MACHINE LEARNING ALGORITHMS APPLIED TO SEISMIC ACTIVITY (original) (raw)
Related papers
The purpose of this research is to apply methods of support vector machines (SVMs) for fast determination of earthquake depths using seismic records of the " El Rosal " station, near to the city of Bogotá – Colombia. The algorithm was trained with time signal descriptors of 863 seismic events acquired between January 1998 and October 2008. Only earthquakes with magnitude ≥ 2 M_L were contemplated, filtering its signals to remove diverse kind of noises not related to earth tremors. During training stages of SVM several combinations of kernel function exponent and complexity factor were considered for time signals of 5, 10 and 15 seconds along with earthquake magnitudes of 2.0, 2.5, 3.0 and 3.5 M_L. The best classification of SVM was obtained using time signals of 15 seconds and earthquake magnitudes of 3.5 M_L with kernel exponent of 10 and complexity factor of 2, showing accuracy of 0,6 ± 16,5 kilometers, which is good enough to be used in an early warning system for the city of Bogotá. It is recommended to provide this model with more recent seismic events in order to improve its accuracy.
Classifying and Forecasting Seismic Event Characteristics Using Artificial Intelligence
Research Square (Research Square), 2024
Seismic events present a significant global threat, underscoring the need for effective models to provide insights into these natural disasters. This paper addresses the critical need for advanced seismic event analysis by combining traditional data analysis with cutting-edge machine learning models. The primary objective is to develop models that classify seismic events into different types based on their geological and seismic characteristics and forecast their magnitude. The seismic activities categorized into groups by magnitude to enhance the understanding of these phenomena. Location-Based and Seismic Characteristics Features are utilized in seven machine learning models: Rule-Based Classifier, K-mean Classifier, Decision Trees, Random Forest, Support Vector Machines (SVM), k-Nearest Neighbors (kNN), and Logistic Regression. This approach aims to provide valuable insights into seismic activities, contributing to the development of more nuanced disaster analysis and early warning systems.
TELKOMNIKA Telecommunication Computing Electronics and Control, 2020
Indonesia resides on most earthquake region with more than 100 active volcanoes, and high number of seismic activities per year. In order to reduce the casualty, some method to predict earthquake have been developed to estimate the seismic movement. However, most prediction use only short term of historical data to predict the incoming earthquake, which has limitation on model performance. This work uses medium to long term earthquake historical data that were collected from 2 local government bodies and 8 legitimate international sources. We make an estimation of a medium-to-long term prediction via machine learning algorithms, which are multinomial logistic regression, support vector machine and Naïve Bayes, and compares their performance. This work shows that the support vector machine outperforms other method. We compare the root mean square error computation results that lead us into how concentrated data is around the line of best fit, where the multinomial logistic regression is 0.777, Naïve Bayes is 0.922 and support vector machine is 0.751. In predicting future earthquake, support vector machine outperforms other two methods that produce significant distance and magnitude to current earthquake report. This is an open access article under the CC BY-SA license.
Classification of Databases and Methods for Seismic Data Analysis and Earthquake Prediction
2014
Earthquake is one the most important disasters in the world. In order to save lives and building substructures of countries, more research in this field should be carried out as a matter of severity. Computer modeling and different artificial intelligence algorithms are known as applicable tools for the earthquake hazards prediction and prevention. This article tries to review the recent studies that have been conducted in this field. For this purpose, the literature methods have been classified into three categories including machine learning, data mining, and seismic feature extraction methods. The machine learning methods are also divided into several subcategories such as Artificial Neural Networks (ANNs), fuzzy systems and Support Vector Machines (SVMs) methods. The similar condition goes with the data mining methods in categorization. Moreover, the seismic feature extraction methods explain the important features used by aforementioned methods. Most of the recent researches ar...
Earthquake Prediction Using Machine Learning
International Research Journal of Modernization in Engineering Technology and Science, 2023
An earthquake is a natural calamity that is well-known for the devastation it causes to both naturally existent and artificial structures, including as buildings and residential areas. Seismometers are used to measure earthquakes because they detect vibrations induced by seismic waves travelling through the earth's crust. To forecast earthquakes, an examination of current machine learning classifier approaches is employed. Machine learning algorithms such as Logistic Regression, Support Vector Machine (SVM), Random Forest Classifier, and K-Nearest Neighbours,decision tree are used to forecast earthquakes. After examining all of the previously utilised methods, the best algorithm will be considered. The method used to forecast the property will be investigated,as will the data analysis.
Support Vector Machine Based Facies Classification Using Seismic Attributes in an Oil Field of Iran
2013
Seismic facies analysis (SFA) aims to classify similar seismic traces based on amplitude, phase, frequency, and other seismic attributes. SFA has proven useful in interpreting seismic data, allowing significant information on subsurface geological structures to be extracted. While facies analysis has been widely investigated through unsupervised-classification-based studies, there are few cases associated with supervised classification methods. In this study, we follow supervised classification scheme under classifiers, the support vector classifier (SVC), and multilayer perceptrons (MLP) to provide an opportunity for directly assessing the feasibility of different classifiers. Before choosing classifier, we evaluate extracted seismic attributes using forward feature selection (FFS) and backward feature selection (BFS) methods for logical SFA. The analyses are examined with data from an oil field in Iran, and the results are discussed in detail. The numerical relative errors associa...
Earthquake prediction in Iraq using machine learning techniques
Indonesian Journal of Electrical Engineering and Computer Science, 2022
This study deals with addressing the scientific achievements and the history of earthquake prediction in Iraq, in addition to attempting to discuss the possibility of machine learning to predict earthquakes from a theoretical perspective. The idea of predicting earthquakes gives at least a little time to protect people and reduce earthquake damage. In Iraq, we notice an increase in the occurrence of earthquakes, especially in the southern regions, where they form a strange phenomenon because they are plain areas and far from the seismic fault line, due to the errors that accompany excessive oil extraction and in random and unstudied ways, and geological studies raise fears in predicting an increase in earthquakes for the coming years. We have explored the possibility of applying machine learning technology to predict earthquakes in Iraq, and follow-up recording of tremors at different stations in Iraq through three centers of seismic sensor networks. In addition to the earthquake catalog in Iraq (1900-2019). This study may pave the way for more research to develop an integrated and accurate earthquake prediction system using machine-learning technologies.
International Journal of Innovative Research in Engineering and Management (IJIREM), 2024
This paper explores the application of machine learning models, specifically XGBoost, Stacking Regressor, and Long Short-Term Memory (LSTM), for predicting earthquake magnitudes in Düzce, Turkey. The models were trained and tested on seismic data to predict moment magnitude (Mw). The performance of each model was evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R²). The results indicate that the XGBoost model outperforms the other models with a higher R² value and lower error metrics, providing a more accurate prediction of seismic events.