Machine Learning Based Classification Algorithm for Seismic Blasting Recognition Model Research
Rong Chen
Mingyuan Liu
Yingchao Niu
Zhuolin Yu
DOI: https://doi.org/10.59429/esta.v10i5.1418
Keywords: CEEMDAN; KNN; SVM; Seismic Blast Recognition
Abstract
Seismic signal identification is an important part of seismology and earthquake observation, but urban engineering and unnatural seismic events interfere with seismic recording and management, requiring the use of data to build relevant and reliable models for identification and exclusion. Firstly, the seismic wave signals are mapped according to the data, the signal characteristics are observed, the seismic signals are decomposed using CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise), the sample entropy is solved for the first 7 IMFs, and the sample entropy is utilized to construct the feature vectors as the Using the sample entropy to construct feature vectors as training features, KNN (K-NearestNeighbor), and SVM (Support Vector Machine) models were constructed to solve and evaluate the model effects, Recall and F1score, with the highest score reaching 100%. It plays a crucial role in the development of earthquake early warning technology as well as earthquake prevention technology, and has great reference value for future related research.
References
Patterson, B., Leone, G., Pantoja, M., & Behrouzi, A. A. (2018). Deep learning for automated image classification of seismic damage to built infrastructure. In Eleventh US National Conference on Earthquake Engineering.
Abdalzaher, M. S., Moustafa, S. S., Abd-Elnaby, M., & Elwekeil, M. (2021). Comparative performance assessments of machine-learning methods for artificial seismic sources discrimination. IEEE Access, 9, 65524-65535.
Yavuz, E., Iban, M. C., & Arpaz, E. (2023). Identifying the source types of the seismic events using discriminant functions and tree-based machine learning algorithms at Soma Region, Turkey. Environmental Earth Sciences, 82(11), 1-15.
Rincon-Yanez, D., De Lauro, E., Petrosino, S., Senatore, S., & Falanga, M. (2022). Identifying the Fingerprint of a Volcano in the Background Seismic Noise from Machine Learning-Based Approach. Applied Sciences, 12(14), 6835.
Huang, L., Li, J., Hao, H., & Li, X. (2018). Micro-seismic event detection and location in underground mines by using Convolutional Neural Networks (CNN) and deep learning. Tunnelling and Underground Space Technology, 81, 265-276.
Ren, J., Zhou, S., Wang, J., Yang, S., & Liu, C. (2022). Research on Identification of Natural and Unnatural Earthquake Events Based on AlexNet Convolutional Neural Network. Wireless Communications and Mobile Computing, 2022.