Vegetation type and land cover mapping in a semi-arid heterogeneous forested wetland of India: comparing image classification algorithms

Kundan Deval and P. K. Joshi ()
Additional contact information
Kundan Deval: Jawaharlal Nehru University
P. K. Joshi: Jawaharlal Nehru University

Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, 2022, vol. 24, issue 3, No 40, 3947-3966

Abstract: Abstract The present study evaluates and compares performance of three supervised classification algorithms namely Maximum Likelihood (MXL), Artificial Neural Network (ANN) and Support Vector Machine (SVM), using very high resolution WorldView-2 satellite imagery for vegetation type/land cover (VT/LC) mapping in Keoladeo National Park (KNP), India. We mapped 16 (8 gregarious VT and 8 LC) classes, and used Bootstrap (with 100 iterations) method for accuracy assessment. All three algorithms produced high overall accuracy (OA) (67–85%) and kappa (K) (65–83) values. Visual comparison of the predictions revealed that SVM (OA = 85.12% (K = 83.9) with 3.85% width of confidence interval) performed the best followed by ANN (69.72% (67.32) with 4.43%) and MXL (67.37% (65.22) with 4.33%). This research provides insight for selection of classification algorithm for detailed VT/LC mapping of wetland associated systems using very high resolution satellite data. The findings of this research are useful for environmental management, restoration and conservation planning of KNP, India. The database will be of high value for future development and sustainability issues in the park.

Keywords: Vegetation type; Land cover; Semi-arid wetland; Maximum Likelihood (MXL); Artificial Neural Network (ANN); Support Vector Machine (SVM); WorldView2 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10668-021-01596-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:endesu:v:24:y:2022:i:3:d:10.1007_s10668-021-01596-6

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/10668

DOI: 10.1007/s10668-021-01596-6

Access Statistics for this article

Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development is currently edited by Luc Hens

More articles in Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().