Generation and Classification of Land Use and Land Cover Datasets in the Indian States: A Comparative Study of Machine Learning and Deep Learning Models

Abstract

Land use and land cover (LULC) analysis is highly significant for various environmental and social applications. As remote sensing (RS) data becomes more accessible, LULC benchmark datasets have emerged as powerful tools for complex image classification tasks. These datasets are used to test state-of-the-art artificial intelligence models, particularly convolutional neural networks (CNNs), which have demonstrated remarkable effectiveness in such tasks. Nonetheless, there are existing limitations, one of which is the scarcity of benchmark datasets from diverse settings, including those specifically pertaining to the Indian scenario. This study addresses these challenges by generating medium-sized benchmark LULC datasets from two Indian states and evaluating state-of-the-art CNN models alongside traditional ML models. The evaluation focuses on achieving high accuracy in LULC classification, specifically on the generated patches of LULC classes. The dataset comprises 4000 labelled images derived from Sentinel-2 satellite imagery, encompassing three visible spectral bands and four distinct LULC classes. Through quantitative experimental comparison, the study demonstrates that ML models outperform CNN models, exhibiting superior performance across various LULC classes with unique characteristics. Notably, using a traditional ML model, the proposed novel dataset achieves an impressive overall classification accuracy of 96.57%. This study contributes by introducing a standardized benchmark dataset and highlighting the comparative performance of deep CNNs and traditional ML models in the field of LULC classification.