Exploring Multi-physics with Extremely Weak Supervision

• URL: http://arxiv.org/abs/2202.01770v1
• Date: Thu, 3 Feb 2022 18:55:09 GMT
• Title: Exploring Multi-physics with Extremely Weak Supervision
• Authors: Shihang Feng, Peng Jin, Yinpeng Chen, Xitong Zhang, Zicheng Liu, Youzuo Lin
• Abstract summary: We develop a new data-driven multi-physics inversion technique with extremely weak supervision. Our key finding is that the pseudo labels can be constructed by learning the local relationship among geophysical properties at very sparse locations. Our results show that we are able to invert for properties without explicit governing equations.
• Score: 23.421788453790302
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-physical inversion plays a critical role in geophysics. It has been widely used to infer various physical properties (such as velocity and conductivity), simultaneously. Among those inversion problems, some are explicitly governed by partial differential equations (PDEs), while others are not. Without explicit governing equations, conventional multi-physical inversion techniques will not be feasible and data-driven inversion require expensive full labels. To overcome this issue, we develop a new data-driven multi-physics inversion technique with extremely weak supervision. Our key finding is that the pseudo labels can be constructed by learning the local relationship among geophysical properties at very sparse locations. We explore a multi-physics inversion problem from two distinct measurements (seismic and EM data) to three geophysical properties (velocity, conductivity, and CO$_2$ saturation). Our results show that we are able to invert for properties without explicit governing equations. Moreover, the label data on three geophysical properties can be significantly reduced by 50 times (from 100 down to only 2 locations).

Related papers

• On a Hidden Property in Computational Imaging [22.665280793360274]
  We show that three inverse problems (FWI, CT, and EM inversion) share a hidden property within their latent spaces. This suggests that after projection into the latent embedding space, the two modalities correspond to different solutions of the same equation.
  arXiv  Detail & Related papers  (2024-10-11T03:52:04Z)
• Visualizing Dynamics of Charges and Strings in (2+1)D Lattice Gauge Theories [103.95523007319937]
  We study the dynamics of local excitations in a lattice of superconducting qubits. For confined excitations, the magnetic field induces a tension in the string connecting them. Our method allows us to experimentally image string dynamics in a (2+1)D LGT.
  arXiv  Detail & Related papers  (2024-09-25T17:59:05Z)
• Transolver: A Fast Transformer Solver for PDEs on General Geometries [66.82060415622871]
  We present Transolver, which learns intrinsic physical states hidden behind discretized geometries. By calculating attention to physics-aware tokens encoded from slices, Transovler can effectively capture intricate physical correlations. Transolver achieves consistent state-of-the-art with 22% relative gain across six standard benchmarks and also excels in large-scale industrial simulations.
  arXiv  Detail & Related papers  (2024-02-04T06:37:38Z)
• SeMAnD: Self-Supervised Anomaly Detection in Multimodal Geospatial Datasets [0.0]
  SeMAnD is able to detect real-world defects and outperforms domain-agnostic anomaly detection strategies by 4.8-19.7%. We show that model performance increases (i) up to 20.4% as the number of input modalities increase and (ii) up to 22.9% as the diversity and strength of training data augmentations increase.
  arXiv  Detail & Related papers  (2023-09-26T20:18:31Z)
• SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases [66.61789780666727]
  We show how the second-order continuity can be incorporated into GNNs while maintaining the equivariant property. We also offer theoretical insights into SEGNO, highlighting that it can learn a unique trajectory between adjacent states. Our model yields a significant improvement over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-08-25T07:15:58Z)
• $\mathbf{\mathbb{E}^{FWI}}$: Multi-parameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties [27.94139165494327]
  $mathbfmathbbEFWI$ is a comprehensive benchmark dataset for elastic full waveform inversion. $mathbfmathbbEFWI$ encompasses 8 distinct datasets that cover diverse subsurface geologic structures. The relation between P- and S-wave velocities provides crucial insights into the subsurface properties.
  arXiv  Detail & Related papers  (2023-06-21T17:11:35Z)
• Learning Physical Dynamics with Subequivariant Graph Neural Networks [99.41677381754678]
  Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics. Physical laws abide by symmetry, which is a vital inductive bias accounting for model generalization. Our model achieves on average over 3% enhancement in contact prediction accuracy across 8 scenarios on Physion and 2X lower rollout MSE on RigidFall.
  arXiv  Detail & Related papers  (2022-10-13T10:00:30Z)
• Curvature-informed multi-task learning for graph networks [56.155331323304]
  State-of-the-art graph neural networks attempt to predict multiple properties simultaneously. We investigate a potential explanation for this phenomenon: the curvature of each property's loss surface significantly varies, leading to inefficient learning.
  arXiv  Detail & Related papers  (2022-08-02T18:18:41Z)
• An Intriguing Property of Geophysics Inversion [21.43509030627468]
  Inversion techniques are widely used to reconstruct subsurface physical properties. The problems are governed by partial differential equations(PDEs) like the wave or Maxwell's equations. Recent studies leverage deep neural networks to learn the inversion mappings from geophysical measurements to the geophysical property directly.
  arXiv  Detail & Related papers  (2022-04-28T18:25:36Z)
• Averaging Spatio-temporal Signals using Optimal Transport and Soft Alignments [110.79706180350507]
  We show that our proposed loss can be used to define temporal-temporal baryechecenters as Fr'teche means duality. Experiments on handwritten letters and brain imaging data confirm our theoretical findings.
  arXiv  Detail & Related papers  (2022-03-11T09:46:22Z)
• Experimental characterization of quantum many-body localization transition [13.805666393282454]
  We experimentally implement a scalable protocol for detecting the many-body localization transition point. By exploiting three quantities, each with different spatial resolution, we identify the transition point with excellent match between simulation and experiment. The protocol is easily scalable and can be performed across various physical platforms.
  arXiv  Detail & Related papers  (2020-12-21T17:35:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.