| 基于深度极限学习机的卫星云图云量计算 |
| |
| 引用本文： | 翁理国,孔维斌,夏旻,仇学飞.基于深度极限学习机的卫星云图云量计算[J].计算机科学,2018,45(4):227-232. |
| |
| 作者姓名： | 翁理国 孔维斌 夏旻 仇学飞 |
| |
| 作者单位： | 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 |
| |
| 基金项目： | 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 |
| |
| 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 |
| 收稿时间： | 2017/1/7 0:00:00 |
| 修稿时间： | 2017/4/3 0:00:00 |
Satellite Imagery Cloud Fraction Based on Deep Extreme Learning Machine |
| |
| WENG Li-guo,KONG Wei-bin,XIA Min and CHOU Xue-fei.Satellite Imagery Cloud Fraction Based on Deep Extreme Learning Machine[J].Computer Science,2018,45(4):227-232. |
| |
| Authors: | WENG Li-guo KONG Wei-bin XIA Min and CHOU Xue-fei |
| |
| Affiliation: | Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology,Nanjing 210044,ChinaJiangsu Key Laboratory of Big Data Analysis Technology,Nanjing University of Information Science and Technology,Nanjing 210044,China,Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology,Nanjing 210044,ChinaJiangsu Key Laboratory of Big Data Analysis Technology,Nanjing University of Information Science and Technology,Nanjing 210044,China,Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology,Nanjing 210044,ChinaJiangsu Key Laboratory of Big Data Analysis Technology,Nanjing University of Information Science and Technology,Nanjing 210044,China and Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology,Nanjing 210044,ChinaJiangsu Key Laboratory of Big Data Analysis Technology,Nanjing University of Information Science and Technology,Nanjing 210044,China |
| |
| 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. |
| |
| Keywords: | Cloud fraction Deep extreme learning machine Cloud detection Spatial correlation Satellite imagery |
|
|
点击此处可从《计算机科学》下载全文 |
|
