Please wait a minute...
 
Remote Sensing for Natural Resources    2022, Vol. 34 Issue (3) : 33-42     DOI: 10.6046/zrzyyg.2021259
|
An FY-4A/AGRI cloud detection model based on the naive Bayes algorithm
YAN Junjie(), GUO Xuexing(), QU Jianhua, HAN Min
Beijing Huayun Shinetek Science and Technology Co., Ltd., Beijing 100081, China
Download: PDF(6670 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

This study developed an automatic cloud detection method based on the naive Bayes algorithm for the cloud detection of the advanced geosynchronous radiation imager (AGRI) aboard the FY-4A satellite. In this method, the naive Bayes algorithm serves as the core structure, and appropriate infrared channels are selected as the parameters of the characteristic classifier according to the basic cloud detection principle of optical payload to ensure the consistency of cloud detection between day and night. After the classified training and construction for different surface types and different months, a cloud detection model based on the naive Bayes algorithm was finally established. Moreover, the classifier for FY-4A/AGRI data used in the method was established considering seven typical cloud detection characteristics and one characteristic based on the infrared composite images. As indicated by the learning tests and verification using the business cloud detection product of the National Satellite Meteorological Center (NSMC) in 2019, the classifier yielded a probability of detection (POD) greater than 98% for land, desert, shallow water, and deep sea, greater than 80% for snow cover, and greater than 80% for North and South poles. The comparison between the cloud detection results of this study and those obtained using the NSMC business system showed that the cloud detection results of this study had an average monthly POD of the whole year greater than 98%, a false alarm ratio (FAR) less than 5%, and all Kuiper’s skill scores (KSSs) greater than 90%.
Keywords FY-4A/AGRI      Naive Bayes Algorithm      cloud detection      POD     
ZTFLH:  TP79  
Corresponding Authors: GUO Xuexing     E-mail: yanjj@cma.gov.cn;guoxuexing@cnhyc.com
Issue Date: 21 September 2022
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Junjie YAN
Xuexing GUO
Jianhua QU
Min HAN
Cite this article:   
Junjie YAN,Xuexing GUO,Jianhua QU, et al. An FY-4A/AGRI cloud detection model based on the naive Bayes algorithm[J]. Remote Sensing for Natural Resources, 2022, 34(3): 33-42.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2021259     OR     https://www.gtzyyg.com/EN/Y2022/V34/I3/33
Fig.1  Methodology of naive bayes cloud detection algorithm
通道序号 中心波长/μm 特性描述
1 0.47 白天云、沙尘和气溶胶
2 0.65 白天云、沙尘、积雪等
3 0.825 白天云、气溶胶、植被、海洋特性检测
4 1.375 卷云
5 1.61 低云/雪 、水云/冰云
6 2.25 卷云、气溶胶
7 3.75H 火点高温
8 3.75L 低云/雾
9 6.25 高层云
10 7.1 中层云
11 8.5 云、沙尘
12 10.7 地球表面和云
13 12.0 云
14 13.5 中低层云
Tab.1  Channel setting of FY-4A AGRI
Fig.2  Classification of global land cover
Fig.3  Global monthly snow cover in 2019
Fig.4  Variation of pseudo 4 μm emissivity with solar zenith Angle
Fig.5  Color composite image of FY-4A/ AGRI GeoColor at 10: 00 UTC January 1, 2020
