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

Aug 4, 2026

Upload by Levi

An object-based image analysis (OBIA) workflow enables delineation of homogeneous image segments using spectral traits, geometry, and spatial structures. This study applies OBIA together with machine learning to map cashew plantations in Ariyalur district, Tamil Nadu, using Sentinel-2 MSI imagery from the 2023 Kharif season. Multiresolution segmentation in eCognition generates objects based on spectral, spatial, and contextual characteristics. Random Forest, Support Vector Machine, and Decision Tree classifiers are assessed to enhance classification accuracy, with SVM delivering the top overall accuracy (92.1%) and kappa (0.85).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Abstract

Introduction

Cashew production relevance and mapping need

Remote sensing and geospatial approaches

From pixel-based to OBIA methods

PLANT SCIENCE TODAY ISSN 2348-1900 (online) Vol 11(sp4): 01–09 [https://doi.org/10.14719/pst.5165](https://doi.org/10.14719/pst.5165) HORIZON e-Publishing Group RESEARCH ARTICLE Object-based image analysis and machine learning for mapping cashew plantations inAriyalur district, Tamil Nadu Karthikkumar Alaguvel1, Kumaraperumal Ramalingam1*, Pazhanivelan Sellaperumal2, Muthumanickam Dhanaraju1, Ragunath Kaliyaperumal2, Selvakumar2 & Nivasraj Moorthi1 1Department of Remote Sensing and Geographic information system, Tamil Nadu Agricultural University, Coimbatore 641 003, Tamil Nadu, India 2Centre for Water and Geospatial Studies, Tamil Nadu Agricultural University, Coimbatore 641 003, Tamil Nadu, India *Email: [kumaraperumal.r@tnau.ac.in](kumaraperumal.r@tnau.ac.in) OPEN ACCESS ARTICLE HISTORY Received: 20 September 2024 Accepted: 14 October 2024 Available online Version 1.0 : 23 December 2024 Additional information Peer review: Publisher thanks Sectional Editor and the other anonymous reviewers for their contribution to the peer review of this work. Reprints & permissions information is available at [https://horizonepublishing.com/](https://horizonepublishing.com/)[ ](https://horizonepublishing.com/)[journals/index.php/PST/open_access_policy](journals/index.php/PST/open_access_policy) [Publisher](Publisher)’s Note: Horizon e-Publishing Group remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Indexing: Plant Science Today, published by Horizon e-Publishing Group, is covered by Scopus, Web of Science, BIOSIS Previews, Clarivate Analytics, NAAS, UGC Care, etc See [https://horizonepublishing.com/journals/](https://horizonepublishing.com/journals/)[ ](https://horizonepublishing.com/journals/)[index.php/PST/indexing_abstracting](index.php/PST/indexing_abstracting) [Copyright](Copyright:)[:](Copyright:) © [The Author](The Author)([s](s))[. This is](. This is) an openaccess article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution and reproduction in any medium, provided the original author and source are credited ([https://creativecommons.org/licenses/](https://creativecommons.org/licenses/)[ ](https://creativecommons.org/licenses/)[by/4.0/](by/4.0/)) CITE THIS ARTICLE Alaguvel K, Ramalingam K, Sellaperumal P, Dhanaraju M, Kaliyaperumal R, Selvakumar, Moorthi N. Object-based image analysis and machine learning for mapping cashew plantations inAriyalur district, Tamil Nadu. Plant Science Today.2024;11(sp4):01-09. [https://doi.org/10.14719/pst.5165](https://doi.org/10.14719/pst.5165) Abstract 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 develo

FAQs

What data source is used to map cashew plantations in the study?

The study uses Sentinel-2 Multi-Spectral Instrument (MSI) imagery acquired during the 2023 Kharif season.

How does the OBIA part of the workflow work here?

It performs multiresolution segmentation in eCognition to delineate homogeneous image objects based on spectral, spatial, and contextual characteristics.

Which machine learning model performs best and what are its results?

Support Vector Machine (SVM) performs best, achieving 92.1% overall accuracy and a kappa coefficient of 0.85.

Aug 4, 2026

Upload by Levi