Evaluating the performance of optical remote sensing data PlanetScope, Landsat 8 and Sentinel-2 for land use land cover classification case study Mendefera town

Temesghen E. Sereke; Vitaliy V. Bratkov

doi:10.30533/scidata-2024-15-08.

VAK Russia 2.3.1 UDC 528.7 CSCSTI 28.29 UDC 528.8

4 more Collapse

EVALUATING THE PERFORMANCE OF OPTICAL REMOTE SENSING DATA PLANETSCOPE, LANDSAT 8 AND SENTINEL-2 FOR LAND USE LAND COVER CLASSIFICATION CASE STUDY MENDEFERA TOWN Evaluating the performance of optical remote sensing data PlanetScope, Landsat 8 and Sentinel-2 for land use land cover classification case study Mendefera town

АА Аа

Published in Spatial Data: Science, Research and Technology · Volume 15, Issue 2, 2024 · Pages 84–98 · Rubric: System analysis, management and information processing

DOI: https://doi.org/10.30533/scidata-2024-15-08.

Received: 16.05.2024 Accepted: 20.06.2024 Published: 27.06.2024

Authors

Temesghen E. Sereke

Vitaliy V. Bratkov

Temesghen E. Sereke

Moscow State University of Geodesy and Cartography Moscow

Vitaliy V. Bratkov

Academic degree: doctor of geographical sciences

Science rang: professor

Moscow State University of Geodesy and Cartography head of the department · Department of Geography · Russian Federation · Moscow

ABSTRACT

Appropriate selection of optical remote sensing (RS) data with appropriate methods will help in improving the accuracy of land use land cover (LULC) classification. The study employed pixel-based supervised classification approach with Support Vector Machine (SVM) algorithm to assess the performance of three optical RS data namely PlanetScope, Landsat 8 and Sentinel-2 for classifying LULC in Mendefera town-Eritrea. Ancillary data such as DEM, NDVI and Slope were incorporated in combination with composite bands during the creation of training samples to improve classification accuracy. Post classification smoothing was employed for all the maps. Moreover, high spatial resolution aerial photos along with Google earth image were employed for accuracy assessment. Four LULC classes namely built up, natural vegetation, agricultural area and open area were created for the classification process. The overall accuracy was 89, 92 and 93 % for Landsat 8, PlanetScope and Sentinel-2 respectively; also, Kappa coefficient of 85, 88 and 90 % was found for Landsat 8, PlanetScope and Sentinel-2 respectively. The result showed us that Sentinel-2 perform comparatively higher than the other two for the study area.

KEYWORDS

land use / land cover (LULC), support vector machine (SVM), overall accuracy, Cohen’s kappa, Mendefera

1. Satir O, Berberoglu S. Land Use / Cover Classification Techniques Using Optical Remotely Sensed Data in Landscape Planning. Landscape Planning. Ózyavuz M (ed.). IntechOpen, 2012. DOIhttps://doi.org/10.5772/31351.

2. Esfandeh S, Danehkar A, Salmanmahiny A, et al. Climate Change Risk of Urban Growth and Land Use/Land Cover Conversion: An In-Depth Review of the Recent Research in Iran. Sustainability. 2022;14(1): 338. DOIhttps://doi.org/10.3390/su14010338.

3. Nasiri V, Deljouei A, Moradi F, et al. Land Use and Land Cover Mapping Using Sentinel-2, Landsat-8 Satellite Images, and Google Earth Engine: A Comparison of Two Composition Methods. Remote Sens. 2022;14(9): 1977. DOIhttps://doi.org/10.3390/rs14091977. 4. Liping C, Yujun S, Saeed S. Monitoring and predicting land use and land cover changes using remote sensing and GIS techniques — A case study of a hilly area, Jiangle, China. PLOS ONE. 2018;13(7): e0200493. DOIhttps://doi.org/10.1371/journal.pone.0200493.

4. Liping C., Yujun S., Saeed S. Monitoring and predicting land use and land cover changes using remote sensing and GIS techniques — A case study of a hilly area, Jiangle, China // PLOS ONE. 2018. Vol. 13. No. 7. P. e0200493. DOIhttps://doi.org/10.1371/journal. pone.0200493.

5. Zeshan MT, Mustafa MRU, Baig MF. Monitoring Land Use Changes and their Future Prospects using GIS and ANN_CA for Perak River Basin, Malaysia. Water. 2021;3(16): 2286. DOIhttps://doi.org/10.3390/w13162286.

6. Araya YH, Hergarten C. A comparison of pixel and object-based land cover classification: A case study of the Asmara region, Eritrea. WIT Transactions on the Built Environment. 2008;100: 233–243. DOIhttps://doi.org/10.2495/GEO080231.

7. Amini S, Saber M, Rabiei-Dastjerdi H, et al. Urban Land Use and Land Cover Change Analysis Using Random Forest Classification of Landsat Time Series. Remote Sens. 2002;14(11): 2654. DOIhttps://doi.org/10.3390/rs14112654.

8. Nivedita Priyadarshini K, Kumar M, Rahaman SA, et al. A Comparative Study of Advanced Land Use / Land Cover Classification Algorithms using Sentinel-2 Data. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences. 2018;XLII-5: 665–670. DOI:10.5194/ isprs-archives-XLII-5-665-2018.