Fig.6  Data partition statistical chart
Fig.7  Modified graph of characteristic distribution and probability curve of cloud genus
月份 云 晴空 KSS
POD FAR POD FAR
1 98.2 5.6 89.4 3.5 87.6
2 98.1 7.4 88.5 3.1 86.6
3 97.8 6.9 87.2 4.2 85.0
4 90.5 6.3 88.7 2.8 87.3
5 98.5 6.4 90.3 2.3 88.9
6 98.9 4.8 89.2 2.7 88.1
7 98.7 5.0 90.3 2.6 89.0
8 98.8 5.2 89.0 2.6 87.8
9 90.4 7.0 88.0 2.8 86.4
10 98.4 7.8 87.6 2.6 86.0
11 98.0 6.7 90.1 3.0 88.1
12 98.2 6.8 89.4 2.9 87.6
均值 97.0 6.3 89.0 2.9 87.4
Tab.2  Cross comparison results of naive Bayes in different months with business CLM as truth value in 2019(%)
Fig.8  Comparison of UTC cloud detection results at 10: 00 UTC on January 1, 2020
Fig.9  T11 characteristic probability curve of each underlying surface in January and June
Fig.10  Comparison of results of cloud mask locally at UTC at 5:00 September 26, 2019
Fig.11  Model detection difference for different months
模型
月份		 类别 云 可能云 可能晴空 晴空 总计
1月 云 50.73 3.75 3.51 1.64 59.63
可能云 1.95 0.51 0.55 0.91 3.92
可能晴空 1.55 0.56 0.47 1.58 4.16
晴空 3.14 1.96 2.65 24.54 32.29
6月 云 46.89 3.83 3.3 8.55 62.57
可能云 1.73 0.35 0.35 1.23 3.66
可能晴空 1.59 0.35 0.34 1.35 3.63
晴空 7.16 2.25 3.19 17.54 30.14
总计 57.37 6.78 7.18 28.67 100
Tab.3  Model cloud detection confusion matrix statistics for different months(%)
[1] 林晔. 大气探测学教程[M]. 北京: 气象出版社, 1995.
[1] Lin Y. Course of atmospheric exploration[M]. Beijing: China Meteorological Press, 1995.
[2] 杨亦萍, 董晓刚, 戴聪明, 等. 利用MODIS数据对北极夏季卷云特性的研究[J]. 红外与激光工程, 2016, 45(4):30-37.
[2] Yang Y P, Dong X G, Dai C M, et al. Cirrus clouds properties in the arctic in summer based on MODIS data[J]. Infrared and Laser Engineering, 2016, 45(4):30-37.
[3] 秦永, 付仲良, 周凡, 等. 一种利用TM影像自动检测云层的方法[J]. 武汉大学学报(信息科学版), 2014, 39(2):234-238.
[3] Qin Y, Fu Z L, Zhou F, et al. A method of automatic cloud detection using TM image[J]. Geomatics and Information Science of Wuhan University, 2014, 39(2):234-238.
[4] 赵忠明, 朱重光. 遥感图象中薄云的去除方法[J]. 环境遥感, 1996, 11(3):195-199.
[4] Zhao Z M, Zhu C G. Approach to removing cloud cover from satellite imagery[J]. Remote Sensing of Environment, 1996, 11(3):195-199.
[5] Rossow W B, Schiffer R A. ISCCP cloud data products[J]. Bulletin of the American Meteorological Society, 1991, 72(1):2-20.
doi: 10.1175/1520-0477(1991)072<0002:ICDP>2.0.CO;2 url: http://journals.ametsoc.org/doi/10.1175/1520-0477(1991)072<0002:ICDP>2.0.CO;2
[6] Seze G, Rossow W B. Time-cumulated visible and infrared radiance histograms used as descriptors of surface and cloud variations[J]. International Journal of Remote Sensing, 1991, 12(5):877-920.
doi: 10.1080/01431169108929702 url: https://www.tandfonline.com/doi/full/10.1080/01431169108929702
[7] Rossow W B, Garder L C. Cloud detection using satellite measurements of infrared and visible radiances for ISCCP[J]. Journal of Climate, 1993, 6(12):2341-2369.
doi: 10.1175/1520-0442(1993)006<2341:CDUSMO>2.0.CO;2 url: http://journals.ametsoc.org/doi/10.1175/1520-0442(1993)006<2341:CDUSMO>2.0.CO;2
[8] 刘健. FY-2云检测中动态阈值提取技术改进方法研究[J]. 红外与毫米波学报, 2010, 29(4):288-292.
[8] Liu J. Improvement of dynamic threshold value extraction technic in FY-2 cloud detection[J]. Journal of Infrared and Millimeter Waves, 2010, 29(4):288-292.
