Figure - available from: Natural Hazards
This content is subject to copyright. Terms and conditions apply.
Source publication
Earthquake is one of the devastating and frightening natural disasters that caused big casualties in a small duration. Earthquake caused lots of damage in just a few minutes and the casualties of the earthquake increase as the population increase which also contribute to higher amount of property and buildings. Therefore, by developing model capabl...
Citations
... Further, Mousavi and Beroza (2022) have shown that machine learning, deep learning, and AI applications are already broadly used in seismology and have the potential to significantly influence the field: i) using deep learning for earthquake early warning (EEW; Wu et al., 2021); ii) detecting seismic signals and forecasting seismic activities with machine learning (Seydoux et al., 2020); and, to a lesser extent and even controversially, iii) helping to predict earthquakes (e.g. Banna et al., 2020;Marhain et al., 2021). AI applications are also applied for wild fire predictions and modelling, and evacuation procedures (Zhao et al., 2020). ...
... AI is also used for rapid impact assessments (Harirchian et al., 2021;Stojadinović et al., 2021). Some scholars even argue that AI can be used to predict earthquakes (e.g., Marhain et al., 2021), but this is heavily disputed since predicting the precise location, time, and magnitude of a future earthquake is not possible at the current state. ...
Disaster risk is increasing globally. Emerging technologies – Artificial Intelligence, Internet of Things, and remote sensing – are becoming more important in supporting disaster risk reduction and enhancing safety culture. Despite their presumed benefits, most research focuses on their technological potential, whereas societal aspects are rarely reflected. Taking a societal perspective is vital to ensure that these technologies are developed and operated in ways that benefit societies’ resilience, comply with ethical standards, are inclusive, and address potential risks and challenges. Therefore, we were particularly interested in understanding how societal impacts can be considered and leveraged throughout the development process. Based on an explorative literature review, we developed a toolbox for professionals working on emerging technologies in disaster risk reduction. By applying a Delphi study with experts on AI in seismology, we iteratively adapted and tested the toolbox. The results show that there is a need for guided reflection in order to foster discussion on the societal impacts. They further indicate a gap in the common understanding that is crucial for developing inclusive technologies or defining regulations. Our toolbox was found to be useful for professionals in reflecting on their developments and making technologies societally relevant, thereby enhancing societies’ resilience.
... One of these studies (Liu et al. 2022) had a low value of efficacy metrics, and the other one had a high value of error measurement criteria (Salam et al. 2021). The non-representativeness of the selected sample was the other problematic methodological issue of AI-based EEW research (two studies (Marhain et al. 2021;Samui and Kim 2014) had not mentioned their sample size, Table 5 in Appendix). All the reviewed studies have used statistical and mathematical computations related to AI techniques to answer their research question, used variables for developing their selected AI models have been clearly explained, and collected meteorological, seismological, and earthquake data samples that are relevant to their research question. ...
... Due to the large range of MAE in this study, the error values of the other two studies also fall within this range. In the other two studies, the MAE value is in the range of 0.2038 to 0.598 (Marhain et al. 2021;Murwantara et al. 2020). The lowest MAE is related to Random Forest and Artificial Neural Network algorithms, but only in one study, with an approximate value of 10 − 6 (Essam et al. 2021 ...
Early Earthquake Warning (EEW) systems alarm about ongoing earthquakes to reduce their devastating human and financial damages. In complicated tasks like earthquake forecasting, Artificial Intelligence (AI) solutions show promising results. The goal of this review is to investigate the AI-based EEW systems. Web of Science, Scopus, Embase, and PubMed databases were systematically searched from its beginning until April 18, 2023. Studies that used AI algorithms to develop EEWs and forecast earthquake magnitude were qualified. The quality assessment was conducted using the Mixed Methods Assessment Tool version 2018. Detailed analysis was performed on 26 of 2604 retrieved articles. Researchers predict earthquakes most often using neural network family models (21 studies). Among eight categorized groups of parameters for earthquake forecasting, it was often predicted utilizing seismic wave characteristics (65.38%) and seismic activity data (61.54%). AI models most often predicted earthquake magnitude (32.69%) and depth (15.38%). Logistic Model Tree and Bayesian Network had the highest sensitivity, accuracy, and F-measure efficiency (99.9%). Findings showed that AI algorithms can forecast earthquakes. However, additional study is needed to determine the efficacy of more data-driven AI algorithms in mining seismic data using more input variables. This review is helpful for seismologists and researchers developing EEW systems using AI.
