Surface wave inversion with unknown number of soil layers based on a hybrid learning procedure of deep learning and genetic algorithm
作者机构:Department of Civil and Environmental EngineeringFaculty of Science and TechnologyUniversity of MacaoMacaoChina
出 版 物:《Earthquake Engineering and Engineering Vibration》 (地震工程与工程振动(英文刊))
年 卷 期:2024年第23卷第2期
页 面:345-358页
核心收录:
学科分类:081801[工学-矿产普查与勘探] 081802[工学-地球探测与信息技术] 08[工学] 0818[工学-地质资源与地质工程] 0814[工学-土木工程]
基 金:provided through research grant No.0035/2019/A1 from the Science and Technology Development Fund,Macao SAR the assistantship from the Faculty of Science and Technology,University of Macao
主 题:surface wave inversion analysis shear-wave velocity profile deep neural network genetic algorithm
摘 要:Surface wave inversion is a key step in the application of surface waves to soil velocity ***,a common practice for the process of inversion is that the number of soil layers is assumed to be known before using heuristic search algorithms to compute the shear wave velocity profile or the number of soil layers is considered as an optimization ***,an improper selection of the number of layers may lead to an incorrect shear wave velocity *** this study,a deep learning and genetic algorithm hybrid learning procedure is proposed to perform the surface wave inversion without the need to assume the number of soil ***,a deep neural network is adapted to learn from a large number of synthetic dispersion curves for inferring the layer ***,the shear-wave velocity profile is determined by a genetic algorithm with the known layer *** applying this procedure to both simulated and real-world cases,the results indicate that the proposed method is reliable and efficient for surface wave inversion.