GOCI Sea Fog Detection Algorithm through Combination with Himawari-8

GOCI Sea Fog Detection Algorithm through Combination with Himawari-8
박명숙; 박영제; 김원국
KIOST Author(s)
Park, Myung Sook(박명숙)Park, Young Je(박영제)
Publication Year
Although marine fog is one of the most dangerous weather hazards that threaten coastal and marine areas, monitoring of marine fog is difficult because of the lack of in-situ observation data. Accordingly, satellite data has been considereda valuable information for marine fog monitoring. In this study, GOCI marine fog detection algorithm based on decision tree technique was developed through combination with Himawari-8. Fine visible channel measurement of GOCI and spatial pattern index were mainly used to detect marine fog in the daytime. In addition, cloud top height from Himawari-8 was used as a supplementary data because visible channel alone is not enough to remove clouds. The algorithm was developed using Decision Tree method because it is easy to understand and to interpret how can marine fog areas are decided. The resulting algorithm consists of main marine fog detection process and two post-processes for cloud removing and marine fog edge detection because it provided the most stable performance. Validation results show that marine fog can be well detected with this algorithm when there is no cloud above the marine fog. Hit rate and false alarm for the validation data are0.783 and 0.161, respectively.
Bibliographic Citation
PORSEC 2018, pp.73, 2018
Pan Ocean Remote Sensing Conference Association
Pan Ocean Remote Sensing Conference Association
Related Researcher
Research Interests

Satellite Remote Sensing,Machine Learning,Climate,원격탐사,머신러닝,기후

Files in This Item:
There are no files associated with this item.


Items in ScienceWatch@KIOST are protected by copyright, with all rights reserved, unless otherwise indicated.