... The array of AI and ML algorithms employed in earthquake prediction, encompassing ANN, SVM, FL, DL, Bi-LSTM, SABT, ANFIS, SVR, PKNN, NB, HMM, KMC, HC, PNN, CNNs etc., leverages diverse datasets-seismic, satellite, GPS-to train and predict models (Bowen et al., 2012, Zhou et al. (2020, Gitis et al. (2021), Essam et al. (2021), Xiong et al. (2021), Marhain et al. (2021), Tehseen et al. (2021), Berhich et al. (2022), Turarbek et al. (2023), Bhatia et al. (2023), Sadhukhan et al. (2023), Abdalzaher et al. (2023b)). While these technological strides have significantly deepened our insights and refined earthquake predictions, it's imperative to acknowledge that each algorithm comes with inherent limitations. ...
... They also suggested that the SVM model be used for additional research and development in earthquake prediction in Malaysia. Marhain et al., (2021) delved into the application of Artificial Intelligence (AI) for earthquake prediction in Terengganu, Malaysia. The study involved the analysis of meteorological data from multiple stations in Terengganu using Machine Learning (ML) methods. ...
... Each reviewed study contributes distinct perspectives on the challenges and potentials of deploying AI in earthquake forecasting. For example, Essam et al. (2021) and Xiong et al. (2021) highlight the efficacy of ground motion parameters and infrared/hyperspectral measurements, while Marhain et al. (2021) tackle challenges linked to meteorological data. Zhou et al. (2020) and Bilal (2022) emphasize the significance of historical seismic data and advanced neural network architectures, respectively. ...
Earthquakes are classified as one of the most devastating natural disasters that can have catastrophic effects on the environment, lives, and properties. There has been an increasing interest in the prediction of earthquakes and in gaining a comprehensive understanding of the mechanisms that underlie their generation, yet earthquakes are
the least predictable natural disaster. Satellite data, global positioning system, interferometry synthetic aperture radar (InSAR), and seismometers such as microelectromechanical system, seismometers, ocean bottom seismometers,
and distributed acoustic sensing systems have all been used to predict earthquakes with a high degree of success. Despite advances in seismic wave recording, storage, and analysis, earthquake time, location, and magnitude prediction remain difficult. On the other hand, new developments in artificial intelligence (AI) and the Internet of Things (IoT) have shown promising potential to deliver more insights and predictions. Thus, this article reviewed the use of AI-driven Models and IoT-based technologies for the prediction of earthquakes, the limitations of current approaches, and open research issues. The review discusses earthquake prediction setbacks due to insufficient data, inconsistencies, diversity of earthquake precursor signals, and the earth's geophysical composition. Finally, this study examines potential approaches or solutions that scientists can employ to address the challenges they face in earthquake prediction. The analysis is based on the successful application of AI and IoT in other fields.
... The study of earthquake forecasting is one of the numerous endeavours scientists make to mitigate the effects of earthquake disasters [8]. Marhain et al. [9], claims that an artificial intelligence (AI) method can be used to predict earthquakes. Using earthquake data compiled and recorded in a database, it is possible to calculate algorithm parameters [10]. ...
... Syifa et al. [24] asserts that SVM and artificial neural network (ANN) have comparable correlation results and accuracy values for tracing earthquake damage when compared. Other evaluations explain that the compared algorithms SVM, decision tree, random forest, and logistic regression have limitations for each data signalling station [9]. Due to the high number of false alarms and missed detections generated by these algorithms, human supervision is always required. ...
