Unpaired Cross-Domain Calibration of DMSP to VIIRS Nighttime Light Data Based on CUT Network

TL;DR

This paper introduces a novel cross-sensor calibration method using a CUT network to transform DMSP nighttime light data into VIIRS-like data, enabling consistent long-term urbanization monitoring despite sensor differences.

Contribution

It presents a new deep learning approach employing contrastive unpaired translation for cross-sensor calibration of nighttime light data, correcting DMSP defects and enhancing data consistency.

Findings

Generated VIIRS-like data shows high correlation with actual VIIRS data (R-squared > 0.87).

The method effectively corrects DMSP sensor defects and enables extended time-series analysis.

The approach improves long-term urbanization monitoring accuracy.

Abstract

Defense Meteorological Satellite Program (DMSP-OLS) and Suomi National Polar-orbiting Partnership (SNPP-VIIRS) nighttime light (NTL) data are vital for monitoring urbanization, yet sensor incompatibilities hinder long-term analysis. This study proposes a cross-sensor calibration method using Contrastive Unpaired Translation (CUT) network to transform DMSP data into VIIRS-like format, correcting DMSP defects. The method employs multilayer patch-wise contrastive learning to maximize mutual information between corresponding patches, preserving content consistency while learning cross-domain similarity. Utilizing 2012-2013 overlapping data for training, the network processes 1992-2013 DMSP imagery to generate enhanced VIIRS-style raster data. Validation results demonstrate that generated VIIRS-like data exhibits high consistency with actual VIIRS observations (R-squared greater than 0.87) and socioeconomic indicators. This approach effectively resolves cross-sensor data fusion issues and calibrates DMSP defects, providing reliable attempt for extended NTL time-series.