EUVIMEDEUVIMED entdecken
Crossref

Land Use Land Cover Study of Sentinel-2A and Landsat-5 Images Using NDVI and Supervised Classification Techniques

Dr. Aziz Makandar, Shilpa Kaman

Computational Intelligence and Machine Learning · 2021

DOI: 10.36647/ciml/02.02.a003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Intelligence and Machine Learning, 2021. Verfasst von Dr. Aziz Makandar und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Land Use Land Cover (LULC) change monitoring plays very significant role in planning, policy making, management programs required for development activities at regional levels of any country. This study is an attempt to monitor LULC change of Vijayapura taluk, Karnataka, India for the period of 25 years from 1995 to 2021 using Remote Sensing (RS) and Geographic Information System (GIS). Satellite Images from Sentinel-2A MSI (Multispectral Imager), Landsat-5TM (Thematic Mapper) are used to generate LULC maps. Vegetation Change in the study area is computed using Normalized Difference Vegetation Index (NDVI) and results show that vegetation rate is increased from 0.6% in 1995 to 27.5% in 2021. Supervised Classification is carried out by using Maximum Likelihood Classification (MLC). 5 major classes considered for classification are namely: Waterbodies, Cropland/Vegetation, Fallow Land, Built-up Area and Barren Land. ArcGIS software tool is used for implementing the proposed study. Google Earth Pro used for accuracy assessment which is done by taking ground truth values for corresponding Classifications. Results show that the proposed system is able to achieve 88.16% of overall accuracy. Keyword : Land Use Land Cover, Supervised Classification, Remote Sensing, Maximum Likelihood Classification, Normalized Difference Vegetation Index, High Resolution, Multitemporal, Satellite Images.

Zitieren

APA

Makandar, D. A., & Kaman, S. (2021). Land Use Land Cover Study of Sentinel-2A and Landsat-5 Images Using NDVI and Supervised Classification Techniques. Computational Intelligence and Machine Learning. https://doi.org/10.36647/ciml/02.02.a003

Vancouver

Makandar DA, Kaman S. Land Use Land Cover Study of Sentinel-2A and Landsat-5 Images Using NDVI and Supervised Classification Techniques. Computational Intelligence and Machine Learning. 2021. doi:10.36647/ciml/02.02.a003

BibTeX
@article{Makandar2021,
  author = {Makandar, Dr. Aziz and Kaman, Shilpa},
  title = {Land Use Land Cover Study of Sentinel-2A and Landsat-5 Images Using NDVI and Supervised Classification Techniques},
  journal = {Computational Intelligence and Machine Learning},
  year = {2021},
  doi = {10.36647/ciml/02.02.a003}
}
Kostenlos starten →