Xinquan Huang, and Tariq Alkhalifah

 GitHub: https://github.com/DeepWave-KAUST/neuroseismic

Full waveform inversion (FWI) is crucial for reconstructing high-resolution subsurface models, but it is often hindered, considering the limited data, by its null space, resulting in low resolution models, and more importantly by its computational cost, especially for real-time applications. Neural operator based full waveform inversion can enhance the computational efficiency but results in noisy inverted results. We introduce a novel physics-informed FWI framework based on neural operator to enhance the inversion both in efficiency and accuracy.