The paper is intended to develop a model to predict the number of damaged buildings and casualties due to earthquake using ANN (Artificial Neural Network). This model is expected to be able to generate the type and amount of relief supplies required by those affected during the emergency phase. This research develops ANN using supervised learning paradigm, and backpropagation learning algorithm. The applied ANN network architecture is a multiple-layer system, with 1 (one) neuron used in both input and output layer, and 95 (ninety-five) neurons used in the hidden layer yielding 0.99971 as the greatest value of the correlation coefficient. The output variable in this study is the earthquake impact consisting of six variables. While the input variables (predictors) in this study consisting of eight variables. The model in this study utilizes 123 seismic datasets, divided into 100 data (80%) for the training process and 23 data (20%) for the testing process. This research adds to the existing research and demonstrates the application of ANN in predicting the numbers of damaged buildings and casualties. The model is useful in supporting and strengthening preparedness and emergency relief activities due to earthquake disaster.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.