Deep-Learning Inversion of Seismic Data

Abstract

We propose a new method to tackle the mapping challenge from time-series data to spatial image in the field of seismic exploration, i.e., reconstructing the velocity model directly from seismic data by deep neural networks (DNNs). The conventional way of addressing this ill-posed inversion problem is through iterative algorithms, which suffer from poor nonlinear mapping and strong nonuniqueness. Other attempts may either import human intervention errors or underuse seismic data. The challenge for DNNs mainly lies in the weak spatial correspondence, the uncertain reflection-reception relationship between seismic data and velocity model, as well as the time-varying property of seismic data. To tackle these challenges, we propose end-to-end seismic inversion networks (SeisInvNets) with novel components to make the best use of all seismic data. Specifically, we start with every seismic trace and enhance it with its neighborhood information, its observation setup, and the global context of its corresponding seismic profile. From the enhanced seismic traces, the spatially aligned feature maps can be learned and further concatenated to reconstruct a velocity model. In general, we let every seismic trace contribute to the reconstruction of the whole velocity model by finding spatial correspondence. The proposed SeisInvNet consistently produces improvements over the baselines and achieves promising performance on our synthesized and proposed SeisInv data set according to various evaluation metrics. The inversion results are more consistent with the target from the aspects of velocity values, subsurface structures, and geological interfaces. Moreover, the mechanism and the generalization of the proposed method are discussed and verified. Nevertheless, the generalization of deep-learning-based inversion methods on real data is still challenging and considering physics may be one potential solution.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• WaveNet: A Generative Model for Raw Audio
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Loss Functions for Neural Networks for Image Processing
• Video-to-Video Synthesis
• DifNet: Semantic Segmentation by Diffusion Networks

Cited by in corpus (29)

• Solving the acoustic VTI wave equation using physics-informed neural networks
• Deep Learning Inversion of Electrical Resistivity Data
• GPRInvNet: Deep Learning-Based Ground Penetrating Radar Data Inversion for Tunnel Lining
• Extrapolated full waveform inversion with deep learning
• Deep Learning in Deterministic Computational Mechanics
• Wavefield reconstruction inversion via physics-informed neural networks
• Deep-Learning based Inverse Modeling Approaches: A Subsurface Flow Example
• A prior regularized full waveform inversion using generative diffusion models
• Hybrid and Automated Machine Learning Approaches for Oil Fields Development: the Case Study of Volve Field, North Sea
• Using Convolutional Neural Networks to Develop Starting Models for 2D Full Waveform Inversion
• On the Use of Neural Networks for Full Waveform Inversion
• InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion
• Quantitative reconstruction of defects in multi-layered bonded composites using fully convolutional network-based ultrasonic inversion
• S2S-WTV: Seismic Data Noise Attenuation Using Weighted Total Variation Regularized Self-Supervised Learning
• Deep-pretrained-FWI: combining supervised learning with physics-informed neural network
• Physics-driven Deep Learning Inversion for Direct Current Resistivity Survey Data
• Deep-tomography: iterative velocity model building with deep learning
• Electrical and seismic refraction methods: fundamental concepts, current trends, and emerging machine learning prospects -- A review
• Inversion of Time-Lapse Surface Gravity Data for Detection of 3D CO${}_2$ Plumes via Deep Learning
• Quantum algorithm for partial differential equations of non-conservative systems with spatially varying parameters
• Integrating Deep Neural Networks with Full-waveform Inversion: Reparametrization, Regularization, and Uncertainty Quantification
• Complete identification of complex salt geometries from inaccurate migrated subsurface offset gathers using deep learning
• Transfer Learning Enhanced Full Waveform Inversion
• Automatic Velocity Picking Using a Multi-Information Fusion Deep Semantic Segmentation Network
• DispFormer: A Pretrained Transformer Incorporating Physical Constraints for Dispersion Curve Inversion
• On the Robustness and Generalization of Deep Learning Driven Full Waveform Inversion
• SVInvNet: A Densely Connected Encoder-Decoder Architecture for Seismic Velocity Inversion
• Across-domains transferability of Deep-RED in de-noising and compressive sensing recovery of seismic data
• Intelligent Decision Method for Main Control Parameters of Tunnel Boring Machine based on Multi-Objective Optimization of Excavation Efficiency and Cost