# Deep-learning inversion: a next generation seismic velocity-model building method

arXiv: https://arxiv.org/abs/1902.06267 · HTML: https://mlsanity.com/paper/1902.06267/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2019.

## Built on by (most cited first, 30 of 50)

- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [OpenFWI: Large-Scale Multi-Structural Benchmark Datasets for Seismic Full Waveform Inversion](https://mlsanity.com/paper/2111.02926/) (2021)
- [Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop](https://mlsanity.com/paper/2110.07584/) (2021)
- [Implicit Full Waveform Inversion with Deep Neural Representation](https://mlsanity.com/paper/2209.03525/) (2022)
- [Deep Learning in Deterministic Computational Mechanics](https://mlsanity.com/paper/2309.15421/) (2023)
- [InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion](https://mlsanity.com/paper/2103.14158/) (2021)
- [Controllable seismic velocity synthesis using generative diffusion models](https://mlsanity.com/paper/2402.06277/) (2024)
- [An Empirical Study of Large-Scale Data-Driven Full Waveform Inversion](https://mlsanity.com/paper/2307.15388/) (2023)
- [An Intriguing Property of Geophysics Inversion](https://mlsanity.com/paper/2204.13731/) (2022)
- [Evaluating the transferability potential of deep learning models for climate downscaling](https://mlsanity.com/paper/2407.12517/) (2024)
- [Encoder-Decoder Architecture for 3D Seismic Inversion](https://mlsanity.com/paper/2207.14789/) (2022)
- [Physics-informed waveform inversion using pretrained wavefield neural operators](https://mlsanity.com/paper/2509.08967/) (2025)
- [Transfer Learning Enhanced Full Waveform Inversion](https://mlsanity.com/paper/2302.11259/) (2023)
- [Cross-Domain Foundation Model Adaptation: Pioneering Computer Vision Models for Geophysical Data Analysis](https://mlsanity.com/paper/2408.12396/) (2024)
- [Inversion of Time-Lapse Surface Gravity Data for Detection of 3D CO2 Plumes via Deep Learning](https://mlsanity.com/paper/2209.02850/) (2022)
- [Revisit Geophysical Imaging in A New View of Physics-informed Generative Adversarial Learning](https://mlsanity.com/paper/2109.11452/) (2021)
- [A Frequency-Velocity CNN for Developing Near-Surface 2D Vs Images from Linear-Array, Active-Source Wavefield Measurements](https://mlsanity.com/paper/2207.09580/) (2022)
- [Using explainability to design physics-aware CNNs for solving subsurface inverse problems](https://mlsanity.com/paper/2211.08651/) (2022)
- [Edge-InversionNet: Enabling Efficient Inference of InversionNet on Edge Devices](https://mlsanity.com/paper/2310.09667/) (2023)
- [Deep Compressed Learning for 3D Seismic Inversion](https://mlsanity.com/paper/2311.00107/) (2023)
- [An Unsupervised Deep Learning Approach for the Wave Equation Inverse Problem](https://mlsanity.com/paper/2311.04531/) (2023)
- [Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion](https://mlsanity.com/paper/2102.13631/) (2021)
- [DuRIN: A Deep-unfolded Sparse Seismic Reflectivity Inversion Network](https://mlsanity.com/paper/2104.04704/) (2021)
- [Joint inversion of Time-Lapse Surface Gravity and Seismic Data for Monitoring of 3D CO2 Plumes via Deep Learning](https://mlsanity.com/paper/2310.04430/) (2023)
- [Integrating Physics of the Problem into Data-Driven Methods to Enhance Elastic Full-Waveform Inversion with Uncertainty Quantification](https://mlsanity.com/paper/2406.05153/) (2024)
- [DispFormer: A Pretrained Transformer Incorporating Physical Constraints for Dispersion Curve Inversion](https://mlsanity.com/paper/2501.04366/) (2025)
- [PreAdaptFWI: Pretrained-Based Adaptive Residual Learning for Full-Waveform Inversion Without Dataset Dependency](https://mlsanity.com/paper/2502.11913/) (2025)
- [Bayesian full waveform inversion with sequential surrogate model refinement](https://mlsanity.com/paper/2505.03246/) (2025)
- [NuSPAN: A Proximal Average Network for Nonuniform Sparse Model -- Application to Seismic Reflectivity Inversion](https://mlsanity.com/paper/2105.00003/) (2021)
- [Learning velocity model for complex media with deep convolutional neural networks](https://mlsanity.com/paper/2110.08626/) (2021)

## Abstract (arXiv)

Seismic velocity is one of the most important parameters used in seismic exploration. Accurate velocity models are key prerequisites for reverse-time migration and other high-resolution seismic imaging techniques. Such velocity information has traditionally been derived by tomography or full-waveform inversion (FWI), which are time consuming and computationally expensive, and they rely heavily on human interaction and quality control. We investigate a novel method based on the supervised deep fully convolutional neural network (FCN) for velocity-model building (VMB) directly from raw seismograms. Unlike the conventional inversion method based on physical models, the supervised deep-learning methods are based on big-data training rather than prior-knowledge assumptions. During the training stage, the network establishes a nonlinear projection from the multi-shot seismic data to the corresponding velocity models. During the prediction stage, the trained network can be used to estimate the velocity models from the new input seismic data. One key characteristic of the deep-learning method is that it can automatically extract multi-layer useful features without the need for human-curated activities and initial velocity setup. The data-driven method usually requires more time during the training stage, and actual predictions take less time, with only seconds needed. Therefore, the computational time of geophysical inversions, including real-time inversions, can be dramatically reduced once a good generalized network is built. By using numerical experiments on synthetic models, the promising performances of our proposed method are shown in comparison with conventional FWI even when the input data are in more realistic scenarios. Discussions on the deep-learning methods, training dataset, lack of low frequencies, and advantages and disadvantages of the new method are also provided.