Summary of Inversion-deeponet: a Novel Deeponet-based Network with Encoder-decoder For Full Waveform Inversion, by Zekai Guo et al.
Inversion-DeepONet: A Novel DeepONet-Based Network with Encoder-Decoder for Full Waveform Inversion
by Zekai Guo, Lihui Chai, Shengjun Huang, Ye Li
First submitted to arxiv on: 15 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers explore ways to improve full waveform inversion (FWI) in geophysics by applying deep learning (DL) methods. One key challenge is the quality and diversity of datasets used for training DL models. Existing datasets, like OpenFWI, have limitations that don’t accurately represent real-world scenarios. The authors propose a new approach using multiple sources with varying frequencies to provide more information about subsurface structures. They develop three enhanced datasets based on OpenFWI and introduce a novel deep operator network (DeepONet) architecture for FWI. DeepONet combines convolutional neural networks (CNNs) and branch net to extract features from seismic data, source parameters, and reconstruct velocity models. Experimental results demonstrate the superior performance of the proposed method compared to existing data-driven FWI methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making geophysics better using computers. Geophysicists use something called full waveform inversion (FWI) to figure out what’s under the ground. They want to make it work better, so they’re trying deep learning (DL). The problem is that the data they use now isn’t very good and doesn’t show what really happens in the real world. So, they’re making new datasets with different kinds of information. Then, they created a special computer program called DeepONet to help make FWI better. They tested it and found out that it works way better than other methods. |
Keywords
» Artificial intelligence » Deep learning
