Spatial Analysis of Land Use Land Cover Dynamics in the Madurai District Using Sentinel-2 Data and Supervised Learning Algorithms

Abstract. LULC, or Land Use and Land Cover, refers to the classification and description of different types of land and its usage patterns, including urban areas, forests, agricultural land, etc. In remote sensing, satellite imagery for LULC mapping is becoming more widespread. Numerous studies examine various approaches to improve mapping efficiency and accuracy, highlighting the significance of various data sources, machine learning algorithms, and categorization techniques. This study employs machine learning classifiers, namely Random Forest (RF), Support Vector Machine (SVM), Gradient Boosted Trees (GTB), Classification and Regression Trees (CART), and K-Nearest Neighbors (KNN) for land use and land cover (LULC) classification of Madurai district utilizing Google Earth Engine. The findings reveal the impressive performance of Random Forest, boasting an overall accuracy of 99.01 percent coupled with a commendable Kappa coefficient of 98.68. Conversely. However, amidst these commendable achievements, it’s noteworthy to highlight the nuanced variations observed between the accuracy of training and validation sets. This discrepancy is attributed to the intrinsic intricacies of the learning processes inherent within the algorithms, underscoring the nuanced nature of algorithmic methodologies and their implications on accuracy assessment within spatial analysis frameworks. The generated land use and land cover (LULC) map allows for a comparison between the ground truth data and the surveys conducted to assess issues such as water scarcity and the drying of natural and man-made water bodies.