Extraction of Urban Quality of Life Indicators Using Remote Sensing and Machine Learning: The Case of Al Ain City, United Arab Emirates (UAE)

Urban quality of life (UQoL) study is very important for many applications such as services distribution, urban planning, and socioeconomic analysis. The objective this to create an index map Al Ain city in the United Arab Emirates (UAE). research aligns with Nations Sustainable Development Goals number ten (reduce inequalities) eleven (sustainable cities communities). In study, remote sensing images GIS vector datasets were used extract biophysical infrastructure facility indicators. indicators are normalized difference vegetation (NDVI), water (NDWI), modified (MNDWI), soil adjusted (SAVI), enhanced impervious surfaces (ENDISI), built-up (NDBI), land surface temperature (LST), slope, use cover (LULC). addition, distances main roads, parks, schools, hospitals obtained. Additional variables namely green area build-up bare ratio extracted from LULC map. Machine learning was classify satellite generate Random Forest (RF) found best machine classifier study. overall classification Kappa hat accuracy 95.3 0.92, respectively. Both integrated using principal component analysis (PCA). PCA identified four components that explain 75% variance among factors interpreted effect LULC, facility, ecological, slope. Finally, assigned weights based on percentage they explained developed UQoL Overall, result showed greenness has a greater spatial pattern city. could be value policy makers planning departments.