Introduction to Machine Learning techniques for Geoscience

Transcript

1. Machine Learning Techniques for Geoscience Applications Jesper Dramsch
2. Where are we going today? • My Background • What’s Machine Learning? • Geo to ML?! • What’s important in ML?
3. What is Machine Learning? And why should I care?
5. if x > 5 Classical rule-based and expert systems
6. Computers figure it out based on the data
7. Tossing Bot! (http://tossingbot.cs.princeton.edu/)
8. Models that do not have external information Blackbox models
9. What is AI, ML, and Deep Learning?
10. Style Transfer for Multiple Tasks
11. Everybody dance now! (https://arxiv.org/pdf/1808.07371.pdf)
12. What is the connection Why do we care in geoscience?!
13. Take seismic data
14. Get some “interpretation”
15. Or get some “inversion”
16. Neural Networks The new hype that is older than all of us
17. A Simple Neuron 1 1 + 2
18. A Small Neural Network
19. A Deep Neural Network
20. Different Combinations In Neural Networks
21. Is that all? What else is there to make Artificial Intelligence?!
22. Convolutional Neural Networks The machine learning that sees
23. A neural network as it is used today
24. The learned filters with different abstractions
25. A Geoscience Application
26. Matching of seismic data
27. The differences between unmatched and matched
28. Compared to a baseline method
29. Take it to the next level
30. Real Data (CC-BY A. Çuğun) 30 How do we generate data like this with a Neural Network?
31. Real Data (CC-BY A. Çuğun) Network Data Legend 31 Generative Adversarial Networks
32. Latent Space (CC-BY Hudson) Real Data (CC-BY A. Çuğun) Network Data Legend 32 Start from latent space
33. Latent Space (CC-BY Hudson) Generator (CC-BY-SA T. Vaughn) Real Data (CC-BY A. Çuğun) Network Data Legend 33 Feed it to a Generator
34. Latent Space (CC-BY Hudson) Generator (CC-BY-SA T. Vaughn) Fake Data (CC-BY Tony A.) Real Data (CC-BY A. Çuğun) Network Data Legend 34 That generates some Fake Data
35. Latent Space (CC-BY Hudson) Generator (CC-BY-SA T. Vaughn) Fake Data (CC-BY Tony A.) Real Data (CC-BY A. Çuğun) Discriminator(CC-BY Brickset) Network Data Legend 35 Discriminator judges if sample is real
36. Latent Space (CC-BY Hudson) Generator (CC-BY-SA T. Vaughn) Fake Data (CC-BY Tony A.) Real Data (CC-BY A. Çuğun) Loss (CC-BY S. MacEntee) Discriminator(CC-BY Brickset) Network Data Legend (CC-BY Dramsch) 36 Both networks learn regardless if D is correct
37. What’s the application?
38. Some seismic data
39. An “inversion” Generator (CC-BY-SA T. Vaughn) generated by a neural network
40. • Generating Synthetic Data • Earthquake localisation • Drill Core Processing • Clustering of Well Data • Prediction of Volcanic activity • Satellite Data What else is possible?
41. Many Other Machine Learning Algorithms
42. Seismogram Tagging (https://www.nature.com/articles/s41467-020-17591-w)
43. Core Image Segmentation (https://joss.theoj.org/papers/10.21105/joss.01969)
44. Well Log Fascies Prediction (https://doi.org/10.1190/tle35100906.1)
45. Remote Sensing Data (https://doi.org/10.1117/1.JRS.11.036028)
46. Some Tips to Get Started?
47. Start Projects Application as important as Theory • Participate in Hackathons • Build Apps • Start Small • Compete on Kaggle • Get familiar with the Math
48. 70 Years of Machine Learning in Geoscience https://authors.elsevier.com/b/1bpiNEroEut0M
50. Available Data For Projects and Experiments • Open Data: https://wiki.seg.org/wiki/Open_d ata • Full Reservoir with Wells: https://wiki.seg.org/wiki/The_No rth_Sea_Volve_Data_Village • Seismic Interpretation: https://github.com/yalaudah/faci es_classification_benchmark • Salt Identification in Seismic: http://bit.ly/kaggle-salt