Published Paper Details:

Remote sensing, a technique involves the use of satellites to gather data from Earth's surface has application across various domains. Over the past few decades, satellite imagery has been useful in large-scale land classification and monitoring agricultural activities. Agriculture monitoring has become very important to ensure food production and security. To maximize production and efficiently manage food supplies, accurate monitoring of agricultural activities on a larger scale is crucial. The Normalized Difference Vegetation Index, or NDVI, is a broadly utilized remote sensing indicator for agricultural management. This study addresses limitations in traditional monitoring methods by integrating Sentinel-2 satellite data with Convolutional Neural Networks (CNNs). The methodology involves preprocessing of satellite imagery and conversion to NDVI images, followed by classification technique to categorize into non-vegetated, stressed, and healthy vegetation classes. This project attempts to address the fundamental problems in traditional agricultural monitoring methods in order to provide farmers and other agricultural stakeholders a convenient and efficient alternative.