EARTHQUAKE IMPACT ASSESSMENT USING NAÃVE BAYESIAN AND LONG SHORT TERM MEMORY MODELS

This research work highlights the use of Deep learning Techniques to assess the impact of earthquakes in a place. This research concentrates on studying the impacts of earthquakes on various situations using the Deep Neural Network and the output of the prediction in terms of the impact will be used to appropriately alert the people in earthquake prone areas, so that the damage or loss of resources could be reduced. We used the historical information from various sources with data on earthquakes which have happened as well as the satellite remote sensing data. The data is used to train a deep neural network, after preprocessing of data, and adjusting the weight connections. The model was tested and the desired classes in terms of damage level, whether it is high, moderate or low were predicted. Using the NaA¯ve Bayesian model we achieved an accuracy of 97% and using LSTM we got 98% accuracy.