Deep-pretrained-FWI: combining supervised learning with physics-informed neural network

Abstract

An accurate velocity model is essential to make a good seismic image. Conventional methods to perform Velocity Model Building (VMB) tasks rely on inverse methods, which, despite being widely used, are ill-posed problems that require intense and specialized human supervision. Convolutional Neural Networks (CNN) have been extensively investigated as an alternative to solve the VMB task. Two main approaches were investigated in the literature: supervised training and Physics-Informed Neural Networks (PINN). Supervised training presents some generalization issues since structures, and velocity ranges must be similar in training and test set. Some works integrated Full-waveform Inversion (FWI) with CNN, defining the problem of VMB in the PINN framework. In this case, the CNN stabilizes the inversion, acting like a regularizer and avoiding local minima-related problems and, in some cases, sparing an initial velocity model. Our approach combines supervised and physics-informed neural networks by using transfer learning to start the inversion. The pre-trained CNN is obtained using a supervised approach based on training with a reduced and simple data set to capture the main velocity trend at the initial FWI iterations. We show that transfer learning reduces the uncertainties of the process, accelerates model convergence, and improves the final scores of the iterative process.

Paper present at machine Learning and the Physical Sciences workshop, NeurIPS 2022

References in corpus (8)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Physics-informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions
• PINNup: Robust neural network wavefield solutions using frequency upscaling and neuron splitting
• 3D Bayesian Variational Full Waveform Inversion
• Transfer learning: Improving neural network based prediction of earthquake ground shaking for an area with insufficient training data
• Predicting Fault Slip via Transfer Learning
• Deep-tomography: iterative velocity model building with deep learning
• Complete identification of complex salt geometries from inaccurate migrated subsurface offset gathers using deep learning

Cited by in corpus (1)

• Neural Networks for Generating Better Local Optima in Topology Optimization