Dryland cropping in different Land uses of Senegal using Sentinel-2 and hybrid ML method

Gumma, M K and Panjala, P and Teluguntla, P (2024) Dryland cropping in different Land uses of Senegal using Sentinel-2 and hybrid ML method. International Journal of Digital Earth, 17 (1). pp. 1-18. ISSN 1753-8947

PDF - Published Version Available under License Creative Commons Attribution Non-commercial. Download (2MB)

Abstract

In rainfed and dryland agricultural areas with smallholder farms (less than 2 ha), crop diversity is high due to farmers' decisions and local climatic conditions, leading to a complex spatial–temporal distribution of crops. Monitoring and mapping crops is crucial for food security and implementing agricultural support programs. This study aims to map crop types across Senegal using Sentinel-2 satellite imagery and the limited ground reference data available, which has been increasing recently. The study compares conventional supervised classification algorithms to unsupervised classification algorithms using high-resolution satellite imagery. Crop type classification for 2020 in Senegal employed supervised machine learning algorithms, including Classification and Regression Trees (CART), Random Forest (RF), and Support Vector Machine (SVM) on the Google Earth Engine (GEE) cloud platform, and the unsupervised Iso-clustering classification algorithm with Spectral Matching Techniques (SMTs). Due to limited ground data, supervised classifiers achieved 45-55% accuracy, whereas the unsupervised semi-automatic approach achieved over 75% accuracy. The study indicates that supervised classifiers' performance depends on ground data quantity, while SMT shows good performance even with limited ground data. This SMT approach is valuable for classifying crop types in dryland areas with smallholder farms and diverse cropping patterns.

Item Type:	Article
Divisions:	Global Research Program - Resilient Farm and Food Systems
CRP:	UNSPECIFIED
Uncontrolled Keywords:	Cropping pattern, sentinel-2, machine learning algorithms, spectral matching techniques, semi-arid, Crop type mapping
Subjects:	Others > GIS Techniques/Remote Sensing
Depositing User:	Mr Nagaraju T
Date Deposited:	27 Aug 2024 03:58
Last Modified:	27 Aug 2024 03:58
URI:	http://oar.icrisat.org/id/eprint/12793
Official URL:	https://www.tandfonline.com/doi/full/10.1080/17538...
Projects:	UNSPECIFIED
Funders:	International Crops Research Institute for the Semi-Arid Tropics (ICRISAT).
Acknowledgement:	This research was supported by the CGIAR Research Program on Climate Change, Agriculture and Food Security (CCAFS). We are very thankful to Mr Adam Oliphant, USGS for English editing and valuable suggestions. We would like to express our sincere gratitude to Dr Adama Sarr, CSE, Dr Mansour, AGRHYMET and Dr Aparna Phalke, NASA for their valuable initial review of the manuscript. We are grateful to Dr. Ramadjita Tabo, Dr Jat ML, Mr. Paul Bartel, from ICRISAT, Dr Bako Mamane, AGRHYMET and Mr Sibiry Traore, ICRISAT for their support and encouragement.
Links:	Google Scholar

View Statistics

Actions (login required)

View Item