Hausdorff-distance-based training dataset construction for numerical dispersion mitigation neural network Full article
| Journal |
Computers and Geosciences
ISSN: 0098-3004 |
||||
|---|---|---|---|---|---|
| Output data | Year: 2023, Volume: 180, Article number : 105438, Pages count : 9 DOI: 10.1016/j.cageo.2023.105438 | ||||
| Tags | Seismic modeling, Numerical dispersion, Deep learning, Hausdorff distance | ||||
| Authors |
|
||||
| Affiliations |
|
Funding (2)
| 1 | Russian Science Foundation | 22-11-00004 |
| 2 |
Министерство науки и высшего образования РФ Mathematical Center in Akademgorodok |
075-15-2019-1613, 075-15-2022-281 |
Abstract:
We present a novel approach for constructing the training dataset for the Numerical Dispersion Mitigation neural network (NDM-net). The NDM-net is a multi-step approach to reduce numerical error in seismic modeling. First, a coarse grid is used to simulate the entire dataset with lower accuracy quickly. A fine grid is then used to simulate selected cases with higher accuracy. Next, the high-accuracy solutions are used together with corresponding low-accuracy solutions as a training dataset for the neural network. Finally, the neural network is used to improve the accuracy of the entire dataset of low-accuracy solutions. Running highaccuracy simulations for the training dataset is the most time-consuming step of the NDM-net approach. Thus, reducing the training dataset may significantly improve the NDM-net performance. In this study, we propose a training dataset construction method that maintains the Hausdorff distance between the training dataset and the complete dataset, allowing the training dataset to be generated from as few as 3%–5% of the total number of sources.
Cite:
Gadylshin K.
, Lisitsa V.
, Vishnevsky D.
, Gadylshina K.
Hausdorff-distance-based training dataset construction for numerical dispersion mitigation neural network
Computers and Geosciences. 2023. V.180. 105438 :1-9. DOI: 10.1016/j.cageo.2023.105438 WOS Scopus РИНЦ OpenAlex
Hausdorff-distance-based training dataset construction for numerical dispersion mitigation neural network
Computers and Geosciences. 2023. V.180. 105438 :1-9. DOI: 10.1016/j.cageo.2023.105438 WOS Scopus РИНЦ OpenAlex
Dates:
| Submitted: | Aug 18, 2022 |
| Accepted: | Aug 19, 2023 |
| Published print: | Aug 24, 2023 |
| Published online: | Aug 24, 2023 |
Identifiers:
| Web of science: | WOS:001070880200001 |
| Scopus: | 2-s2.0-85171525355 |
| Elibrary: | 63244826 |
| OpenAlex: | W4386122715 |