Computer Science ›› 2022, Vol. 49 ›› Issue (6A): 675-679.doi: 10.11896/jsjkx.210300177

• Interdiscipline & Application • Previous Articles     Next Articles

Study on Cloud Classification Method of Satellite Cloud Images Based on CNN-LSTM

WANG Shan1, XU Chu-yi1, SHI Chun-xiang2, ZHANG Ying3   

  1. 1 College of Information Engineering,East China Jiaotong University,Nanchang 330013,China
    2 National Meteorological Information Center,China Meteorological Adminstration,Beijing 100081,China
    3 Jiangxi Provincial Meteorological Observatory,Jiangxi Meteorological Bureau,Nanchang 330000,China
  • Online:2022-06-10 Published:2022-06-08
  • About author:WANG Shan,born in 1981,Ph.D,professor.His main research interests include image processing and artificial intelligence.
    XU Chu-yi,born in 1995,postgraduate.Her main research interests include meteorological data processing and so on.
  • Supported by:
    National Natural Science Foundation of China(41965007) and Jiangxi Outstanding Young Talents Subsidy Project(20192BCB23029).

Abstract: The classification of satellite cloud images has always been one of the research hotspots in the field of meteorology.But there are some problems,such as the same cloud type has different spectral features,different cloud types have the same spectral features,and mainly use the spectral features and ignore spatial features.To solve the above problems,this paper proposes a cloud classification method of satellite cloud image based on CNN-LSTM,which makes full use of spectral information and spatial information to improve the accuracy of cloud classification.Firstly,the spectral features are screened based on the physical characteristics of the cloud,and the square neighborhood of the point cloud is used as the spatial information.Then,the convolutional neural network(CNN) is used to automatically extract the spatial features,which solves the problem of difficult classification with spectral feature alone.Finally,on this basis,combined with the spatial local difference features extracted by the long short-term memory(LSTM) network,it provides multi-view features for the classification of satellite cloud images,and solves the problem of misjudgment caused by the similarity of cloud spatial structure.Experimental results show that the overall classification accuracy of the proposed method for satellite cloud images reaches 93.4%,which is 2.7% higher than that of the single CNN method.

Key words: Cloud classification, CNN-LSTM, Convolution neural network, Long short-term memory network, Spectral features

CLC Number: 

