Earthquake Probability Assessment for the Indian Subcontinent Using Deep Learning

Abstract

Earthquake prediction is a popular topic among earth scientists; however, this task is challenging and exhibits uncertainty therefore, probability assessment is indispensable in the current period. During the last decades, the volume of seismic data has increased exponentially, adding scalability issues to probability assessment models. Several machine learning methods, such as deep learning, have been applied to large-scale images, video, and text processing; however, they have been rarely utilized in earthquake probability assessment. Therefore, the present research leveraged advances in deep learning techniques to generate scalable earthquake probability mapping. To achieve this objective, this research used a convolutional neural network (CNN). Nine indicators, namely, proximity to faults, fault density, lithology with an amplification factor value, slope angle, elevation, magnitude density, epicenter density, distance from the epicenter, and peak ground acceleration (PGA) density, served as inputs. Meanwhile, 0 and 1 were used as outputs corresponding to non-earthquake and earthquake parameters, respectively. The proposed classification model was tested at the country level on datasets gathered to update the probability map for the Indian subcontinent using statistical measures, such as overall accuracy (OA), F1 score, recall, and precision. The OA values of the model based on the training and testing datasets were 96% and 92%, respectively. The proposed model also achieved precision, recall, and F1 score values of 0.88, 0.99, and 0.93, respectively, for the positive (earthquake) class based on the testing dataset. The model predicted two classes and observed very-high (712,375 km2) and high probability (591,240.5 km2) areas consisting of 19.8% and 16.43% of the abovementioned zones, respectively. Results indicated that the proposed model is superior to the traditional methods for earthquake probability assessment in terms of accuracy. Aside from facilitating the prediction of the pixel values for probability assessment, the proposed model can also help urban-planners and disaster managers make appropriate decisions regarding future plans and earthquake management.

Deep Learning for Earthquake Disaster Assessment: Objects, Data, Models, Stages, Challenges, and Opportunities

“…Earthquake catalogues often include time of occurrence, location of epicentre, depth of source, magnitude, latitude, longitude, and intensity of the epicentre. Jena et al [78] used the distributed earthquake catalogue and data from USGS to train the model, predict classifications, and generate the probability map in the study. Jena et al [79] collected a complete catalogue of historic events for probability mapping.…”

Towards personalised early prediction of Intra-Operative Hypotension following anesthesia using Deep Learning and phenotypic heterogeneity

“…Supervised Machine Learning methods provide an opportunity to exploit large amounts of sequential data and are therefore increasingly utilized in training and analysing physiological timeseries for prediction. Deep learning (DL) methods also represent an important alternative to assist clinicians as they can learn more complex relationships of the input data without the need of human interpretation (22,23,20,24,25). In the field of anaesthesiology, the development of algorithms predictive of intra-operative physiological alterations is showing encouraging results, often outperforming traditional modelling (26,27,28).…”

“…It was utilised for the real-time prediction of a IOH at 5, 10 and 15 minutes in advance using combined biosignal waveforms (acquired using one-point SBP/DBP, photoplethysmography, capnography and electrocardiography) and may provide a more reliable prediction for patients than the more invasive arterial catheterisation. Another study (22) aimed at predicting hypotensive events occurring between tracheal intubation and incision. To do so, the authors trained several machine learning models with data recorded from the start of anesthesia induction to right before intubation.…”

A Deep Learning-Based Electromagnetic Signal for Earthquake Magnitude Prediction

“…Ratiranjan Jena studied a CNN network to assess the probability of earthquakes in the Indian subcontinent [ 16 ]. In the same year, Ratiranjan researched another CNN model to assess the magnitude and damage of earthquakes in Indonesia [ 17 ]. Subsequently, J.…”