| INCREASING THE SPATIAL ACCURACY OF THE LAND USE MAP USING FUSION OF OPTICAL AND RADAR IMAGES OF SENTINEL AND GOOGLE EARTH ENGINE |
| Paper ID : 1225-GEOSPATIAL (R6) |
| Authors: |
|
Sara Attarchi *1, Jafar Jafarzadeh2 1Department of Remote sensing and GIS, Faculty of Geography, University of Tehran 2, Faculty of Geography, University of Tehran, Tehran, I.R. Iran |
| Abstract: |
| Nowadays, accurate and real-time land use and land cover (LULC) maps are important to provide information for dynamic monitoring, planning and land management. New opportunities arise in large-scale LULC mapping with the advent of cloud computing systems, time series feature extraction techniques, and machine learning classifiers. The main objective of this research is to produce a land use map with a spatial resolution of 10 meters by combining Sentinel-1 radar images and Sentinel-2 optical images. NDVI, NDBI and NDWI were also used to increase classification accuracy. Eleven LULC classes were found in the study area. The classification was done based on the decision tree method. Validation points were randomly collected over the study area to evaluate the classification accuracy and the final map. The processing was done in Google Earth Engine cloud computing system. The results of the comparison of the ground control points and the final classified map showed that the classification accuracy was around 94%. The obtained results from the current research can be optimally used in urban planning and crisis management. |
| Keywords: |
| Land Use, Sentinel, Radar, Optics, Decision Tree, Google Earth Engine |
| Status : Paper Accepted (Poster Presentation) |
