Journal article
Retrieval of nighttime oceanic liquid cloud optical and microphysical parameters from VIIRS observations: a physics-informed machine learning approach
Remote sensing of environment, Vol.347(15 December 2026), 115684
09/24/2026
DOI: 10.1016/j.rse.2026.115684
Abstract
Accurate retrieval of nighttime water cloud optical and microphysical properties, including cloud optical thickness (COT) and cloud effective radius (CER), remains a long-standing challenge. This study develops a physics-informed machine-learning framework, UI-Cloud (Unified Illumination Cloud Microphysics Retrieval Framework), to retrieve nighttime oceanic liquid-cloud COT and CER from observations of the Visible Infrared Imaging Radiometer Suite (VIIRS). The framework unifies solar and lunar illumination regimes by training on daytime data and applying physically constrained corrections to nighttime radiance inputs. The VIIRS Day/Night Band (DNB) top-of-atmosphere reflectance serves as a bridging variable linking daytime and nighttime conditions. Lookup tables generated using the UNified Linearized Vector Radiative Transfer Model (UNL-VRTM) quantify day–night brightness temperature (BT) offsets and enable dynamic correction of residual solar contributions in the 4.065 μm thermal emissive band (M13).
The daytime model demonstrates strong agreement with VIIRS standard retrievals (R = 0.98). Direct application to nighttime data results in CER overestimation, whereas incorporation of the UNL-VRTM-based M13 BT correction yields nighttime global mean values (COT = 16.0; CER = 16.8 μm) that are consistent with daytime references (14.6 and 15.9 μm). Validation against liquid water path (LWP) retrievals from the Advanced Microwave Scanning Radiometer 2 (AMSR2) demonstrates RMSE reduction from 261.9 to 147.9 g m−2 and bias decrease from 180% to 62%. Retrieval accuracy is high for Moon Illumination Fraction (MIF) above 70% and remains robust down to approximately 50%, enabling the UI-Cloud framework to extend diurnal cloud optical and microphysical observations beyond daytime-only conditions into lunar-illuminated nights.
•Unified ML framework retrieves nighttime and daytime cloud microphysics from VIIRS.•VIIRS Day/Night Band enables cloud retrieval under lunar illumination.•Physics-informed correction reduces 4 μm solar residual bias.•Nighttime COT and CER validated using AMSR2 liquid water path.•Extends global cloud microphysical observations into moonlit nights.
Details
- Title: Subtitle
- Retrieval of nighttime oceanic liquid cloud optical and microphysical parameters from VIIRS observations: a physics-informed machine learning approach
- Creators
- Ying-Chieh Chen - Department of Chemical and Biochemical Engineering, The University of Iowa, Iowa City, IA, USAMeng Zhou - Department of Chemical and Biochemical Engineering, The University of Iowa, Iowa City, IA, USAJun Wang - Department of Chemical and Biochemical Engineering, The University of Iowa, Iowa City, IA, USAXi Chen - University of IowaJing Zeng - University of IowaYongxiang Hu - Langley Research Center
- Resource Type
- Journal article
- Publication Details
- Remote sensing of environment, Vol.347(15 December 2026), 115684
- DOI
- 10.1016/j.rse.2026.115684
- ISSN
- 0034-4257
- eISSN
- 1879-0704
- Publisher
- Elsevier Inc
- Grant note
- NASA's Terra, Aqua, and SNPP Program: 80NNSC21L1976 NASA's Modeling and Analysis Program (MAP): 80NSSC21K1494 NASA TEMPO-GOES/R Program: 80NSSC25K0221
This work was supported in part by NASA's Terra, Aqua, and SNPP Program under Award 80NNSC21L1976; in part by NASA's Modeling and Analysis Program (MAP) under Award 80NSSC21K1494; and in part by the NASA TEMPO-GOES/R Program under Award 80NSSC25K0221. The authors gratefully acknowledge the NASA LAADS DAAC and the NASA GMAO for providing the VIIRS and MERRA-2 datasets used in this study. The authors also thank Kerry G. Meyer (NASA Goddard Space Flight Center) for helpful guidance and documentation regarding the VIIRS cloud products. The authors also sincerely thank NASA's Distributed Active Archive Centers (DAACs) for providing the support to access the data used in this study.-
- Language
- English
- Date published
- 09/24/2026
- Academic Unit
- Electrical and Computer Engineering; Iowa Technology Institute; Physics and Astronomy; Chemical and Biochemical Engineering
- Record Identifier
- 9985240904002771
Metrics
1 Record Views