Machine Learning Modelling and Feature Engineering in Seismology Experiment

Abstract

This article aims to discusses machine learning modelling using a dataset provided by the LANL (Los Alamos National Laboratory) earthquake prediction competition hosted by Kaggle. The data were obtained from a laboratory stick-slip friction experiment that mimics real earthquakes. Digitized acoustic signals were recorded against time to failure of a granular layer compressed between steel plates. In this work, machine learning was employed to develop models that could predict earthquakes. The aim is to highlight the importance and potential applicability of machine learning in seismology The XGBoost algorithm was used for modelling combined with 6-fold cross-validation and the mean absolute error (MAE) metric for model quality estimation. The backward feature elimination technique was used followed by the forward feature construction approach to find the best combination of features. The advantage of this feature engineering method is that it enables the best subset to be found from a relatively large set of features in a relatively short time. It was confirmed that the proper combination of statistical characteristics describing acoustic data can be used for effective prediction of time to failure. Additionally, statistical features based on the autocorrelation of acoustic data can also be used for further improvement of model quality. A total of 48 statistical features were considered. The best subset was determined as having 10 features. Its corresponding MAE was 1.913 s, which was stable to the third decimal point. The presented results can be used to develop artificial intelligence algorithms devoted to earthquake prediction.

Attention Network Forecasts Time‐to‐Failure in Laboratory Shear Experiments

“…(2020), who used a CNN and LSTM for an MAE of 1.51, and Brykov et al. (2020), who used XGBoost for an MAE of 1.91. It is unclear if the reported MAE from these follow‐up papers comes from the small “public” test set available to all during the competition, or the larger “private” test set, which was used to determine the competition winners.…”

An Object-Oriented Approach for the Recursive Numeration and Visualization of the Key Strata of Coal Mines

“…Emerging technologies such as artificial intelligence, data mining, machine learning, and big data have had huge impacts on many traditional industries. Many traditional industries have made full use of the research results from the development of computer technology to provide new research ideas and solutions for the research of some professional problems (Lin et al, 2018;Ahmed et al, 2020;Lin et al, 2020b;Brykov et al, 2020;Ge et al, 2020;Leng et al, 2020). Under the background of the rapid popularization of computer technology in various areas, basic programming abilities, which makes it possible to write programs by oneself, have become basic skills of universities, research institutions, and even field staff.…”

(Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural Network

“…ANNs are clearly not new in the processing of geophysical data [36][37][38][39][40]. However, the attempts to apply them to ATEM observations are limited to the data processing [41] and geological interpretation of the geophysical results [42].…”