基于密集残差物理信息神经网络的各向异性旅行时计算方法  

Anisotropic travel time computation method based on dense residual connection physical information neural networks

作　　者：赵亦群 张志禹[1] 董雪 ZHAO Yiqun;ZHANG Zhiyu;DONG Xue(College of Automation and Information Engineering,Xi’an University of Technology,Xi’an Shaanxi 710048,China)

机构地区：[1]西安理工大学自动化与信息工程学院,西安710048

出　　处：《计算机应用》2024年第7期2310-2318,共9页journal of Computer Applications

基　　金：国家自然科学基金资助项目(U21A20485)。

摘　　要：针对目前利用物理信息神经网络计算旅行时只是应用在各向同性介质上、在远离震源时误差较大和效率低等问题,而有限差分法、试射法和弯曲法等方法在多震源、高密度网格上计算成本高等问题,提出一种密集残差物理信息神经网络计算各向异性介质旅行时的方法。首先推导了各向异性因式分解后的程函方程作为损失函数项;其次引入局部自适应反正切函数为激活函数和L-BFGS-B(Limited-memory Broyden-Fletcher-Goldfarb-Shanno-B)作为优化器;最后在网络中采用分段式训练的方式,先训练深层密集残差网络,然后冻结其参数,再训练具有物理意义的浅层密集残差网络,从而评估网络得到旅行时。实验结果表明,所提方法在均匀速度模型下的旅行时最大绝对误差达到了0.0158μs,其他速度模型下平均绝对误差平均下降了两个数量级,在效率方面也平均提高了1倍,明显优于快速扫描法。In order to solve problems that the travel time calculation by Physical Information Neural Network(PINN)is only applied to isotropic media at present,the error is large and the efficiency is low when far away from the seismic source,and finite difference method,shooting method and bending method have high computational cost on multiple seismic sources and high-density grids,a method of calculating the travel time using Dense Residual Connection PINN(DRC-PINN)in anisotropic media was proposed.Firstly,the eikonal equation after anisotropic factorization was derived as the loss function term.Secondly,the local adaptive arctangent function was selected as the activation function and Limited-memory Broyden-Fletcher-Goldfarb-Shanno-B(L-BFGS-B)was used as the optimizer.Finally,the network was trained in a segmented manner,the deep dense residual network was trained first,their parameters were frozen,and then the shallow dense residual network with physical meaning was trained,so that the network was evaluated and the travel time was obtained.The experimental results show that the maximum absolute error of the proposed method is 0.0158μs in the uniform velocity model,and the average absolute errors in other velocity models are reduced by two orders of magnitude,and the efficiency is doubled compared with that of the original model.The proposed method is obviously better than fast sweeping method.

关 键 词：深度学习 物理信息神经网络 各向异性 旅行时 程函方程 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] P631.4[自动化与计算机技术—控制科学与工程]