,
Research Scholar, Department of Electronics and Communication Engineering, Karunya Institute of Technology and Sciences , Coimbatore, Tamil Nadu , India
,
Associate Professor, Department of Electronics and Communication Engineering, SRM TRP Engineering College , Trichy, Tamil Nadu , India
,
Assistant Professor, Department of Electronics and Communication Engineering, Karunya institute of technology and science , Coimbatore, Tamil Nadu , India
,
Associate Professor, Department of Electronics and Communication Engineering, Presidency University , Bangalore, Karnataka , India
Research Scholar, Department of Information Technology, University of the Cumberlands , Williamsburg, Kentucky , United States
High-precision crop type mapping is fundamental for agricultural monitoring, food security assessment, and sustainable land management. Recent breakthroughs in Earth observation and machine learning (ML) have greatly enhanced the potential for satellite data to capture crop phenology, spatial variability, and temporal variations. This paper conducts a systematic review of over 30 satellite-based crop type mapping studies, covering satellite data sources, multi-sensor fusion techniques, and classification models. The quantitative meta-analysis of the reviewed studies indicates that the fusion of optical and synthetic aperture radar (SAR) data can enhance overall classification accuracy by 0.2% to 0.6%, especially in areas with high spatial variability and frequent cloud cover. In addition, ensemble learning and deep learning models have been found to outperform conventional classifiers, with substantial improvements in both accuracy and robustness for various agro-ecological zones. Pixel-level fusion methods have been found to be the most effective means of enhancing crop type discrimination and area estimation.
This is an open access article distributed under the Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
0
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.