Assessing seismic-like events prediction in model knits with unsupervised machine learning
Source abstract
Abstract
Knitted fabric exhibits avalanche-like events when deformed, which we are interested in predicting, by analogy with earthquakes. However, as in most analogous seismic models, the time intermittence and scale-invariance of these events severely jeopardize this endeavor. But more importantly, such predictions are hard to assess and not easily compared. Here we introduce a framework that allows not only to predict seismic-like, rebalanced time series, but to also evaluate and compare the relevance of competing predictions. It relies on a reinforcement learning environment that learns risk management in a model, seismically active city subjected to the crackling dynamics observed in the mechanical response of knitted fabric. Relying on extensive experimental data, we show that this mechanism allows to assess the finite predictibility of seismic-like activity, and to compare the performance of different approaches in the operational usage of such predictions.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Textile materials and evaluations · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (30)
Show source-provided references
1. Silver · 2017
2. Mnih · 2013
3. Grandmaster level in StarCraft II using multi-agent reinforcement learning10.1038/s41586-019-1724-z ↗
4. Devlin · 2018
5. Li · 2016
6. Applications of deep learning in robot vision
7. Identifying exoplanets with deep learning: A five-planet resonant chain around kepler-80 and an eighth planet around kepler-9010.3847/1538-3881/aa9e09 ↗
8. Machine learning at the energy and intensity frontiers of particle physics10.1038/s41586-018-0361-2 ↗
9. Detecting and classifying lesions in mammograms with deep learning10.1038/s41598-018-22437-z ↗
10. Improved protein structure prediction using potentials from deep learning10.1038/s41586-019-1923-7 ↗
11. Deep learning for drug design: An artificial intelligence paradigm for drug discovery in the big data era10.1208/s12248-018-0210-0 ↗
12. Neural network models for earthquake magnitude prediction using multiple seismicity indicators10.1142/S0129065707000890 ↗
13. Machine learning predicts laboratory earthquakes10.1002/2017GL074677 ↗
14. Laboratory earthquake forecasting: A machine learning competition10.1073/pnas.2011362118 ↗
15. Earthquake magnitude prediction in Hindukush region using machine learning techniques10.1007/s11069-016-2579-3 ↗
16. A study on earthquake prediction using neural network algorithms
17. Machine learning can predict the timing and size of analog earthquakes10.1029/2018GL081251 ↗
18. Large earthquake magnitude prediction in Taiwan based on deep learning neural network10.14311/NNW.2018.28.009 ↗
19. Probing slow earthquakes with deep learning10.1029/2019GL085870 ↗
20. Major earthquake event prediction using various machine learning algorithms
21. Spatiotemporally explicit earthquake prediction using deep neural network10.1016/j.soildyn.2021.106663 ↗
22. Machine learning plastic deformation of crystals10.1038/s41467-018-07737-2 ↗
23. Learning local, quenched disorder in plasticity and other crackling noise phenomena10.1038/s41524-018-0083-x ↗
24. Crackling dynamics in the mechanical response of knitted fabrics10.1103/PhysRevLett.121.058002 ↗
25. Geometry and elasticity of a knitted fabric
26. Avalanche prediction in a self-organized pile of beads10.1103/PhysRevLett.102.078701 ↗
27. K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778.10.1109/CVPR.2016.90 ↗
28. Bellemare · 2017
29. The complete (3-D) surface displacement field in the epicentral area of the 1999 MW7.1 Hector Mine Earthquake, California, from space geodetic observations10.1029/2001GL013174 ↗
30. Three-dimensional analyses of slip distributions on normal fault arrays with consequences for fault scaling10.1016/S0191-8141(96)80051-4 ↗