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

2026-03-17

AI Summary

This study addresses the challenge of integrating DMSP and VIIRS nighttime light data for long-term urbanization monitoring, hindered by sensor discrepancies that prevent direct fusion. To overcome this limitation without requiring paired observations, the authors propose a novel unpaired cross-sensor calibration framework based on the CUT (Contrastive Unpaired Translation) network, incorporating a multi-layer block-wise contrastive learning strategy coupled with mutual information maximization. This approach effectively mitigates DMSP’s saturation and low-resolution issues by translating its outputs into a VIIRS-like style. The resulting calibrated data exhibit strong consistency with actual VIIRS observations (R² > 0.87) and demonstrate significant correlations with socioeconomic indicators, thereby enabling high-quality reconstruction of long-term nighttime light time series.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Web data integration and cleaning
• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• cross-sensor calibration
• nighttime light data
• DMSP-OLS
• VIIRS
• sensor incompatibility

Innovation

• Contrastive Unpaired Translation
• cross-sensor calibration
• nighttime light data
• mutual information
• unpaired image translation