... Next is the model training scenario stage with a comparison of 70% training data and 30% test data. Training the model affects the availability of activation functions, the number of neurons used, and optimization as a performance criterion obtained from the values obtained by contrasting accuracy parameters [9]. The final stage is to carry out validation data and evaluate algorithm performance. ...
span>Artificial intelligence (AI) can use seismic training data to discover relationships between inputs and outcomes in real-world applications. Despite this, particularly when using geographical data, it has not been used to predict earthquakes in the Flores Sea. The algorithm will read the seismic data as a pattern of iterations throughout the operation. The output data is created by grouping based on clusters using the most effective WCSS analysis, while the input features are derived from the original international resource information system (IRIS) web service data. Given that earthquake prediction is an effort to reduce seismic disasters, this research is essential. By generating predictions, it can reduce the devastation caused by earthquakes. Using the support vector machine (SVM), hyperparameter support vector machine (HP-SVM), and particle swarm optimization support vector machine (PSO-SVM) algorithms, this study seeks to forecast the Flores Sea earthquake. According to the estimation results, the SVM algorithm’s evaluation value is less precise than that of the HP-SVM, especially the linear HP-SVM and HP-SVM Polynomial models. However, the HP-SVM RBF model’s accuracy rating is identical to that of the traditional SVM model.
The improvement of the PSO-SVM model, which has the finest gamma position and a value of 9.</span
... The method was applied to the interferometric coherence computed from C-band synthetic aperture radar images from Sentinel-1 [15]. Marhain et al. (2021) implemented a few artificial intelligence algorithms, such as support vector machine, boosted decision tree regression, random forest, and multivariate adaptive regression spline, to develop the best model algorithm in earthquake prediction. In their study, meteorological data were collected from several stations in Terengganu and processed for normalization, and the data were analyzed using algorithms, and the performance was evaluated [16]. ...
... Marhain et al. (2021) implemented a few artificial intelligence algorithms, such as support vector machine, boosted decision tree regression, random forest, and multivariate adaptive regression spline, to develop the best model algorithm in earthquake prediction. In their study, meteorological data were collected from several stations in Terengganu and processed for normalization, and the data were analyzed using algorithms, and the performance was evaluated [16]. Li et al. (2023) processed Sentinel-1 and GPS data to derive the complete surface displacement caused by the 2023 Turkey earthquake sequence [17]. ...
On 6 February 2023, at 1:17:34 UTC, a powerful Mw = 7.8 earthquake shook parts of Turkey and Syria. Investigating the behavior of different earthquake precursors around the time and location of this earthquake can facilitate the creation of an earthquake early warning system in the future. Total electron content (TEC) obtained from the measurements of GPS satellites is one of the ionospheric precursors, which in many cases has shown prominent anomalies before the occurrence of strong earthquakes. In this study, five classical and intelligent anomaly detection algorithms, including median, Kalman filter, artificial neural network (ANN)-multilayer perceptron (MLP), long short-term memory (LSTM), and ant colony optimization (ACO), have been used to detect seismo-anomalies in the time series of TEC changes in a period of about 4 months, from 1 November 2022 to 17 February 2023. All these algorithms show outstanding anomalies in the period of 10 days before the earthquake. The median method shows clear TEC anomalies in 1, 2 and, 3 days before the event. Since the behavior of the time series of a TEC parameter is complex and nonlinear, by implementing the Kalman filter method, pre-seismic anomalies were observed in 1, 2, 3, 5, and 10 days prior to the main shock. ANN as an intelligent-method-based machine learning also emphasizes the abnormal behavior of the TEC parameter in 1, 2, 3, 6, and 10 days before the earthquake. As a deep-learning-based predictor, LSTM indicates that the TEC value in the 10 days prior to the event has crossed the defined permissible limits. As an optimization algorithm, the ACO method shows behavior similar to Kalman filter and MLP algorithms by detecting anomalies 3, 7, and 10 days before the earthquake. In a previous paper, the author showed the findings of implementing a fuzzy inference system (FIS), indicating that the magnitude of the mentioned powerful earthquake could be predicted during about 9 to 1 day prior to the event. The results of this study also confirm the findings of another study. Therefore, considering that different lithosphere-atmosphere-ionosphere (LAI) precursors and different predictors show abnormal behavior in the time period before the occurrence of large earthquakes, the necessity of creating an earthquake early warning system based on intelligent monitoring of different precursors in earthquake-prone areas is emphasized.
