Land Cover Change Detection Using Deep Learning Technique
Land cover refers to the surface cover on the ground, whether it is vegetation, urban Infrastructure, water etc. Identifying, delineating and mapping land cover using Remote Sensing (RS) imagery is essential for many environmental and social applications. Recent advances in sensor technologies have witnessed a vast amount of very fine spatial resolution (sentinel-2) remotely sensed imagery being collected for every 5 days. The increase in availability of RS data has led to the development of new techniques for digital pattern classification. Recently, Deep learning (DL) models have emerged as a powerful solution to approach many machine learning (ML) problems. This is largely driven by the wave of excitement in deep learning to model the high-level abstractions through hierarchical feature representations without human-designed features or rules, which demonstrates great potential in identifying and characterizing LC patterns. Proposing Deep Convolutional Neural Networks method to detect the Land Cover on Agriculture by using Sentinel-2 Satellite Images to produce the final output. Experimental results show that our proposed Deep Convolutional Neural Networks method achieves high-level accuracy in detecting the Land Cover on Agriculture. This research made a significant contribution in Land Cover classification through deep learning-based innovations, and has great potential utility in a wide range of geospatial applications. Keywords - Land Cover, Sentinel-2, Deep Learning, Agriculture.