Learned multiphysics inversion with differentiable programming and machine learning
Learned multiphysics inversion with differentiable programming and machine learning
复制标题
DOI：
10.1190/tle42070474.1
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
M. Louboutin;Ziyi Yin;Rafael Orozco;Thomas J. Grady;Ali Siahkoohi;G. Rizzuti;Philipp A. Witte;O. Møyner;G. Gorman;F. Herrmann
中科院分区：
文献类型：
--
作者：
M. Louboutin;Ziyi Yin;Rafael Orozco;Thomas J. Grady;Ali Siahkoohi;G. Rizzuti;Philipp A. Witte;O. Møyner;G. Gorman;F. Herrmann
我们提出了用于计算地球物理的成像和建模/监测地震实验室开源软件框架，更一般地说，涉及涉及波动方程（例如地震和医学超声）的反演问题、利用学习先验进行正则化以及用于多相流模拟的学习神经代理。通过集成多个抽象层，该软件被设计为可读且可扩展，使研究人员能够轻松地以抽象方式表述问题，同时利用高性能计算的最新发展。通过构建一个可扩展的原型来说明和演示设计原理及其优点，该原型用于根据时移井间地震数据进行渗透率反演，除了波物理和多相流的耦合之外，还涉及机器学习。
We present the Seismic Laboratory for Imaging and Modeling/Monitoring open-source software framework for computational geophysics and, more generally, inverse problems involving the wave equation (e.g., seismic and medical ultrasound), regularization with learned priors, and learned neural surrogates for multiphase flow simulations. By integrating multiple layers of abstraction, the software is designed to be both readable and scalable, allowing researchers to easily formulate problems in an abstract fashion while exploiting the latest developments in high-performance computing. The design principles and their benefits are illustrated and demonstrated by means of building a scalable prototype for permeability inversion from time-lapse crosswell seismic data, which, aside from coupling of wave physics and multiphase flow, involves machine learning.