Earthquake detection and location for Earthquake Early Warning Using Deep Learning

Abstract

Earthquake Early Warning System (EEWS) is a warning system that provides information about the estimated S wave arrival time, which can cause significant and destructive seismic energy using the information carried by the P wave. Technological advances in analyzing data supported by big data, the interconnection between networks, and high-performance computing systems in the era of the 4.0 industrial revolution have posed challenges to process and analyze earthquake early warning using modern seismological techniques. Early identification of earthquake events is the key to time efficiency to accelerate the dissemination of information. Here, we implement deep learning for early detection and classification of the earthquake P wave and noise signals using raw historical data from 3 component BMKG single station (2014 -2020) in the subduction zone of West Sumatra. The feature selection of the waveform is only selected for earthquakes distance in the cluster close to the station centroid. Statistically, the results of training and testing show good and convergent performance. This result is a preliminary study of deep learning, which is targeted at the classification of earthquakes p wave and noise signals and its association to estimate early earthquake location using 3 component record channels.

Securing Fast and High-Precision Localization for Shallow Underground Explosive Source: A Curiosity-Driven Deep Reinforcement Learning Approach

“…The biggest advantage over the traditional back propagation training methods is that the deep learning can learn and model the one-to-one relationships between vibration data and source location labels automatically and independently without human involvement. Once the model is trained well, it can accurately locate the source instantly [27], [28], [29]. For example, Huang et al developed a method for identifying the TDOA and the source location of microseismic events in underground mines by combining convolutional neural network (CNN) and deep learning techniques [30].…”

An Energy Focusing-Based Scanning and Localization Method for Shallow Underground Explosive Sources

“…With the rapid development of machine learning, underground source localization methods based on machine learning have been developed [24][25][26], but they are still immature and not universal. The main reasons are: (1) there are not enough prior samples for network model training, and a large number of training samples obtained through forward simulation are not universal; (2) when underground medium changes (such as continuous hydraulic fracturing, continuous mine exploitation, etc.…”