Forest Cover Type Prediction

The traditional techniques of classifying the type of various forest cover based on field surveys and manual mapping can be time-consuming and labor-intensive. The purpose of this research was to help the Forest Department in predicting the forest cover types and decreasing the time taken for predicting using Machine learning and to improve the results with minor changes in the algorithm. The approach that had been chosen was to use the cartographic variables and find the algorithm which was best suited for the modern and digital world where data needed to be acquired as quickly as possible and accurately. The comparison of accuracy of the algorithms like K-Nearest Neighbors (KNN), Linear Support Vector Classifier (Linear SVC), Gaussian Naive Bayes (Gaussian NB), Logistic Regression, Random Forest Classifier (RFC), Gradient Boosting Classifier and Decision Tree Classifier had been done. The accuracy of Random Forest and KNN were highest and taken into consideration for further analysis.