{ "id": 572365, "title": "📶🌊Good starter resources for Yale/UNC GWI contest 📶🌊", "url": "/competitions/waveform-inversion/discussion/572365", "author_name": "Kalilur Rahman", "post_date": "2025-04-09T06:58:35.198000", "votes": 10, "comment_count": 0, "views": 0, "content": "

Some good resources for you to look at!

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
ResourceNote/CommentActual URL
PaperLarge-scale FWI dataset-based learning for better accuracy and generalization.https://arxiv.org/abs/2206.09806
PaperSelf-supervised learning for pseudo low-frequency data generation.https://arxiv.org/abs/2107.12345
PaperSiameseFWI: Self-supervised comparative analysis using twin CNNs.https://arxiv.org/abs/2301.09876
Code RepositoryDevito-based FWI tutorial for forward modeling and optimization workflows.https://github.com/devitocodes/devito
Code RepositorySelf-supervised FWI pipeline with field data examples (SiameseFWI).https://figshare.com/articles/code/FWI_Codes/25521475
ArticleOverview of Full Waveform Inversion and hybrid ML approaches.https://library.seg.org/doi/10.1190/1.3238367
Video TutorialIntroduction to FWI and seismic imaging techniques.https://www.youtube.com/watch?v=22m27MhzSQs
PaperCombined misfit functions for FWI with real-land seismic data applications.https://doi.org/10.3389/feart.2023.1264009
PaperAccelerating FWI using transfer learning for faster convergence and robustness.https://arxiv.org/abs/2408.00695
PaperPhysics-guided self-supervised learning for low-frequency data prediction in FWI.https://library.seg.org/doi/10.1190/segam2020-3423396.1
SoftwareSeisFlows: Python-based automated workflow tool for FWI and seismic migration.https://pypi.org/project/seisflows
PaperGlobal FWI reveals complex mantle structures with diverse origins of anomalies.https://pmc.ncbi.nlm.nih.gov/articles/PMC11535529
PaperEmpirical study of large-scale data-driven FWI using OpenFWI datasets.https://pmc.ncbi.nlm.nih.gov/articles/PMC11358280
PaperDeep pre-trained FWI combining supervised learning and physics-informed networks.https://academic.oup.com/gji/article/235/1/119/7176057
\n

Kaggle Notebooks/Kernels on Seismic activity analysis

\n\n

- Introduction to Python & ML for Geosciences - https://www.kaggle.com/code/rajsahu2004/introduction-to-python-ml-for-geosciences

\n", "messages": [ { "id": 3174487, "postDate": "2025-04-09T06:58:35.200Z", "content": "

Some good resources for you to look at!

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
ResourceNote/CommentActual URL
PaperLarge-scale FWI dataset-based learning for better accuracy and generalization.https://arxiv.org/abs/2206.09806
PaperSelf-supervised learning for pseudo low-frequency data generation.https://arxiv.org/abs/2107.12345
PaperSiameseFWI: Self-supervised comparative analysis using twin CNNs.https://arxiv.org/abs/2301.09876
Code RepositoryDevito-based FWI tutorial for forward modeling and optimization workflows.https://github.com/devitocodes/devito
Code RepositorySelf-supervised FWI pipeline with field data examples (SiameseFWI).https://figshare.com/articles/code/FWI_Codes/25521475
ArticleOverview of Full Waveform Inversion and hybrid ML approaches.https://library.seg.org/doi/10.1190/1.3238367
Video TutorialIntroduction to FWI and seismic imaging techniques.https://www.youtube.com/watch?v=22m27MhzSQs
PaperCombined misfit functions for FWI with real-land seismic data applications.https://doi.org/10.3389/feart.2023.1264009
PaperAccelerating FWI using transfer learning for faster convergence and robustness.https://arxiv.org/abs/2408.00695
PaperPhysics-guided self-supervised learning for low-frequency data prediction in FWI.https://library.seg.org/doi/10.1190/segam2020-3423396.1
SoftwareSeisFlows: Python-based automated workflow tool for FWI and seismic migration.https://pypi.org/project/seisflows
PaperGlobal FWI reveals complex mantle structures with diverse origins of anomalies.https://pmc.ncbi.nlm.nih.gov/articles/PMC11535529
PaperEmpirical study of large-scale data-driven FWI using OpenFWI datasets.https://pmc.ncbi.nlm.nih.gov/articles/PMC11358280
PaperDeep pre-trained FWI combining supervised learning and physics-informed networks.https://academic.oup.com/gji/article/235/1/119/7176057
\n

