The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLVIII-4/W1-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-4/W1-2022, 237–243, 2022
https://doi.org/10.5194/isprs-archives-XLVIII-4-W1-2022-237-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-4/W1-2022, 237–243, 2022
https://doi.org/10.5194/isprs-archives-XLVIII-4-W1-2022-237-2022
 
05 Aug 2022
05 Aug 2022

ANALYSIS OF FREE AND OPEN LAND COVER MAPS FOR AGRICULTURAL LAND USE PLANNING AT LOCAL LEVEL

S. Jovanović1, T. Predić1, and G. Bratić2 S. Jovanović et al.
  • 1PI Agricultural Institute of Republic of Srpska, Department of Agroecology Knjaza Miloša 17,78000 Banja Luka, Bosnia and Herzegovina
  • 2Politecnico di Milano, Department of Civil and Environmental Engineering, Via Gaetano Previati 1/c, 23900 Lecco, Italy

Keywords: Agricultural land protection, Land Cover Land Use, CORINE LC, QGIS, Python

Abstract. According to the Law on Agricultural Land of the Republic of Srpska, municipalities and cities are obliged to prepare a planning document “Groundwork for Agricultural Land Protection, Use and Restructuring (The groundwork)”. Information related to the current state of land cover and land cover use are essential for the groundwork. Such layer was created for the municipality Laktaši in Bosnia and Herzegovina by digitization of land cover features from orthophoto imagery. Even if digitization provides highly reliable data, it is also time-consuming activity, and therefore the evaluation of Corine Land Cover (CLC) for the municipality Laktaši was performed to determine if it is accurate enough to sustain the groundwork for other municipalities. In this paper, using free open source programs, a comparison of two sets of data representing land cover was performed: manually vectorized data with orthophoto images of LC/LU and CLC. Using QGIS, the two datasets were harmonized, and then the error matrix and accuracy indexes were computed by using Python. The obtained results show that the overall accuracy of CLC with respect to LC/LU reference is 70%, but the class related to agricultural areas are overestimated in some locations and underestimated in other locations. After analyzing the results, it was concluded that the CLC in the studied area is not a sufficiently precise GIS basis for agricultural land use planning at the local level. However, it can be a good starting point for making of LC/LU, which would significantly shorten the time of its creating.