Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Physics-guided Generative AI Toolkit for Geophysical Monitoring (2401.03131v1)

Published 6 Jan 2024 in cs.LG, cs.AI, cs.CV, eess.SP, and physics.geo-ph

Abstract: Full-waveform inversion (FWI) plays a vital role in geoscience to explore the subsurface. It utilizes the seismic wave to image the subsurface velocity map. As the ML technique evolves, the data-driven approaches using ML for FWI tasks have emerged, offering enhanced accuracy and reduced computational cost compared to traditional physics-based methods. However, a common challenge in geoscience, the unprivileged data, severely limits ML effectiveness. The issue becomes even worse during model pruning, a step essential in geoscience due to environmental complexities. To tackle this, we introduce the EdGeo toolkit, which employs a diffusion-based model guided by physics principles to generate high-fidelity velocity maps. The toolkit uses the acoustic wave equation to generate corresponding seismic waveform data, facilitating the fine-tuning of pruned ML models. Our results demonstrate significant improvements in SSIM scores and reduction in both MAE and MSE across various pruning ratios. Notably, the ML model fine-tuned using data generated by EdGeo yields superior quality of velocity maps, especially in representing unprivileged features, outperforming other existing methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (24)
  1. K. T. Tran and et al., “Sinkhole detection using 2d full seismic waveform tomography,” Geophysics, 2013.
  2. D. Alumbaugh and et al., “The kimberlina synthetic multiphysics dataset for co2 monitoring investigations,” Geoscience Data Journal, 2023.
  3. Y. Lin and et al., “Quantifying subsurface geophysical properties changes using double-difference seismic-waveform inversion with a modified total-variation regularization scheme,” Geophysical Supplements to the Monthly Notices of the Royal Astronomical Society, 2015.
  4. J. Yang and et al., “Automated architecture search for brain-inspired hyperdimensional computing,” arXiv preprint arXiv:2202.05827, 2022.
  5. J. Liao and et al., “Shadow detection via predicting the confidence maps of shadow detection methods,” in Proceedings of the 29th ACM International Conference on Multimedia, 2021, pp. 704–712.
  6. J. Yang and et al., “On-device unsupervised image segmentation,” arXiv preprint arXiv:2303.12753, 2023.
  7. J. Li and et al., “A novel spatial-temporal variational quantum circuit to enable deep learning on nisq devices,” in 2023 IEEE International Conference on Quantum Computing and Engineering (QCE), vol. 1.  IEEE, 2023, pp. 272–282.
  8. Z. Hu and et al., “Battle against fluctuating quantum noise: Compression-aided framework to enable robust quantum neural network,” arXiv preprint arXiv:2304.04666, 2023.
  9. Y. Wu and et al., “Inversionnet: An efficient and accurate data-driven full waveform inversion,” IEEE Transactions on Computational Imaging, 2019.
  10. Y. Sheng and et al., “The larger the fairer? small neural networks can achieve fairness for edge devices,” in Proceedings of the 59th ACM/IEEE Design Automation Conference, 2022, pp. 163–168.
  11. Y. Sheng and et al., “Muffin: A framework toward multi-dimension ai fairness by uniting off-the-shelf models,” in 2023 60th ACM/IEEE Design Automation Conference (DAC).  IEEE, 2023, pp. 1–6.
  12. J. J. Sousa and et al., “Geohazards monitoring and assessment using multi-source earth observation techniques,” Remote Sensing, 2021.
  13. Z. Wang, Y. Wu, and et al, “Lightweight run-time working memory compression for deployment of deep neural networks on resource-constrained mcus,” in Proceedings of the 26th Asia and South Pacific Design Automation Conference, 2021, pp. 607–614.
  14. W. Jiang and et al., “Hardware/software co-exploration of neural architectures,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 39, no. 12, pp. 4805–4815, 2020.
  15. Y. Wu and et al, “Intermittent inference with nonuniformly compressed multi-exit neural network for energy harvesting powered devices,” in 2020 57th ACM/IEEE Design Automation Conference (DAC).  IEEE, 2020, pp. 1–6.
  16. Y. Song and et al., “Dancing along battery: Enabling transformer with run-time reconfigurability on mobile devices,” in 2021 58th ACM/IEEE Design Automation Conference (DAC).  IEEE, 2021, pp. 1003–1008.
  17. Z. Wang, I. Putla, W. Jiang, and Y. Lin, “Edge-inversionnet: Enabling efficient inference of inversionnet on edge devices,” in Third International Meeting for Applied Geoscience & Energy.  Society of Exploration Geophysicists and American Association of Petroleum …, 2023, pp. 1059–1063.
  18. Z. Zhou and et al., “A data-driven co2 leakage detection using seismic data and spatial–temporal densely connected convolutional neural networks,” International Journal of Greenhouse Gas Control, 2019.
  19. C. Deng and et al., “OpenFWI: large-scale multi-structural benchmark datasets for seismic full waveform inversion,” arXiv preprint arXiv:2111.02926, 2021.
  20. D. P. Kingma and et al., “Auto-encoding variational bayes,” arXiv preprint arXiv:1312.6114, 2013.
  21. Y. Yang and et al., “Making invisible visible: Data-driven seismic inversion with spatio-temporally constrained data augmentation,” IEEE Transactions on Geoscience and Remote Sensing, 2022.
  22. J. Ho and et al., “Denoising diffusion probabilistic models,” Advances in neural information processing systems, 2020.
  23. J. Song and et al., “Denoising diffusion implicit models,” arXiv preprint arXiv:2010.02502, 2020.
  24. Z. Liu and et al., “Learning efficient convolutional networks through network slimming,” in Proceedings of ICCV, 2017.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Junhuan Yang (11 papers)
  2. Hanchen Wang (49 papers)
  3. Yi Sheng (13 papers)
  4. Youzuo Lin (51 papers)
  5. Lei Yang (372 papers)
Citations (2)

Summary

We haven't generated a summary for this paper yet.