A comparative analysis of machine learning algorithms for land use and land cover classification using google earth engine platform

Abstract

This study evaluates different machine learning algorithms for land use and land cover classification using Sentinel-2 Level-1C data with 10-meter spatial resolution. The algorithms include Random Forest (RF), Classification and Regression Trees (CART), Support Vector Machines (SVM), Naive Bayes (NB), and Gradient Boosting (GTB). The classification was performed on the Google Earth Engine (GEE) platform. Results highlight variations in land cover classification among algorithms, with RF and CART identifying cropland as dominant, SVM indicating fallow land presence, NB revealing significant forest cover, and GTB emphasizing cropland importance. Accuracy assessment was performed to evaluate the performance of the algorithms, considering metrics such as producer accuracy, consumer accuracy, overall accuracy, and Kappa coefficient. SVM demonstrates the highest overall accuracy and agreement with reference data. The study contributes insights for land management and planning, and GEE proves valuable for LULC classification.