Identifying the Land Use Land Cover (LULC) changes in Pristina, (Kosova) using “Machine Learning" and “Remote Sensing" techniques

Session

Civil Engineering, Infrastructure and Environment

Description

In the last decade, the number of residents living in urban areas has increased rapidly, and in this way green surfaces are being cut more and more. Changes in land use categories, respectively the conversion of vegetated and green lands into urban areas, affects the changes of the Land Use and Land Cover (LULC). Nowadays, the environmental monitoring and assessment can be done easily from the satellites which provide access to the Earth Observations.

The present study is aimed to develop the assessment of LULC of Pristina Municipality in Kosova using Geospatial Technologies, precisely Remote Sensing (RS), Machine Learning (ML) and Geographic Information System (GIS). The Remote sensing products were used as input data, including multi-spectral Landsat 5 and Landsat 8 datasets in the raster format with 30m spatial resolution. The analysis were performed for four time series, including 1991, 2001, 2011 and 2021.

The data validation process was done through the matrix of confusion, as well as was done the data publishing on a web browser with the intention of visual comparison between time series raster thematic maps.

The present approach emphasis the great potential for analysis the Land Use and Land Cover (LULC), in order to meet the goal of the sustainable development in the capital of Kosova, Pristina.

Keywords:

Land Use Land Cover, Satellite Images, Machine Learning, Thematic Maps.

Proceedings Editor

Edmond Hajrizi

ISBN

978-9951-550-95-6

Location

UBT Lipjan, Kosovo

Start Date

28-10-2023 8:00 AM

End Date

29-10-2023 6:00 PM

DOI

10.33107/ubt-ic.2023.344

This document is currently not available here.

Share

COinS
 
Oct 28th, 8:00 AM Oct 29th, 6:00 PM

Identifying the Land Use Land Cover (LULC) changes in Pristina, (Kosova) using “Machine Learning" and “Remote Sensing" techniques

UBT Lipjan, Kosovo

In the last decade, the number of residents living in urban areas has increased rapidly, and in this way green surfaces are being cut more and more. Changes in land use categories, respectively the conversion of vegetated and green lands into urban areas, affects the changes of the Land Use and Land Cover (LULC). Nowadays, the environmental monitoring and assessment can be done easily from the satellites which provide access to the Earth Observations.

The present study is aimed to develop the assessment of LULC of Pristina Municipality in Kosova using Geospatial Technologies, precisely Remote Sensing (RS), Machine Learning (ML) and Geographic Information System (GIS). The Remote sensing products were used as input data, including multi-spectral Landsat 5 and Landsat 8 datasets in the raster format with 30m spatial resolution. The analysis were performed for four time series, including 1991, 2001, 2011 and 2021.

The data validation process was done through the matrix of confusion, as well as was done the data publishing on a web browser with the intention of visual comparison between time series raster thematic maps.

The present approach emphasis the great potential for analysis the Land Use and Land Cover (LULC), in order to meet the goal of the sustainable development in the capital of Kosova, Pristina.