Pertinent Multigate Mixture-of-Experts-Based Prestack Three-Parameter Seismic Inversion
- 21 September 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-15
Abstract
Seismic inversion is a method used to identify the spatial structure and obtain the physical properties of underground strata by processing seismic data. As a data-driven approach, deep learning (DL) is widely used in prestack three-parameter inversion to solve its nonlinearity and ill-posed problems. However, traditional DL-based methods involve the construction of a separate network for each task and thus ignore the correlations between different tasks. Multitask learning (MTL) aims to promote the effectiveness of each task with implicit information amplification by training multiple tasks simultaneously. However, information sharing in conventional MTL may cause negative effects on parallel tasks. To solve this problem, a novel MTL method, called pertinent multigate mixture-of-experts (PMMOE), was proposed for prestack three-parameter inversion. PMMOE introduces the mixture-of-experts (MOE) structure for MTL and creatively divides experts into three special experts and a shared expert. In PMMOE, the input data of different experts are discrepant, enabling the retrieval of different features for different tasks. Experiments revealed that our proposed method has higher accuracy than other methods, and the inversion results of synthetic data and field data further demonstrate the effectiveness of our proposed method.Keywords
Funding Information
- National Key Research and Development Program of China (2019YFC0312003)
- National Natural Science Foundation of China (41774129, 41774131)
This publication has 51 references indexed in Scilit:
- Stochastic inversion of magnetotelluric data using a sharp boundary parameterization and application to a geothermal siteGeophysics, 2012
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Enforcing smoothness and assessing uncertainty in non‐linear one‐dimensional prestack seismic inversionGeophysical Prospecting, 2006
- Linearized amplitude variation with offset (AVO) inversion with supercritical anglesGeophysics, 2006
- Bayesian linearized AVO inversionGeophysics, 2003
- Constrained restoration and the recovery of discontinuitiesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991
- Plane-wave reflection coefficients for gas sands at nonnormal angles of incidenceGeophysics, 1984
- Optimization by Simulated AnnealingScience, 1983
- The Coefficient of Determination-Some LimitationsThe American Statistician, 1974