A New Application of Unsupervised Learning to Nighttime Sea Fog Detection

• Published in: Asia-Pacific journal of atmospheric sciences Vol. 54; no. 4; pp. 527 - 544
• Main Authors: Shin, Daegeun, Kim, Jae-Hwan
• Format: Journal Article
• Language: English
• Published: Seoul Korean Meteorological Society 01.11.2018; Springer Nature B.V; 한국기상학회
• Subjects: Algorithms; Atmospheric Sciences; Brightness temperature; Climate models; Climatic analysis; Climatology; Communication; Data; Detection; Earth and Environmental Science; Earth Sciences; Fog; Geophysics/Geodesy; Lidar; Low clouds; Meteorological satellites; Methods; Night-time; Original; Original Article; Probability theory; Satellites; Sea fog; Sea ice; Sea ice temperatures; Sea surface; Sea surface temperature; Stratus clouds; Surface radiation temperature; Surface temperature; Temperature; Temperature differences; Vertical profiles; 대기과학; Sea fog detection; CALIPSO; COMS; EM algorithm; Unsupervised learning
• ISSN: 1976-7633; 1976-7951; 1976-7951
• DOI: 10.1007/s13143-018-0050-y

This paper presents a nighttime sea fog detection algorithm incorporating unsupervised learning technique. The algorithm is based on data sets that combine brightness temperatures from the 3.7 μm and 10.8 μm channels of the meteorological imager (MI) onboard the Communication, Ocean and Meteorological Satellite (COMS), with sea surface temperature from the Operational Sea Surface Temperature and Sea Ice Analysis (OSTIA). Previous algorithms generally employed threshold values including the brightness temperature difference between the near infrared and infrared. The threshold values were previously determined from climatological analysis or model simulation. Although this method using predetermined thresholds is very simple and effective in detecting low cloud, it has difficulty in distinguishing fog from stratus because they share similar characteristics of particle size and altitude. In order to improve this, the unsupervised learning approach, which allows a more effective interpretation from the insufficient information, has been utilized. The unsupervised learning method employed in this paper is the expectation–maximization (EM) algorithm that is widely used in incomplete data problems. It identifies distinguishing features of the data by organizing and optimizing the data. This allows for the application of optimal threshold values for fog detection by considering the characteristics of a specific domain. The algorithm has been evaluated using the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) vertical profile products, which showed promising results within a local domain with probability of detection (POD) of 0.753 and critical success index (CSI) of 0.477, respectively.