Published on Mon Nov 25 2019

Solving Traveltime Tomography with Deep Learning

Yuwei Fan, Lexing Ying

This paper introduces a neural network approach for solving two-dimensional traveltime tomography problems based on the eikonal equation. We propose an effective neural network architecture for the inverse map using the recently proposed BCR-Net.

0
0
0
Abstract

This paper introduces a neural network approach for solving two-dimensional traveltime tomography (TT) problems based on the eikonal equation. The mathematical problem of TT is to recover the slowness field of a medium based on the boundary measurement of the traveltimes of waves going through the medium. This inverse map is high-dimensional and nonlinear. For the circular tomography geometry, a perturbative analysis shows that the forward map can be approximated by a vectorized convolution operator in the angular direction. Motivated by this and filtered back-projection, we propose an effective neural network architecture for the inverse map using the recently proposed BCR-Net, with weights learned from training datasets. Numerical results demonstrate the efficiency of the proposed neural networks.

Thu Oct 10 2019
Machine Learning
Solving Optical Tomography with Deep Learning
This paper presents a neural network approach for solving two-dimensional optical tomography problems. The problem of OT is to recover the optical properties of an object based on the albedo operator.
0
0
0
Thu Jun 06 2019
Machine Learning
Solving Electrical Impedance Tomography with Deep Learning
This paper introduces a new approach for solving electrical impedance tomography (EIT) problems using deep neural networks. The mathematical problem of EIT is to invert the electrical conductivity from the Dirichlet-to-Neumann(DtN) map.
0
0
0
Wed Mar 25 2020
Machine Learning
EikoNet: Solving the Eikonal equation with Deep Neural Networks
EikoNet is a deep learning approach to solving the Eikonal equation. The method exploits the differentiability of neural networks to calculate spatial gradients analytically. The approach has important applications to earthquake hypocenterversion, ray multi-pathing, and tomographic modeling.
0
0
0
Thu Feb 04 2021
Machine Learning
Incorporating Kinematic Wave Theory into a Deep Learning Method for High-Resolution Traffic Speed Estimation
We propose a kinematic wave based Deep Convolutional Neural Network to estimate high resolution traffic speed dynamics from sparse probe vehicle trajectories. We use an anisotropic roadway-based kernel for the CNN. This kernel is designed to explicitly take forward and backward traffic wave propagation characteristics into account during reconstruction in the space-time
0
0
0
Wed Jun 10 2020
Machine Learning
Learning the geometry of wave-based imaging
A key difficulty in imaging problems with a varying background wave speed is that the medium "bends" the waves differently. We build an interpretable neural architecture inspired by Fourier integral operators.
0
0
0
Sat Dec 16 2017
Machine Learning
Travel time tomography with adaptive dictionaries
We develop a 2D travel time tomography method which regularizes the inversion by modeling groups of slowness pixels. We propose to use dictionary learning during the inversions to adapt dictionaries to Specific Slowness maps.
0
0
0