计算机科学 ›› 2018, Vol. 45 ›› Issue (4): 227-232.doi: 10.11896/j.issn.1002-137X.2018.04.038

• 人工智能 • 上一篇    下一篇

基于深度极限学习机的卫星云图云量计算

翁理国,孔维斌,夏旻,仇学飞   

  1. 南京信息工程大学江苏省大气环境与装备技术协同创新中心 南京210044南京信息工程大学江苏省大数据分析重点实验室 南京210044,南京信息工程大学江苏省大气环境与装备技术协同创新中心 南京210044南京信息工程大学江苏省大数据分析重点实验室 南京210044,南京信息工程大学江苏省大气环境与装备技术协同创新中心 南京210044南京信息工程大学江苏省大数据分析重点实验室 南京210044,南京信息工程大学江苏省大气环境与装备技术协同创新中心 南京210044南京信息工程大学江苏省大数据分析重点实验室 南京210044
  • 出版日期:2018-04-15 发布日期:2018-05-11
  • 基金资助:
    本文受国家自然科学基金(61503192),江苏省自然科学基金(BK20161533),江苏省六大人才高峰高层次人才资助

Satellite Imagery Cloud Fraction Based on Deep Extreme Learning Machine

WENG Li-guo, KONG Wei-bin, XIA Min and CHOU Xue-fei   

  • Online:2018-04-15 Published:2018-05-11

摘要: 卫星云图云量计算是卫星气象应用的基础,现阶段对其的研究未能充分利用卫星云图的特征,导致云检测及云量计算的效果不好。针对该问题,利用多层神经网络进行卫星云图的特征提取,并通过大量实验寻找到最优的深度学习的网络结构。基于度极限学习机对卫星云图的云进行检测和分类,再利用“空间相关法”计算云图中的总云量。实验结果表明,基于传统极限学习机的深度极限学习机能够充分提取云图的特征,在进行云分类时能够较清晰地区分厚云和薄云间的界限。相比于传统阈值法、极限学习机模型以及卷积神经网络,深度极限学习机的云识别率以及云量计算准确率更高,且所提方法比卷积神经网络的效率更高。

关键词: 云量计算,深度极限学习机,云检测,空间相关法,卫星图像

Abstract: Cloud fraction is the key point for the application of satellite imagery.The existing methods cannot make full use of characteristics of satellite imagery,resulting in ineffective cloud detection and cloud fraction.In this paper,multi-layer neural network was used to extract the feature of satellite cloud image,and and through a large number of experiments,the best structure of depth learning network was found.This paper used deep extreme learning machine to detect and classify the cloud of satellite cloud image,and then used spatial correlation method to calculate the total cloud fraction.The results show that the deep extreme learning machine based on traditional extreme learning machine can extract the features of cloud images effectively,and can distinguish the boundary between thick cloud and thin cloud well.The cloud classification and cloud fraction accuracy of deep extreme learning machine are better than traditional thresho-ld method,extreme learning machine and convolutional neural network.

Key words: Cloud fraction,Deep extreme learning machine,Cloud detection,Spatial correlation,Satellite imagery