[9] Saunders R W, Kriebel K T. An improved method for detecting clear sky and cloudy radiances from AVHRR data[J]. International Journal of Remote Sensing, 1988, 9(1):123-150.
doi: 10.1080/01431168808954841 url: https://www.tandfonline.com/doi/full/10.1080/01431168808954841
[10] Kriebel K T, Saunders R W, Gesell G. Optical properties of clouds derived from fully cloudy AVHRR pixels[J]. Beiträge zur Physik der freien Atmosphäre, 1989, 62:165-171.
[11] Gesell G. An algorithm for snow and ice detection using AVHRR data an extension to the APOLLO software package[J]. International Journal of Remote Sensing, 1989, 10:4-5,897-905.
[12] Stowe L L, McClain E P, Carey R, et al. Global distribution of cloud cover derived from NOAA/AVHRR operational satellite data[J]. Advances in Space Research, 1991, 11(3):51-54.
[13] Stowe L L, Vemury S K, Rao A V. AVHRR clear sky radiation data sets at NOAA/NESDIS[J]. Advance in Space Research, 1994, 14(1):113-116.
[14] Menzel W P, Wylie D P, Strabala K I. Seasonal and diurnal changes in cirrus clouds as seen in four years of observations with the VAS[J]. Journal of Applied Meteorology, 1992, 31(4):370-385.
doi: 10.1175/1520-0450(1992)031<0370:SADCIC>2.0.CO;2 url: http://journals.ametsoc.org/doi/10.1175/1520-0450(1992)031<0370:SADCIC>2.0.CO;2
[15] Wylie D P, Menzel W P, Woolf H M, et al. Four years of global cirrus cloud statistics using HIRS[J]. Journal of Climate, 1994, 7(12):1972-1986.
doi: 10.1175/1520-0442(1994)007<1972:FYOGCC>2.0.CO;2 url: http://journals.ametsoc.org/doi/10.1175/1520-0442(1994)007<1972:FYOGCC>2.0.CO;2
[16] Shan N, Zheng T Y, Wang Z S. High-speed and high-accuracy algorithm for cloud detection and its application[J]. Journal of Remote Sensing, 2009, 13(6):1138-1146.
[17] Goodman A H, Henderson-Sellers A. Cloud detection and analysis:A review of recent progress[J]. Atmospheric Research, 1988, 21(3-4):203-228.
doi: 10.1016/0169-8095(88)90027-0 url: https://linkinghub.elsevier.com/retrieve/pii/0169809588900270
[18] 韩成鸣, 李耀东, 史小康. 云分析预报方法研究进展[J]. 地球科学进展, 2015, 30(4):505-516.
doi: 10.1167/j.issn.1001-8166.2015.04.0505
[18] Han C M, Li Y D, Shi X K. Overview of researches on cloud analysis and prediction methods[J]. Advances in Earth Science, 2015, 30(4):505-516.
[19] 孙汝星, 范荣双. 基于支持向量机的多特征融合影像云检测[J]. 测绘与空间地理信息, 2018, 41(6):153-156,160.
[19] Sun R X, Fan R S. Multi-feature fusion image cloud detection based on SVM[J]. Geomatics and Spatial Information Technology, 2018, 41(6):153-156,160.
[20] 关峥嵘, 谭毅华, 田金文. 一种快速的遥感卫星图像云检测算法. 计算机与数字工程, 2019, 47(11):2808-2811.
[20] Guan Z R, Tan Y H, Tian J W. A fast cloud detection method in remote sensing satellite images[J]. Computer and Digital Engineering, 2019, 47(11):2808-2811.
[21] 瞿建华, 鄢俊洁, 薛娟, 等. 基于深度学习的FY3D/MERSI和EOS/MODIS云检测模型研究[J]. 气象与环境学报, 2019, 35(3):87-93.
[21] Qu J H, Yan J J, Xue J, et al. Research on the cloud detection model of FY3D /MERSI and EOS /MODIS based on deep learning[J]. Journal of Meteorology and Environment, 2019, 35(3):87-93.
[22] 董瑶海. 风云四号气象卫星及其应用展望[J]. 上海航天, 2016, 33(2):1-8.
[22] Dong Y H. Fy-4 meteorological satellite and its application prospect[J]. Aerospace Shanghai, 2016, 33(2):1-8.