... This algorithm can reduce the variance without increasing the bias. In addition, the accuracy of this model can be improved by increasing the CART (ntree) model ensemble 23 . ...
Earthquake is one of the natural disasters that have a big impact on society. Currently, there are many studies on earthquake detection. However, the vibrations that were detected by sensors were not only vibrations caused by the earthquake, but also other vibrations. Therefore, this study proposed an earthquake multi-classification detection with machine learning algorithms that can distinguish earthquake and non-earthquake, and vandalism vibration using acceleration seismic waves. In addition, velocity and displacement as integration products of acceleration have been considered additional features to improve the performances of machine learning algorithms. Several machine learning algorithms such as Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and Artificial Neural Network (ANN) have been used to develop the best algorithm for earthquake multi-classification detection. The results of this study indicate that the ANN algorithm is the best algorithm to distinguish between earthquake and non-earthquake, and vandalism vibrations. Moreover, it’s also more resistant to various input features. Furthermore, using velocity and displacement as additional features has been proven to increase the performance of every model.
... In the civil engineering community, researchers have been exploring the application of machine learning methods for estimating the seismic response, detecting/classifying damage and predicting earthquake events [6][7][8][9]. Sun et al. [10] summarizes the application of machine learning in structural design and performance assessment into four categories: (1) predicting structural response and performance, (2) models developed using data from physical experiments, (3) information retrieval using images and written text and (4) models developed using field reconnaissance and structural health monitoring data. ...
... Recall k (9) where k denotes the kth class. Finally, we look at the F-beta score which is a harmonic mean of precision and recall ...
A methodology is presented for performing dynamic seismic damage assessment of distributed infrastructure systems using graph neural networks and semi-supervised machine learning. To achieve this goal, a pre-event damage assessment is performed using either traditional fragility-based models or a machine learning classification algorithm trained on historical damage data. Then, a graph-neural network is implemented to perform semi-supervised learning and update the pre-event predictions as observations of actual damage become available during the post-earthquake inspection process. The methodology is demonstrated on the pipe network for the City of Napa, California water distribution system. A dataset of pipes damaged during the 2014 M 6.0 earthquake is used for validation purposes. A conventional neural network classification model is first trained on a portion of the observed pipe damage and used to perform the pre-event damage assessment i.e., supervised learning. Following the earthquake, a graph neural network model is employed to update the damage estimates given the information incrementally collected during the inspection process. The evaluation results show that the neural network supervised learning model provides better pre-event damage estimates than the existing repair rate-based model. Also, the graph neural network models can provide improved damage quantification given partial information collected during the inspection process.
Earthquakes are a phenomenon that is still a mystery in terms of predicting events, one of which is the magnitude. As technology develops, there are many algorithms that can be used as approaches in earthquake forecasting. In the context of magnitude forecasting, the application of GaussianNB, Random Forest, and SVM has the potential to reveal these patterns and relationships in the data. With the six main phases of this research, namely data acquisition, data pre-processing, feature selection, model training, forecast result evaluation, and performance analysis, this study is expected to contribute to the development of more accurate and effective earthquake forecasting methods. From these results we first obtain the result that the GaussianNB model has a relatively simple and fast method in training its model. However, the weakness lies in the assumption of a Gaussian distribution, which may not always suit the complex and diverse characteristics of earthquake data. Second, Random Forest, this method can increase accuracy and overcome the overfitting problem that occurs when forecasting magnitudes. In contrast to GaussianNB, it tends to result in models with greater complexity and requires more time to compute. The third option is SVM, which has both benefits and drawbacks that must be taken into account. The capacity of SVM to separate data that has both linear and nonlinear separation is one of its key advantages; nevertheless, the main drawback is that it is sensitive to hyperparameter adjustments.
