摘要：Earthquakes, a type of inevitable natural disaster, is responsible for the highest average death toll per year compared to other types of a natural disaster. Even though it is inevitable, but it can be anticipated to minimize damage and casualties, such as predicting the earthquake‘s magnitude using a neural network. In this study, a backpropagation algorithm is used to train the multilayer neural network to weekly predict the average magnitude of earthquakes in grid-based locations in Indonesia. Based on the findings in this research, the neural network is able to predict the magnitude of earthquakes in grid-based locations across Indonesia with a minimum error rate of 0.094 in 34.475 seconds. This best result is achieved when the neural network is trained for 210 epochs, with 16 neurons used in the input and output layer, one hidden layer consisted of 5 neurons and a learning rate of 0.1. This result showed backpropagation has pretty good generalization capability in order to map the relations between variables when mathematical function is not explicitly available.
