Climatic and seismic data-driven deep learning model for earthquake magnitude prediction

Abstract

The effects of global warming are felt not only in the Earth’s climate but also in the geology of the planet. Modest variations in stress and pore-fluid pressure brought on by temperature variations, precipitation, air pressure, and snow coverage are hypothesized to influence seismicity on local and regional scales. Earthquakes can be anticipated by intelligently evaluating historical climatic datasets and earthquake catalogs that have been collected all over the world. This study attempts to predict the magnitude of the next probable earthquake by evaluating climate data along with eight mathematically calculated seismic parameters. Global temperature has been selected as the only climatic variable for this research, as it substantially affects the planet’s ecosystem and civilization. Three popular deep neural network models, namely, long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), and transformer models, were used to predict the magnitude of the next earthquakes in three seismic regions: Japan, Indonesia, and the Hindu-Kush Karakoram Himalayan (HKKH) region. Several well-known metrics, such as the mean absolute error (MAE), mean squared error (MSE), log-cosh loss, and mean squared logarithmic error (MSLE), have been used to analyse these models. All models eventually settle on a small value for these cost functions, demonstrating the accuracy of these models in predicting earthquake magnitudes. These approaches produce significant and encouraging results when used to predict earthquake magnitude at diverse places, opening the way for the ultimate robust prediction mechanism that has not yet been created.

Electromagnetic Umbrella Modeling of Mega Meteorological Anomaly Disasters and Large Earthquake Associations

“…(1) His analysis of the correlation between droughts and earthquakes was questioned and criticized by many later researchers because he used only crude and simple statistical calculations and did not reveal the deeper geophysical mechanisms. (2) In 2023, Indian scholars like Bikash Sadhukhan and others comprehensively evaluated the results of academics in seismic events and climate anomalies, including drought, precipitation, and so on. (2) We agree with the view that data on climate anomalies can be used as an aid in predicting earthquakes as precursors.…”

“…(2) In 2023, Indian scholars like Bikash Sadhukhan and others comprehensively evaluated the results of academics in seismic events and climate anomalies, including drought, precipitation, and so on. (2) We agree with the view that data on climate anomalies can be used as an aid in predicting earthquakes as precursors. Meteorology, as a well-established discipline with welldeveloped theories, is able to predict climate change quite accurately by using meteorological satellite imagery, such as changes in temperature, barometric pressure, cyclones and atmospheric circulations, and the stresses induced by precipitation, barometric pressure, and snow accumulation.…”

Short term prediction of water level based on deep learning during the flood season, in the downstream area of The Three Gorges Reservoir

“…The Transformer is a new model architecture proposed by the Google team in 2017 (Vaswani et al 2017). This model departs from the traditional encoder-decoder approach, which typically combines Convolutional Neural Network (CNN) or RNN, by replacing LSTM with an Attention-based structure (Sadhukhan et al 2023). Building a model based on the Transformer can alleviate the bottleneck of previous algorithms.…”

Analysis of Machine Learning Algorithms for Seismic Anomaly Detection in Indonesia: Unveiling Patterns in the Pacific Ring of Fire

“…The resurgence and advancement of machine learning technologies, such as Support Vector Machines and Artificial Neural Networks, have revolutionized seismic analysis. However, these technologies usually necessitate substantial amounts of labeled data for effective training, a significant challenge given the infrequent and unpredictable nature of seismic anomalies (Ruff et al, 2021;Sadhukhan, Chakraborty, Mukherjee, & Samanta, 2023;Spahic, Lundteigen, & Hepsø, 2023;Zhao, 2021). Our study addresses this hurdle by focusing on unsupervised learning algorithms, which are highly effective in situations with ample data but limited labeling.…”

“…This is particularly relevant for Indonesia, where seismic events are not only common but also diverse in nature, rendering labeled data sparse and often not representative (Al-Ruzouq et al, 2020;Figueira & Vaz, 2022;Münchmeyer, Bindi, Leser, & Tilmann, 2021). Conventional models often lag in adapting to the variable and unpredictable seismic patterns characteristic of Indonesia (Chen, Qin, Xue, Yang, & Zhang, 2022;Ridzwan & Yusoff, 2023;Sadhukhan et al, 2023).…”