[1] ROSSOW W B,GARDER L C.Cloud Detection Using Satellite Measurements of Infrared and Visible Radiances for ISCCP[J].Journal of Climate,1994,6(12):2341-2369.
[2] STOWE L L,DAVIS P A,MCCLAIN E P.Scientific Basis and Initial Evaluation of the CLAVR-1Global Clear/Cloud Classification Algorithm for the Advanced Very High Resolution Radio-meter[J].Journal of Atmospheric & Oceanic Technology,1996,16(6):656-681.
[3] SAUNDERS R W,KRIEBEL K T.An improved method of detecting clear sky and cloudy radiances from AVHRR data[J].International Journal of Remote Sensing,1998,9(1):123-150.
[4] KRIEBEL K T,GESELL G,KAESTNER M,et al.Cloud detection in AVHRR and ATSR data with APOLLO[J].Passive Infrared Remote Sensing of Clouds & the Atmosphere II,1994,2309:36-44.
[5] FREY R A,ACKERMAN S A,LIU Y,et al.Cloud Detection with MODIS.Part I:Improvements in the MODIS Cloud Mask for Collection 5[J].Journal of Atmospheric & Oceanic Techno-logy,2008,25(7):1057-1072.
[6] 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(0143-1161),1988,9(1):123-150.
[7] ZHEN X H,XU G Q,WEI R Q.Introducing and Influence Testing of the New Cloud Fraction Scheme in the GRAPES[J].Meteorological Monthly,2013,39(1):57-66.(in Chinese) 郑晓辉,徐国强,魏荣庆.GRAPES新云量计算方案的引进和影响试验[J].气象,2013,39(1):57-66.
[8] LIU J,ZHANG L Y.Calculation and Validation Method ofCloud Amount by High Spatial Resolution Satellite Data[J].Journal of Applied Meteorological Science,2011,22(1):35-45.(in Chinese) 刘健,张里阳.气象卫星高空间分辨率数据的云量计算与检验[J].应用气象学报,2011,22(1):35-45.
[9] KOPP T J,THOMAS W,HEIDINGER A K,et al.The VIIRS Cloud Mask:Progress in the first year of S-NPP toward a common cloud detection scheme[J].Journal of Geophysical Research Atmospheres,2014,119(5):2441-2456.
[10] KANG H L,LIU C,JIANG X J.Weather Recognition Algo-rithm Based onthe Characteristics of Atmospheric Electric Field Signal[J].Computer Simulation,2014,31(12):312-315.(in Chinese) 康海龙,刘成,姜秀杰.基于大气电场特征的天气现象识别算法研究[J].计算机仿真,2014,31(12):312-315.
[11] HE C H,HU Y C.Automatic Threshold Image Segmentation Approach Based on Improved Genetic Algorithm[J].Computer Simulation,2011,28(2):312-315.(in Chinese) 何春华,胡迎春.基于改进遗传算法的自动阈值图像分割方法[J].计算机仿真,2011,28(2):312-315.
[12] YAN W U,YIN Y,SHI C X,et al.Validation of NOAA/AVHRR Cloud Detections by an Automated Dynamic Thre-shold Cloud-Masking Algorithm[J].Plateau Meteorology,2012,31(3):745-751.
[13] ZHANG Y,KLEIN S,MACE G G,et al.Cluster analysis of tropical clouds using CloudSatdata[J].Geophysical Research Letters,2007,34(12):195-225.
[14] HUANG Q,WANG S L,XU D L,et al.Adaptive threshold approach for night-sky cloud inspection[J].Journal of Image and Graphics,2012,17(8):71-76.(in Chinese) 黄茜,王少龙,徐道磊,等.云的自适应阈值检测方法[J].中国图象图形学报,2012,17(8):71-76.
[15] REN X F,QIN J Y,YANG J,et al.Energy model based LS-TSVM for action recognition[J].Application Research of Compu-ters,2016,33(2):598-601.(in Chinese) 任晓芳,秦健勇,杨杰,等.基于能量模型的LS-TSVM在人体动作识别中的应用[J].计算机应用研究,2016,33(2):598-601.
[16] HE W Q,XUE H F,XIE D R,et al.Support Vector Machine Classification Based on K-nearest Neighbor[J].Computer Simulation,2008,25(11):161-163.(in Chinese) 和文全,薛惠峰,解丹蕊,等.基于K近邻的支持向量机分类方法[J].计算机仿真,2008,25(11):161-163.
[17] SUN Y,QI H.Study on fluorescence fiber temperature mea-surement system using fuzzy strategy [J].Journal of Fuzhou University(Natural Science Edition),2016,44(1):76-80.(in Chinese) 孙岩,齐虹.基于模糊策略的荧光光纤测温系统研究[J].福州大学学报(自然科学版),2016,44(1):76-80.
[18] SCHMIDHUBER J.Deep learning in neural networks:An overview[J].Neural Networks,2015,61:85-117.
[19] WANG G H,XU J.Fast feature representation method based on multilevel pyramid convolution neural network[J].Application Research of Computers,2015,32(8):2492-2495.(in Chinese) 王冠皓,徐军.基于多级金字塔卷积神经网络的快速特征表示方法[J].计算机应用研究,2015,32(8):2492-2495.
[20] HUANG G B,ZHU Q Y,SIEW C K.Extreme learning ma-chine:Theory and applications[J].Neurocomputing,2006,70(1-3):489-501.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!