CALIPSO-Guided Dual-Branch Network With Spectral–Spatial Attention for Himawari-8 Sea Fog Detection
Open Access
- 11 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 11027-11041
Abstract
Sea fog poses a critical challenge to maritime safety. Current sea fog detection methods based on geostationary satellite data predominantly rely on the visual interpretation of samples, yet conventional visual interpretation methods are prone to subjective biases in sample labeling. This study proposes a novel dual-branch Patch-CNN architecture using Himawari-8 satellite data, which addresses labeling uncertainty through CALIPSO-derived vertical aerosol profiles that unambiguously discriminate sea fog from low-level clouds. Training samples were exclusively constructed from CALIPSO vertical feature masks (VFM), ensuring spectral reliability by eliminating cloud-fog ambiguity. The framework integrates three distinctive features: (1) Spatial-context preservation via patch-based inputs to encapsulate neighborhood characteristics around sample points; (2) multispectral feature extraction through a dual-branch architecture that separately captures characteristics from visible-near infrared and infrared channels; and (3) adaptive feature fusion employing attention-weighted feature integration to enhance discriminative representation. Evaluated across the Yellow-Bohai Sea region, the model achieved 89.74% overall accuracy and 82.98% detection probability, outperforming conventional machine learning and deep learning benchmarks. In validation testing with meteorological station data, the proposed method exhibited stronger robustness than traditional machine learning and deep learning methods, with 87 true positives, while case studies using CALIOP VFM and ICOADS visibility data found that the present network could accurately identify the foggy area. This work establishes a satellite-based fog detection network, particularly suited for complex marine environments where fog-cloud spectral overlap challenges traditional methods.Keywords
Funding Information
- Shandong Province Natural Science Foundation, China (ZR2022MD043)
- National Key Research and Development Program of China (2017YFC1405600)
- Fundamental Research Funds for the Central Universities, China (24CX02030A)
This publication has 33 references indexed in Scilit:
- Satellite detection of sea fog and low clouds in the Arctic in the daytime during the summer through multiple sources of infrared remote sensingGlobal and Planetary Change, 2024
- Automatic impervious surface mapping in subtropical China via a terrain-guided gated fusion networkInternational Journal of Applied Earth Observation and Geoinformation, 2024
- Exploring spatial non-stationarity of near-miss ship collisions from AIS data under the influence of sea fog using geographically weighted regression: A case study in the Bohai Sea, ChinaActa Oceanologica Sinica, 2023
- Daytime sea fog monitoring using multimodal self-supervised learning with band attention mechanismNeural Computing and Applications, 2022
- Combining Sentinel-1 and Sentinel-2 Satellite Image Time Series for land cover mapping via a multi-source deep learning architectureISPRS Journal of Photogrammetry and Remote Sensing, 2019
- Development of a daytime cloud and haze detection algorithm for Himawari‐8 satellite measurements over central and eastern ChinaJournal of Geophysical Research: Atmospheres, 2017
- A method of detecting sea fogs using CALIOP data and its application to improve MODIS-based sea fog detectionJournal of Quantitative Spectroscopy and Radiative Transfer, 2015
- A Comprehensive Dynamic Threshold Algorithm for Daytime Sea Fog Retrieval over the Chinese Adjacent SeasPure and Applied Geophysics, 2013
- Fog Research: A Review of Past Achievements and Future PerspectivesPure and Applied Geophysics, 2007
- Radiative properties of terrestrial clouds at visible and infra‐red thermal window wavelengthsQuarterly Journal of the Royal Meteorological Society, 1973