Digital Mapping of Land Cover Changes Using the Fusion of SAR and MSI Satellite Data

Guste Metrikaityte, Jurate Suziedelyte Visockiene and Kestutis Papsys
Additional contact information
Guste Metrikaityte: Department of Geodesy and Cadastre, Vilnius Gediminas Technical University, Sauletekio av. 11, LT-10223 Vilnius, Lithuania
Jurate Suziedelyte Visockiene: Department of Geodesy and Cadastre, Vilnius Gediminas Technical University, Sauletekio av. 11, LT-10223 Vilnius, Lithuania
Kestutis Papsys: Department of Cartography and Geoinformatics, Vilnius University, M. K. Ciurlionio 21/27, LT-03101 Vilnius, Lithuania

Land, 2022, vol. 11, issue 7, 1-20

Abstract: The aim of this article is to choose the most appropriate method for identifying and managing land cover changes over time. These processes intensify due to human activities such as agriculture, urbanisation and deforestation. The study is based in the remote sensing field. The authors used four different methods of satellite image segmentation with different data: Synthetic Aperture Radar (SAR) Sentinel-1 data, Multispectral Imagery (MSI) Sentinel-2 images and a fusion of these data. The images were preprocessed under segmentation by special algorithms and the European Space Agency Sentinel Application Platform (ESA SNAP) toolbox. The analysis was performed in the western part of Lithuania, which is characterised by diverse land use. The techniques applied during the study were: the coherence of two SAR images; the method when SAR and MSI images are segmented separately and the results of segmentation are fused; the method when SAR and MSI data are fused before land cover segmentation; and an upgraded method of SAR and MSI data fusion by adding additional formulas and index images. The 2018 and 2019 results obtained for SAR image segmentation differ from the MSI segmentation results. Urban areas are poorly identified because of the similarity of spectre signatures, where urban areas overlap with classes such as nonvegetation and/or sandy territories. Therefore, it is necessary to include the field surveys in the calculations in order to improve the reliability and accuracy of the results. The authors are of the opinion that the calculation of the additional indexes may help to enhance the visibility of vegetation and urban area classes. These indexes, calculated based on two or more different bands of multispectral images, would help to improve the accuracy of the segmentation results.

Keywords: image fusion; SAR; MSI RGB; segmentation; land cover changes; LULC; coherence (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/11/7/1023/pdf (application/pdf)
https://www.mdpi.com/2073-445X/11/7/1023/ (text/html)

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:gam:jlands:v:11:y:2022:i:7:p:1023-:d:857004

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().