Deep Convolutional neural network model for Land Classification using Satellite Images

Abstract

The significance of land image classification extends across diverse fields and disciplines, playing a crucial role in offering valuable insights into the Earth's surface. This intricate process entails the categorization of land cover types, including forests, urban areas, water bodies, and agricultural land, utilizing satellite or aerial imagery. Its relevance is evident in its applications spanning environmental monitoring, urban planning, agriculture, forestry, and disaster management. The ability of machine learning models to adapt and improve over time enhances the precision and reliability of land cover classifications, making them invaluable tools for decision-makers. This integration not only expedites the classification process but also opens up possibilities for real-time monitoring and adaptive management strategies, contributing to more effective and sustainable resource utilization. In this work, a Convolution neural network is used for land classification using satellite images.