Accurate and comprehensive urban poverty monitoring is undoubtedly essential to support the urban poverty alleviation targets in many developing countries. The currently available urban poverty monitoring in Indonesia is, however, primarily depends on the expensive and resource-demanding Indonesia National Socio-Economic Survey (SUSENAS). Despite its high-quality poverty statistics, such national-scale survey collection methods are indispensably labor and cost expensive to scale. Alternative data is essentially required to be explored for supporting government poverty data in order to increase the data granularity. In this study, we aim to develop the spatially granular poverty index (SGPI) consisting of multisource remote sensing satellite imageries and big data sources. With 1 km resolution, the SGPI is composed of nighttime light (NTL), normalized difference built-up index (NDBI), carbon monoxide (CO) and nitrogen dioxide (NO2) pollution levels, education and healthcare Point of Interest (POI) data, as alternative economic activity and poverty proxy indicators. Three different approaches of the equal-weighted sum method, the Pearson correlation coefficient method weighted method, and PCA weighted method are compared and evaluated to combine different indicators. Our result shows that the SGPI built in the scope of Jakarta Metropolitan Area (JMA) by using the equal weighted sum with Yeo-Johnson transformation (EWS-YJ) has the highest correlation with official poverty data which is 0.954. Based on visual identifications through high-resolution satellite imagery, the areas with a relatively high SGPI value are densely populated, and vice versa. Our findings suggest that multi-source remote sensing and geospatial big data integration are promising alternative approaches for granular urban poverty mapping based on spatial characteristics.
