Datasets for Satellite Remote Sensing in Agriculture: An Overview and Analysis

Accurate classification of agricultural land cover using satellite remote sensing is essential for monitoring crop health, predicting yields, and optimizing farming practices. This paper examines key datasets such as the Landsat series (Landsat 7–9), Sentinel-1, Sentinel-2, and MODIS, among others, assessing their suitability for these purposes. It compares critical features like sensor types, spectral bands, and spatial/temporal resolutions, swath width to highlight their advantages and limitations. The paper also discusses important pre-processing techniques, including radiometric and atmospheric corrections, stressing their role in preparing satellite images for analysis. Additionally, it reviews widely used processing software tools like ENVI, Google Earth Engine, and SNAP, detailing their functionalities. The goal is to provide researchers and practitioners with valuable insights into utilizing satellite imagery for agricultural land cover classification by comparing these datasets and tools.