Generation of monthly VIIRS nighttime lights time-series (1992–2013) images using deep learning (cGAN) technique

Abstract

Satellite-based nighttime lights (NTL) are often used as indicators of the socioeconomic dynamics of an area. The Earth Observation Group at Colorado School of Mines provides monthly NTL products from the Day Night Band (DNB) sensor on board the Visible and Infrared Imaging Suite (VIIRS) satellite (April 2012 onwards) and from Operational Linescan System (OLS) sensor onboard the Defense Meteorological Satellite Program (DMSP) satellites (April 1992–December 2013). VIIRS-DNB (hereinafter referred to as VIIRS) and DMSP-OLS (hereinafter referred to as DMSP) NTL images have 15-arc second and 30-arc second spatial resolution, respectively. In the current study, an attempt has been made to generate synthetic (fine-resolution) monthly VIIRS-like products of 1992–2012 from (coarse-resolution) DMSP products, using a deep learning-based image translation network. Initially, the defects of the 216 monthly DMSP images (1992–2013) were corrected to remove geometric errors, background noise, and radiometric errors. Correction on monthly VIIRS imagery to remove background noise and ephemeral lights was done by thresholding. Improved monthly NTL images of DMSP-OLS and VIIRS from April 2012–December 2013 were used in a conditional generative adversarial network (cGAN) along with the land cover, as auxiliary input, to generate VIIRS-like monthly imagery from 1992 to 2012. The modelled imagery was aggregated annually, which showed an R2 of 0.94 with the results of other annual-scale VIIRS-like imagery products (2000–2020) over India; R2 of 0.85 w.r.t GDP; and R2 of 0.69 w.r.t population. Regression analysis of the generated VIIRS-like products with the actual VIIRS images for the years 2012 and 2013 over India indicated a good approximation with an R2 of 0.64 and 0.67 respectively, while the spatial density relation depicted an under-estimation of the brightness values by the model at extremely high radiance values with an R2 of 0.56 and 0.53 respectively. Qualitative analysis is also performed on both country and State scales. Visual analysis over 1992–2013 confirms a gradual increase in the brightness of the nighttime lights indicating that the cGAN model images closely represent the actual pattern followed by the nighttime lights. Finally, synthetically generated monthly VIIRS-like products are delivered to the research community which will be useful for studying the changes in socio-economic dynamics over time.