9. Oo TK, Arunrat N, Ussawarujikulchai A. Comparing Four Machine Learning Algorithms for Land Cover Classification in Gold Mining: A Case Study of Kyaukpahto Gold Mine, Northern Myanmar. Sustainability. 2022;14(17): 10754. DOI:0.3390/su141710754.

10. Melgani F, Bruzzone L. Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing. 2004;42(8): 1778–1790. DOIhttps://doi.org/10.1109/TGRS.2004.831865.

11. Muslim AM, Razman N, Khalil I, et al. Evaluation of soft classification algorithm for sub-pixel mapping of the shoreline. 34th International Symposium on Remote Sensing of Environment. Sydney, 2011. Available from: https://www.isprs.org/proceedings/2011/isrse-34/211104015Final00287.pdf (Accessed 21 April 2024).

12. Hashim H, Latif Z, Adnan N. Land Use Land Cover Analysis with Pixel-Based Classification Approach. Indonesian Journal of Electrical Engineering and Computer Science. 2019;16(3): 1327–1333. DOIhttps://doi.org/10.11591/ijeecs.v16.i3.pp1327-1333.

13. Basheer S, Wang X, Farooque AA, et al. Comparison of Land Use Land Cover Classifiers Using Different Satellite Imagery and Machine Learning Techniques. Remote Sens. 2022;14(19): 4978. DOIhttps://doi.org/10.3390/rs14194978.

14. Valero Medina JA, Alzate Atehortúa BE. Comparison of maximum likelihood, support vector machines, and random forest techniques in satellite images classification. Tecnura. 2019;23(59): 13–26. DOIhttps://doi.org/10.14483/22487638.14826.

15. Nurlina N, Kadir S, Kurnain A, et al. Comparison of Maximum Likelihood and Support Vector Machine Classifiers for Land Use/Land Cover Mapping Using Multitemporal Imagery. Academic Research International. 2021;12(1): 1–13.

16. Sereke T, Bratkov V, Aristarkhova V. Vydelenie kategorij zemel’ s ispol’zovaniem algoritma Maximum Likelihood po snimkam Landsat 8 (na primere podzony Mendefera, Eritreya) [Allocation of Land Categories Using the Maximum Likelihood Algorithm Based on Landsat 8 Images (Using The Example Of The Mendefera Subzone, Eritrea)]. Monitoring. Science and Technologies. 2023;2(56): 68–74. (In Russian). DOIhttps://doi.org/10.25714/MNT.2023.56.009.

JATS XML

Editor-in-Chief, editorial board chair

EDITOR-IN-CHIEF Nadezhda Rostislavovna KAMYNINA PhD in Engineering, Doctor of Economics, Associate Professor; Rector of the Moscow State University of Geodesy and Cartography; Member of the Bologna Process Follow-up Group (BFUG); Executive Secretary of the Working Group of the Ministry of Science and Higher Education of the Russian Federation on the Bologna Process; Member of the Working Group on Spatial Data Infrastructure of the CIS Interstate Council on Geodesy, Cartography, Cadastre, and Remote Sensing, member of the Russian Federation's team of experts on higher education reform under the Erasmus+ program; Awarded the Medal of the Ministry of Education and Science of the Russian Federation "For Contribution to the Implementation of State Education Policy."

downloads

GOST

Sereke T., Bratkov V. V. Evaluating the performance of optical remote sensing data PlanetScope, Landsat 8 and Sentinel-2 for land use land cover classification case study Mendefera town // Spatial Data: Science, Research and Technology. 2024. no. 2. pp. 84-98. DOI: https://doi.org/10.30533/scidata-2024-15-08.. (Date of access 07.11.2026).

MLA

Temesghen E. Sereke, Bratkov V. V.. "Evaluating the performance of optical remote sensing data PlanetScope, Landsat 8 and Sentinel-2 for land use land cover classification case study Mendefera town." Spatial Data: Science, Research and Technology 15.2 (2024): 84-98. DOI: https://doi.org/10.30533/scidata-2024-15-08..

APA

Sereke T., Bratkov V. V. (2024). Evaluating the performance of optical remote sensing data PlanetScope, Landsat 8 and Sentinel-2 for land use land cover classification case study Mendefera town. Spatial Data: Science, Research and Technology, 15(2), 84-98. https://doi.org/10.30533/scidata-2024-15-08.

Chicago

Temesghen E. Sereke, Bratkov V. V.. "Evaluating the performance of optical remote sensing data PlanetScope, Landsat 8 and Sentinel-2 for land use land cover classification case study Mendefera town." Spatial Data: Science, Research and Technology 15, no. 2 (2024): 84-98. https://doi.org/10.30533/scidata-2024-15-08..

WIKI

{{cite journal | author = Sereke T., Bratkov V. V. | title = Evaluating the performance of optical remote sensing data PlanetScope, Landsat 8 and Sentinel-2 for land use land cover classification case study Mendefera town | journal = Spatial Data: Science, Research and Technology | year = 2024 | volume = 15 | issue = 2 | pages = 84-98 | doi = 10.30533/scidata-2024-15-08. }}

Copy

Export: BibTeX EndNote RefMan RusMARC

Confirmation