  • TP183
[1] ZHOU W,LI W B.Classification of Cloud Using GMS-5 Infrared Data[J].Journal of Peking University(Natural Science Edition),2003,39(1):83-90.
[2] WANG J G,ZHANG R,HONG M,et al.Synthetical optimization clustering method for classifying cloud from satellite images[J].Journal of PLA University of Science and Technology(Na-tural Science Edition),2005,6(6):585-590.
[3] ZHANG Y,YANG H T,YUAN C H.A Survey of RemoteSensing Image Classification Methods[J].Journal of Sichuan Ordnance,2018,241(8):114-118.
[4] SHENK W E,HOLUB R J,NEFF R A.A Multispectral Cloud Type Identification Method Developed for Tropical Ocean Areas with Nimbus-3 MRIR Measurements[J].Monthly Weather Review,1976,104(3):284.
[5] ZHAO Y,ZHANG L,LI P,et al.Classification of High Spatial Resolution Imagery Using Improved Gaussian Markov Random-Field-Based Texture Features[J].IEEE Transactions on Geo-science and Remote Sensing,2007,45(5):1458-1468.
[6] ZHANG T,TANG H.A Comprehensive Evaluation of Approaches for Built-Up Area Extraction from Landsat OLI Images Using Massive Samples[J].Remote Sensing,2018,11(1):2.
[7] KOFFLER R,DECOTIIS A G,RAO P K.A Procedure for Estimating Cloud Amount and Height From Satellite Infrared Radia-tion Data[J].Monthly Weather Review,2009,101(3):240-243.
[8] KEY J R,MASLANIK J A,SCHWEIGER A J.Classification of merged AVHRR and SMMR Arctic data with neural networks[J].Photogrammetric Engineering and Remote Sensing,1989,55(9):1331.
[9] SHI C X,QU J H.Cloud Classification for NOAA-AVHRR byUsing a neural network[J].ACTA Meteorologica Sinica,2002,60(2):250-255.
[10] CAI K Y,WANG H.Cloud Classification of Satellite ImageBased on Convolutional Neural Networks[C]//IEEE International Conference on Software Engineering and Service Science(ICSESS).2017:894-897.
[11] GAO Y L,ZHAN X G,CHI C Y.Research on sentiment ana-lysis based on CNN-LSTM model[J].Journal of University of Science and Technology Liaoning,2018,41(6):469-474.
[12] LI T,HUA M,WU X.A Hybrid CNN-LSTM Model for Forecasting Particulate Matter(PM2.5)[J].IEEE Access,2020(8):26933-26940.
[13] REHMAN A U,MALIK A K,RAZA B,et al.A Hybrid CNN-LSTM Model for Improving Accuracy of Movie Reviews Sentiment Analysis[J].Multimedia Tools and Applications,2019,78(18):26597-26613.
[14] KBESSHO,DATE K,HAYASHI M,et al.An Introduction to Himawari-8/9-Japan's New-Generation Geostationary Meteorological Satellites[J].Journal of the Meteorological Society of Japan,2016,94(2):151-183.
[15] PURBANTORO B,AMINUDDIN J,MANAGO N,et al.Comparison of Cloud Type Classification with Split Window Algorithm Based on Different Infrared Band Combinations of Himawari-8 Satellite[J].Advances in Remote Sensing,2018,7(3):218-234.
[16] ZHANG C W.The Cloud-type Classification Research and itsApplication for the New Generation Geostationary Satellite Himawari-8[D].Nanjing:Nanjing University,2019.
[17] LI Y Y,FANG L Z,KOU X W.Principle and Standard of Auto-Observation Cloud Classification for Satellite,Ground Measurements and model[J].Chinense Journal of Geophysics,2014,57(8):2433-2441.
[18] LIU Y.Remote Sensing Precipitation Forecasting Model Using Radar and Geostationary Meteorological Satellite and Analysis on Precipitation Predictability[D].Beijing:Chinese Academy of Sciences,2014.
[19] FENG F,WANG S,WANG C,et al.Learning Deep Hierarchical Spatial-Spectral Features for Hyperspectral Image Classification Based on Residual 3D-2D CNN[J].Sensors,2019,19(23):5276.
[20] ROY S K,KRISHNA G,DUBEY S R,et al.HybridSN:Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification[J].IEEE Geoscience and Remote Sensing Letters,2020,17(2):277-281.
[1] WANG Xin-tong, WANG Xuan, SUN Zhi-xin. Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network [J]. Computer Science, 2022, 49(8): 314-322.
[2] ZHANG Ying-tao, ZHANG Jie, ZHANG Rui, ZHANG Wen-qiang. Photorealistic Style Transfer Guided by Global Information [J]. Computer Science, 2022, 49(7): 100-105.
[3] LI Si-quan, WAN Yong-jing, JIANG Cui-ling. Multiple Fundamental Frequency Estimation Algorithm Based on Generative Adversarial Networks for Image Removal [J]. Computer Science, 2022, 49(3): 179-184.
[4] LIU Yang, LI Fan-zhang. Fiber Bundle Meta-learning Algorithm Based on Variational Bayes [J]. Computer Science, 2022, 49(3): 225-231.
[5] PAN Zhi-hao, ZENG Bi, LIAO Wen-xiong, WEI Peng-fei, WEN Song. Interactive Attention Graph Convolutional Networks for Aspect-based Sentiment Classification [J]. Computer Science, 2022, 49(3): 294-300.
[6] HU Yan-li, TONG Tan-qian, ZHANG Xiao-yu, PENG Juan. Self-attention-based BGRU and CNN for Sentiment Analysis [J]. Computer Science, 2022, 49(1): 252-258.
[7] LI Shan, XU Xin-zheng. Parallel Pruning from Two Aspects for VGG16 Optimization [J]. Computer Science, 2021, 48(6): 227-233.
[8] ZHAN Rui, LEI Yin-jie, CHEN Xun-min, YE Shu-han. Street Scene Change Detection Based on Multiple Difference Features Network [J]. Computer Science, 2021, 48(2): 142-147.
[9] PENG Bin, LI Zheng, LIU Yong, WU Yong-hao. Automatic Code Comments Generation Method Based on Convolutional Neural Network [J]. Computer Science, 2021, 48(12): 117-124.
[10] CHEN Hao-nan, LEI Yin-jie, WANG Hao. Lightweight Lane Detection Model Based on Row-column Decoupled Sampling [J]. Computer Science, 2021, 48(11A): 416-419.
[11] ZHANG Ning, FANG Jing-wen, ZHAO Yu-xuan. Bitcoin Price Forecast Based on Mixed LSTM Model [J]. Computer Science, 2021, 48(11A): 39-45.
[12] WANG Xin-ping, XIA Chun-ming, YAN Jian-jun. Sign Language Recognition Based on Image-interpreted Mechanomyography and Convolution Neural Network [J]. Computer Science, 2021, 48(11): 242-249.
[13] XIAO Shi-long, WU Di, TANG Chao-chen, SHEN Xian-hao, ZHANG De-yu. Control Application of Wolf Group Optimization Convolutional Neural Network in Ship Virtual Manufacturing [J]. Computer Science, 2021, 48(10): 135-139.
[14] ZHANG Yu-shuai, ZHAO Huan, LI Bo. Semantic Slot Filling Based on BERT and BiLSTM [J]. Computer Science, 2021, 48(1): 247-252.
[15] ZHUANG Zhi-gang, XU Qing-lin. Scene Graph Generation Model Combining Multi-scale Feature Map and Ring-type RelationshipReasoning [J]. Computer Science, 2020, 47(4): 136-141.
Full text



No Suggested Reading articles found!