Ensuring Earthquake-Proof Development in a Swiftly Developing Region through Neural Network Modeling of Earthquakes Using Nonlinear Spatial Variables

Northern Pakistan, the center of major construction projects due to commencement China Pakistan Economic Corridor, is among most earthquake-prone regions globally owing its tectonic settings. The area has experienced several devastating earthquakes in past, and these pose a severe threat infrastructure life. Several researchers have previously utilized advanced tools such as Machine Learning (ML) Deep (DL) algorithms for earthquake predictions. This technological advancement helps with innovation, instance, by designing earthquake-proof buildings. However, previous studies focused mainly on temporal rather than spatial variables. present study examines impact variables assess performance different ML DL predicting magnitude short-term future North Pakistan. Two methods, namely Modular Neural Network (MNN) Shallow (SNN), two Recurrent (RNN) (DNN) algorithms, were used meet research objectives. techniques was assessed using statistical measures, including accuracy, information gain analysis, sensitivity, specificity, positive negative predictive values. These metrics evaluate new variable, Fault Density (FD), standard seismic proposed models examined patterns classes earthquakes. accuracy training data ranged from 73% 89%, testing 64% 85%. analysis outcomes demonstrated an improved when additional variable FD low high magnitudes, whereas less moderate-magnitude DNN, SNN models, performed relatively better other models. results provide valuable insights about influence variable. outcome adds existing pool knowledge prediction, fostering safer more secure regional development plan involving innovative construction.