Using Histogram Extracted from Satelite Imagery and Convolutional Network to Predict GRDP in Java Region

Inequality is one of the problems faced by all countries in the world, including Indonesia. The data used to measure development inequality between regions mostly uses GRDP data. However, the GRDP data issued by BPS has a deficiency, it was released after the current year, and this figure is provisional. So, a new data source is needed that can be used to estimate the value of economic activity so that it can be used to measure the level of development inequality in a region. Night-time Light (NTL) satellite imagery data can be an alternative to see socio-economic activity in an area and has been shown to have a strong correlation with socio-economic activity. In this study, we used VIIRS NTL satellite imagery data and Dynamic World land cover data to estimate GRDP. Rather than using statistical features for each area of interest, we use features in the form of histograms extracted from NTL images and land cover images for each area of interest. By using a histogram, we don’t lose spatial information from satellite imagery. Then we proposed a deep learning method in the form of a one-dimensional convolutional neural network using the Huber loss function. This model obtained good accuracy with an R square value of 0.8549, beating the baseline method with two-dimensional convolutional networks. The use of Huber loss function can improve the performance of the model, which has a smaller total loss and have smoother gradient.