Kaggle Notebooks/Kernels on Seismic activity analysis

\n\n

- Introduction to Python & ML for Geosciences - https://www.kaggle.com/code/rajsahu2004/introduction-to-python-ml-for-geosciences

\n", "rawMarkdown": "Some good resources for you to look at!\n\n| **Resource** | **Note/Comment** | **Actual URL** |\n|---------------------|----------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------|\n| Paper | Large-scale FWI dataset-based learning for better accuracy and generalization. | [https://arxiv.org/abs/2206.09806](https://arxiv.org/abs/2206.09806) |\n| Paper | Self-supervised learning for pseudo low-frequency data generation. | [https://arxiv.org/abs/2107.12345](https://arxiv.org/abs/2107.12345) |\n| Paper | SiameseFWI: Self-supervised comparative analysis using twin CNNs. | [https://arxiv.org/abs/2301.09876](https://arxiv.org/abs/2301.09876) |\n| Code Repository | Devito-based FWI tutorial for forward modeling and optimization workflows. | [https://github.com/devitocodes/devito](https://github.com/devitocodes/devito) |\n| Code Repository | Self-supervised FWI pipeline with field data examples (SiameseFWI). | [https://figshare.com/articles/code/FWI_Codes/25521475](https://figshare.com/articles/code/FWI_Codes/25521475) |\n| Article | Overview of Full Waveform Inversion and hybrid ML approaches. | [https://library.seg.org/doi/10.1190/1.3238367](https://library.seg.org/doi/10.1190/1.3238367) |\n| Video Tutorial | Introduction to FWI and seismic imaging techniques. | [https://www.youtube.com/watch?v=22m27MhzSQs](https://www.youtube.com/watch?v=22m27MhzSQs) |\n| Paper | Combined misfit functions for FWI with real-land seismic data applications. | [https://doi.org/10.3389/feart.2023.1264009](https://doi.org/10.3389/feart.2023.1264009) |\n| Paper | Accelerating FWI using transfer learning for faster convergence and robustness. | [https://arxiv.org/abs/2408.00695](https://arxiv.org/abs/2408.00695) |\n| Paper | Physics-guided self-supervised learning for low-frequency data prediction in FWI.| [https://library.seg.org/doi/10.1190/segam2020-3423396.1](https://library.seg.org/doi/10.1190/segam2020-3423396.1) |\n| Software | SeisFlows: Python-based automated workflow tool for FWI and seismic migration. | [https://pypi.org/project/seisflows](https://pypi.org/project/seisflows) |\n| Paper | Global FWI reveals complex mantle structures with diverse origins of anomalies. | [https://pmc.ncbi.nlm.nih.gov/articles/PMC11535529](https://pmc.ncbi.nlm.nih.gov/articles/PMC11535529) |\n| Paper | Empirical study of large-scale data-driven FWI using OpenFWI datasets. | [https://pmc.ncbi.nlm.nih.gov/articles/PMC11358280](https://pmc.ncbi.nlm.nih.gov/articles/PMC11358280) |\n| Paper | Deep pre-trained FWI combining supervised learning and physics-informed networks.| [https://academic.oup.com/gji/article/235/1/119/7176057](https://academic.oup.com/gji/article/235/1/119/7176057) |\n\n\n## Kaggle Notebooks/Kernels on Seismic activity analysis \n- Starter: Seismic activity 148e0bef-5 - https://www.kaggle.com/code/kerneler/starter-seismic-activity-148e0bef-5\n- Starter: Seismic_classification_data 3ec3eb71-5 -https://www.kaggle.com/code/kerneler/starter-seismic-classification-data-3ec3eb71-5\n- Starter: Seismic Center (ROM)- 57dfea41-4 - https://www.kaggle.com/code/kerneler/starter-seismic-center-rom-57dfea41-4\n- Starter: 3D reflection seismic data fa518515-7 https://www.kaggle.com/code/kerneler/starter-3d-reflection-seismic-data-fa518515-7\n- Starter: Seismic Data b8025654-f - https://www.kaggle.com/code/kerneler/starter-seismic-data-b8025654-f\n# - Introduction to Python & ML for Geosciences - https://www.kaggle.com/code/rajsahu2004/introduction-to-python-ml-for-geosciences\n- DWT Earthquake w LTO v01 - https://www.kaggle.com/code/pnussbaum/dwt-earthquake-w-lto-v01\n- Romanian Earthquakes analysis notebook - https://www.kaggle.com/code/gpreda/romanian-earthquakes-analysis-notebook \n- SEG-Y headers and Seismic inversion - https://www.kaggle.com/code/alaahassan/seg-y-headers-and-seismic-inversion\nAll the best!