Sustainable Development of Prediction Model for Seismic Hazard Analysis

Abstract

Hazard mitigation has become a crucial and important activity to eliminate the risk to life and property and can lead to a path of sustainable development. Liquefaction is one of the most disastrous phenomena that arise due to earthquakes and has always been a major concern due to the damages and devastation it causes to the environment, structures and the human life it takes. The present study proposes the use of machine learning techniques based on the soil data to evaluate liquefaction potential which uses less data to predict broader area, thus minimizing the resource consumption. Artificial neural network (ANN) model has been developed for predicting liquefaction susceptibility. The significance of fine content on liquefaction has also been considered while developing the ANN model. The results confirm that the use of artificial intelligence for hazard mitigation can save us from incurring massive damages caused due to hazards like liquefaction, and due to it cost efficiency and quick predictions, it may be categorized as a sustainable method for evaluating and predicting risk against any seismic hazards.