Predicting Damage to a Building During Earthquake

Earthquake is one of the most hazardous natural calamities. It occurs due to sudden shaking of ground which is caused by movement of seismic waves. The tectonic plates are always slowly moving, but they get stuck at their edges due to friction. When the stress on the edge overcomes the friction, there is an earthquake that releases energy in waves that travel through the earth's crust and cause the shaking that we feel. The problem statement of this project is determining the degree of damage that is done to buildings, thus when an earthquake occur we can help identify safe and unsafe buildings, thus avoiding death and injuries resulting from aftershocks. Leveraging the power of machine learning is one viable option that can potentially prevent massive loss of lives while simultaneously making rescue efforts easy and efficient. During this study, earthquake prediction was performed, by training different Machine Learning models on dataset collected from hackerearth website. During this research, machine learning algorithms like Random Forest, Neural Network and XGBoost Mechanism are separately applied and accuracies in the training and testing datasets were compared to pick out the best model.