the difficulty of model training or the overfitting of results,thus limiting its practical application.We want to solve the above problems from the model structure.Methods:We proposed to build a multi-dimensional CNN coupling model.Through the asymmetric aggregation of feature maps,one-dimensional CNN(1D-CNN)and two-dimensional CNN(2D-CNN)were connected to maintain network depth,limit model parameters,and reduce computation.The parameters sharing of multidimensional convolution kernels was used to capture the deep coupling features of different dimensions and different landslide factors,so as to make full use of features and avoid overfitting.Taking Sedongpu gully in Xizang,China as the experimental area,this paper selected 11 kinds of landslide influencing factors to analyze the landslide susceptibility.Results:The results show that the multi-dimensional CNN coupling structure had the same training efficiency as the shallow 2D-CNN with fewer parameters due to the reduced computational effort.While compared with the deep 2D-CNN with the approximate number of parameters,the training time of the proposed method was significantly reduced and the training cost was lower.In addition,the coupled model had a stronger feature learning ability than the independent 1D-CNN and 2D-CNN,and therefore obtained higher model accuracy.Under each confusion matrix metric of the testing data,the coupled model received higher scores,and thus obtained more reliable landslide susceptibility assessment results.Conclusions:The multidimensional CNN coupling model proposed in this paper

关 键 词：1D-CNN 2D-CNN 滑坡易发性评价 耦合模型 

分 类 号：P237[天文地球—摄影测量与遥感] P694[天文地球—测绘科学与技术]