[23] 陆风, 张晓虎, 陈博洋, 等. 风云四号气象卫星成像特性及其应用前景[J]. 海洋气象学报, 2017, 37(2):1-12.
[23] Lu F, Zhang X H, Chen B Y, et al. FY-4 geostationary meteorological satellite imaging characteristics and its application prospects[J]. Journal of Marine Meteorology, 2017, 37(2):1-12.
[24] 杨军. 气象卫星及其应用[M]. 北京: 气象出版社. 2012.
[24] Yang J. Meteorological satellites and their applications[M]. Beijing: China Meteorological Press, 2012.
[25] Ackerman S A, Smith W L, Revercomb H E, et al. The 27-28 October 1986 FIRE IFO cirrus case study:Spectral properties of cirrus clouds in the 8-12μm[J]. Monthly Weather Review, 1990, 118(11),2377-2388.
doi: 10.1175/1520-0493(1990)118<2377:TOFICC>2.0.CO;2 url: http://journals.ametsoc.org/doi/10.1175/1520-0493(1990)118<2377:TOFICC>2.0.CO;2
[26] Miller S D, Lindsey D T, Seaman C J, et al. GeoColor:A blending technique for satellite imagery[J]. Journal of Atmospheric and Oceanic Technology, 2020, 37(3):429-448.
doi: 10.1175/JTECH-D-19-0134.1 url: https://journals.ametsoc.org/view/journals/atot/37/3/JTECH-D-19-0134.1.xml
[1] WU Weichao, YE Fawang. Cloud detection of Sentinel-2 images for multiple backgrounds[J]. Remote Sensing for Natural Resources, 2023, 35(3): 124-133.
[2] LIU Guangjin, WANG Guanghui, BI Weihua, LIU Huijie, YANG Huachao. Cloud detection algorithm of remote sensing image based on DenseNet and attention mechanism[J]. Remote Sensing for Natural Resources, 2022, 34(2): 88-96.
[3] LI Xusheng, LIU Yufeng, CHEN Donghua, LIU Saisai, LI Hu. Cloud detection based on support vector machine with image features for GF-1 data[J]. Remote Sensing for Land & Resources, 2020, 32(3): 55-62.
[4] LIU Zihan, WU Yanlan. A review of cloud detection methods in remote sensing images[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(4): 6-7.
[5] XIA Lang, MAO Kebiao, SUN Zhiwen, MA Ying, ZHAO Fen. Method for detecting cloud at night from VIIRS data based on DNB[J]. REMOTE SENSING FOR LAND & RESOURCES, 2014, 26(3): 74-79.
[6] QIN Yan, DENG Ru-ru, HE Ying-qing, CHEN Lei, CHEN Qi-dong, XIONG Shou-ping. Algorithm for Removing Thick Clouds in TM Image Based on Spectral and Geometric Information[J]. REMOTE SENSING FOR LAND & RESOURCES, 2012, 24(4): 55-61.
[7] HAN Jie, YANG Lei-ku, LI Hui-fang, LIANG Hong-you, MA Xiao-hong, XIE Yu-juan. Research on Algorithm of Cloud Detection for HJ-1B Image Based on Dynamical Thresholding[J]. REMOTE SENSING FOR LAND & RESOURCES, 2012, 24(2): 12-18.
[8] HOU Yue, LIU Pei-Xun, CHEN Shun-Yun, LIU Shao-Feng. A STUDY OF NIGHT CLOUD DETECTION BASED ON MODIS IMAGE[J]. REMOTE SENSING FOR LAND & RESOURCES, 2008, 20(1): 34-37.
[9] HE Quan-Jun, CAO Jing, HUANG Jiang, WU Zhi-Jun. CLOUD DETECTION IN MODIS DATA BASED ON MULTI-SPECTRUM SYNTHESIS[J]. REMOTE SENSING FOR LAND & RESOURCES, 2006, 18(3): 19-22.
[10] JIANG Geng-ming, NIU Zheng, RUAN Wei-li, WANG Chang-yao . CLOUD-FREE COMPOSITION OF MODIS DATA AND ALGORITHM REALIZATION[J]. REMOTE SENSING FOR LAND & RESOURCES, 2004, 16(2): 11-15，79.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech