Object-based image analysis and machine learning for mapping cashew plantations in Ariyalur district, Tamil Nadu

An object-based image analysis (OBIA) approach provides a comprehensive method for delineating homogeneous segments based on spectral characteristics, geometry, and spatial imagery structures. The present study utilizes OBIA and machine learning (ML) techniques to map cashew plantations in Ariyalur district of Tamil Nadu, India. Sentinel-2 Multi-Spectral Instrument (MSI) imagery, acquired during the 2023 Kharif season, was employed as the primary data source due to its high spatial and spectral resolution, suitable for detailed land cover mapping. The OBIA methodology involved multiresolution segmentation using eCognition software to delineate homogeneous image objects based on spectral, spatial, and contextual characteristics. Machine learning algorithms, including Random Forest (RF), Support Vector Machine (SVM), and Decision Tree (DT), were evaluated to improve classification accuracy. The SVM demonstrated the best superior performance, achieving an overall accuracy of 92.1% and a kappa coefficient of 0.85. The results underscore the effectiveness of machine learning techniques in conjunction with object-based image analysis (OBIA) for precise cashew plantation mapping while contributing to improved land use/land cover mapping, agricultural resource management, and sustainable development within the region.