Including Physics in Deep Learning -- An example from 4D seismic pressure saturation inversion
arXiv:1904.02254 · doi:10.3997/2214-4609.201901967
Abstract
Geoscience data often have to rely on strong priors in the face of uncertainty. Additionally, we often try to detect or model anomalous sparse data that can appear as an outlier in machine learning models. These are classic examples of imbalanced learning. Approaching these problems can benefit from including prior information from physics models or transforming data to a beneficial domain. We show an example of including physical information in the architecture of a neural network as prior information. We go on to present noise injection at training time to successfully transfer the network from synthetic data to field data.
arXiv comment5 pages, 5 figures, workshop, extended abstract, EAGE 2019 Workshop Programme, European Association of Geoscientists and Engineers
References in corpus (5)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Auto-Encoding Variational Bayes
- Quantum-Chemical Insights from Deep Tensor Neural Networks
- Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling
- A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks