# PreAdaptFWI: Pretrained-Based Adaptive Residual Learning for Full-Waveform Inversion Without Dataset Dependency

arXiv: https://arxiv.org/abs/2502.11913 · HTML: https://mlsanity.com/paper/2502.11913/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 71 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep-learning inversion: a next generation seismic velocity-model building method](https://mlsanity.com/paper/1902.06267/) (2019)
- [Data-driven Seismic Waveform Inversion: A Study on the Robustness and Generalization](https://mlsanity.com/paper/1809.10262/) (2018)
- [Seismic Signal Denoising and Decomposition Using Deep Neural Networks](https://mlsanity.com/paper/1811.02695/) (2018)
- [PINNup: Robust neural network wavefield solutions using frequency upscaling and neuron splitting](https://mlsanity.com/paper/2109.14536/) (2021)
- [Can learning from natural image denoising be used for seismic data interpolation?](https://mlsanity.com/paper/1902.10379/) (2019)
- [SG-DeepONet: Source-generalized deep operator learning for full waveform inversion](https://mlsanity.com/paper/2408.08005/) (2024)

## Built on by (most cited first, 1 of 1)

- [The Neuro-Physical Inverter: A Modular Framework for Magnetotelluric Inversion Coupling Ensemble Conditioning with Residual Learning](https://mlsanity.com/paper/2610.03225/) (2026)

## Abstract (arXiv)

Full-waveform inversion (FWI) is a method that utilizes seismic data to invert the physical parameters of subsurface media by minimizing the difference between simulated and observed waveforms. Due to its ill-posed nature, FWI is susceptible to getting trapped in local minima. Consequently, various research efforts have attempted to combine neural networks with FWI to stabilize the inversion process. This study presents a simple yet effective training framework that is independent of dataset reliance and requires only moderate pre-training on a simple initial model to stabilize network outputs. During the transfer learning phase, the conventional FWI gradients will simultaneously update both the neural network and the proposed adaptive residual learning module, which learns the residual mapping of large-scale distribution features in the network's output, rather than directly fitting the target mapping. Through this synergistic training paradigm, the proposed algorithm effectively infers the physically-informed prior knowledge into a global representation of stratigraphic distribution, as well as capturing subtle variations in inter-layer velocities within local details, thereby escaping local optima. Evaluating the method on two benchmark models under various conditions, including absent low-frequency data, noise interference, and differing initial models, along with corresponding ablation experiments, consistently demonstrates the superiority of the proposed approach.