LGGEO-PHMLMar 21, 2025

Towards Understanding the Benefits of Neural Network Parameterizations in Geophysical Inversions: A Study With Neural Fields

arXiv:2503.17503v24 citationsh-index: 14IEEE Trans Geosci Remote Sens
Originality Incremental advance
AI Analysis

This work addresses artifacts in subsurface models for geophysical applications, but it is incremental as it builds on existing neural field methods and focuses on specific synthetic cases.

The study tackled the problem of artifacts in geophysical inversion models by using neural fields in a test-time learning approach, showing that it can eliminate unwanted artifacts and improve results such as dip angle recovery and boundary prediction in synthetic seismic tomography and direct current resistivity examples.

In this work, we employ neural fields, which use neural networks to map a coordinate to the corresponding physical property value at that coordinate, in a test-time learning manner. For a test-time learning method, the weights are learned during the inversion, as compared to traditional approaches which require a network to be trained using a training dataset. Results for synthetic examples in seismic tomography and direct current resistivity inversions are shown first. We then perform a singular value decomposition analysis on the Jacobian of the weights of the neural network (SVD analysis) for both cases to explore the effects of neural networks on the recovered model. The results show that the test-time learning approach can eliminate unwanted artifacts in the recovered subsurface physical property model caused by the sensitivity of the survey and physics. Therefore, NFs-Inv improves the inversion results compared to the conventional inversion in some cases such as the recovery of the dip angle or the prediction of the boundaries of the main target. In the SVD analysis, we observe similar patterns in the left-singular vectors as were observed in some diffusion models, trained in a supervised manner, for generative tasks in computer vision. This observation provides evidence that there is an implicit bias, which is inherent in neural network structures, that is useful in supervised learning and test-time learning models. This implicit bias has the potential to be useful for recovering models in geophysical inversions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes