A Machine-Learning-Based Study on All-Day Cloud Classification Using Himawari-8 Infrared Data

被引:3
作者
Fu, Yashuai [1 ,2 ]
Mi, Xiaofei [3 ]
Han, Zhihua [1 ,2 ]
Zhang, Wenhao [1 ,2 ]
Liu, Qiyue [1 ,2 ]
Gu, Xingfa [1 ,3 ]
Yu, Tao [1 ,3 ]
Anton, Manuel
Gultepe, Ismail
机构
[1] North China Inst Aerosp Engn, Sch Remote Sensing & Informat Engn, Langfang 065000, Peoples R China
[2] Hebei Collaborat Innovat Ctr Aerosp Remote Sensing, Langfang 065000, Peoples R China
[3] Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China
关键词
all-day cloud classification; XGBoost; CPR/CALIOP; Himawari-8; AInfraredCCM; A-TRAIN; ALGORITHM;
D O I
10.3390/rs15245630
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Clouds are diverse and complex, making accurate cloud type identification vital in improving the accuracy of weather forecasting and the effectiveness of climate monitoring. However, current cloud classification research has largely focused on daytime data. The lack of visible light data at night presents challenges in characterizing nocturnal cloud attributes, leading to difficulties in achieving continuous all-day cloud classification results. This study proposed an all-day infrared cloud classification model (AInfraredCCM) based on XGBoost. Initially, the latitude/longitude, 10 infrared channels, and 5 brightness temperature differences of the Himawari-8 satellite were selected as input features. Then, 1,314,275 samples were collected from the Himawari-8 full-disk data and cloud classification was conducted using the CPR/CALIOP merged cloud type product as training data. The key cloud types included cirrus, deep convective, altostratus, altocumulus, nimbostratus, stratocumulus, stratus, and cumulus. The cloud classification model achieved an overall accuracy of 86.22%, along with precision, recall, and F1-score values of 0.88, 0.84, and 0.86, respectively. The practicality of this model was validated across all-day temporal, daytime/nighttime, and seasonal scenarios. The results showed that the AInfraredCCM consistently performed well across various time periods and seasons, confirming its temporal applicability. In conclusion, this study presents an all-day cloud classification approach to obtain comprehensive cloud information for continuous weather monitoring, ultimately enhancing weather prediction accuracy and climate monitoring.
引用
收藏
页数:25
相关论文
共 47 条
  • [1] Astafurov VG, 2021, RUSS METEOROL HYDRO+, V46, P839, DOI [10.52002/0130-2906-2021-12-57-70, 10.3103/S1068373921120050]
  • [2] Phenomenological Description of Tropical Clouds Using CloudSat Cloud Classification
    Behrangi, Ali
    Kubar, Terry
    Lambrigtsen, Bjorn
    [J]. MONTHLY WEATHER REVIEW, 2012, 140 (10) : 3235 - 3249
  • [3] Cloud properties and radiative effects of the Asian summer monsoon derived from A-Train data
    Berry, Elizabeth
    Mace, Gerald G.
    [J]. JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES, 2014, 119 (15) : 9492 - 9508
  • [4] An Introduction to Himawari-8/9-Japan's New-Generation Geostationary Meteorological Satellites
    Bessho, Kotaro
    Date, Kenji
    Hayashi, Masahiro
    Ikeda, Akio
    Imai, Takahito
    Inoue, Hidekazu
    Kumagai, Yukihiro
    Miyakawa, Takuya
    Murata, Hidehiko
    Ohno, Tomoo
    Okuyama, Arata
    Oyama, Ryo
    Sasaki, Yukio
    Shimazu, Yoshio
    Shimoji, Kazuki
    Sumida, Yasuhiko
    Suzuki, Masuo
    Taniguchi, Hidetaka
    Tsuchiyama, Hiroaki
    Uesawa, Daisaku
    Yokota, Hironobu
    Yoshida, Ryo
    [J]. JOURNAL OF THE METEOROLOGICAL SOCIETY OF JAPAN, 2016, 94 (02) : 151 - 183
  • [5] Cai KY, 2017, INT CONF SOFTW ENG, P874, DOI 10.1109/ICSESS.2017.8343049
  • [6] A novel approach to fog/low stratus detection using Meteosat 8 data
    Cermak, Jan
    Bendix, Joerg
    [J]. ATMOSPHERIC RESEARCH, 2008, 87 (3-4) : 279 - 292
  • [7] The Cloud Top Distribution and Diurnal Variation of Clouds Over East Asia: Preliminary Results From Advanced Himawari Imager
    Chen, Dandan
    Guo, Jianping
    Wang, Hongqing
    Li, Jian
    Min, Min
    Zhao, Wenhui
    Yao, Dan
    [J]. JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES, 2018, 123 (07) : 3724 - 3739
  • [8] Construction of Nighttime Cloud Layer Height and Classification of Cloud Types
    Chen, Sijie
    Cheng, Chonghui
    Zhang, Xingying
    Su, Lin
    Tong, Bowen
    Dong, Changzhe
    Wang, Fu
    Chen, Binglong
    Chen, Weibiao
    Liu, Dong
    [J]. REMOTE SENSING, 2020, 12 (04)
  • [9] [范霄 Fan Xiao], 2023, [遥感技术与应用, Remote Sensing Technology and Application], V38, P156
  • [10] Deep Neural Network Cloud-Type Classification (DeepCTC) Model and Its Application in Evaluating PERSIANN-CCS
    Gorooh, Vesta Afzali
    Kalia, Subodh
    Phu Nguyen
    Hsu, Kuo-lin
    Sorooshian, Soroosh
    Ganguly, Sangram
    Nemani, Ramakrishna R.
    [J]. REMOTE SENSING, 2020, 12 (02)