\n", "votes": 10 } ], "comments": [], "raw_markdown_by_id": { "3174487": "Some good resources for you to look at!\n\n| **Resource** | **Note/Comment** | **Actual URL** |\n|---------------------|----------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------|\n| Paper | Large-scale FWI dataset-based learning for better accuracy and generalization. | [https://arxiv.org/abs/2206.09806](https://arxiv.org/abs/2206.09806) |\n| Paper | Self-supervised learning for pseudo low-frequency data generation. | [https://arxiv.org/abs/2107.12345](https://arxiv.org/abs/2107.12345) |\n| Paper | SiameseFWI: Self-supervised comparative analysis using twin CNNs. | [https://arxiv.org/abs/2301.09876](https://arxiv.org/abs/2301.09876) |\n| Code Repository | Devito-based FWI tutorial for forward modeling and optimization workflows. | [https://github.com/devitocodes/devito](https://github.com/devitocodes/devito) |\n| Code Repository | Self-supervised FWI pipeline with field data examples (SiameseFWI). | [https://figshare.com/articles/code/FWI_Codes/25521475](https://figshare.com/articles/code/FWI_Codes/25521475) |\n| Article | Overview of Full Waveform Inversion and hybrid ML approaches. | [https://library.seg.org/doi/10.1190/1.3238367](https://library.seg.org/doi/10.1190/1.3238367) |\n| Video Tutorial | Introduction to FWI and seismic imaging techniques. | [https://www.youtube.com/watch?v=22m27MhzSQs](https://www.youtube.com/watch?v=22m27MhzSQs) |\n| Paper | Combined misfit functions for FWI with real-land seismic data applications. | [https://doi.org/10.3389/feart.2023.1264009](https://doi.org/10.3389/feart.2023.1264009) |\n| Paper | Accelerating FWI using transfer learning for faster convergence and robustness. | [https://arxiv.org/abs/2408.00695](https://arxiv.org/abs/2408.00695) |\n| Paper | Physics-guided self-supervised learning for low-frequency data prediction in FWI.| [https://library.seg.org/doi/10.1190/segam2020-3423396.1](https://library.seg.org/doi/10.1190/segam2020-3423396.1) |\n| Software | SeisFlows: Python-based automated workflow tool for FWI and seismic migration. | [https://pypi.org/project/seisflows](https://pypi.org/project/seisflows) |\n| Paper | Global FWI reveals complex mantle structures with diverse origins of anomalies. | [https://pmc.ncbi.nlm.nih.gov/articles/PMC11535529](https://pmc.ncbi.nlm.nih.gov/articles/PMC11535529) |\n| Paper | Empirical study of large-scale data-driven FWI using OpenFWI datasets. | [https://pmc.ncbi.nlm.nih.gov/articles/PMC11358280](https://pmc.ncbi.nlm.nih.gov/articles/PMC11358280) |\n| Paper | Deep pre-trained FWI combining supervised learning and physics-informed networks.| [https://academic.oup.com/gji/article/235/1/119/7176057](https://academic.oup.com/gji/article/235/1/119/7176057) |\n\n\n## Kaggle Notebooks/Kernels on Seismic activity analysis \n- Starter: Seismic activity 148e0bef-5 - https://www.kaggle.com/code/kerneler/starter-seismic-activity-148e0bef-5\n- Starter: Seismic_classification_data 3ec3eb71-5 -https://www.kaggle.com/code/kerneler/starter-seismic-classification-data-3ec3eb71-5\n- Starter: Seismic Center (ROM)- 57dfea41-4 - https://www.kaggle.com/code/kerneler/starter-seismic-center-rom-57dfea41-4\n- Starter: 3D reflection seismic data fa518515-7 https://www.kaggle.com/code/kerneler/starter-3d-reflection-seismic-data-fa518515-7\n- Starter: Seismic Data b8025654-f - https://www.kaggle.com/code/kerneler/starter-seismic-data-b8025654-f\n# - Introduction to Python & ML for Geosciences - https://www.kaggle.com/code/rajsahu2004/introduction-to-python-ml-for-geosciences\n- DWT Earthquake w LTO v01 - https://www.kaggle.com/code/pnussbaum/dwt-earthquake-w-lto-v01\n- Romanian Earthquakes analysis notebook - https://www.kaggle.com/code/gpreda/romanian-earthquakes-analysis-notebook \n- SEG-Y headers and Seismic inversion - https://www.kaggle.com/code/alaahassan/seg-y-headers-and-seismic-inversion\nAll the best!\n" } }