Spatial data mining is the data collected from physical real-life locations containing map data, image data, and graph data. Spatial data mining focuses on extracting patterns and information from geographical datasets. In this paper, we have presented earthquake significance classification using Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), Support Vector Machine (SVM), K-Nearest Neighbors (K-NNs), Gaussian Naive Bayes, Neural Networks (NNs), AdaBoost, and Bagging. Further, the performances of those algorithms were evaluated using F1-score, Recall, Precision, and Accuracy. From this analysis, it is observed that RF and Bagging performing better as compared to other techniques.