微信服务号

微信订阅号

2025年4月17日 1:40 星期四
首页 > 过刊浏览>2017年第28卷第11期 >2925-2939. DOI:10.13328/j.cnki.jos.005336
PDF HTML阅读 XML下载 导出引用 引用提醒
多源数据融合高时空分辨率晴雨分类
作者:
基金项目:

国家自然科学基金（61432008，61532006，61472423，61305018）


Fusion of Multi-Source Data for Rain/No-Rain Classification with High Spatiotemporal Resolution
Author:
Fund Project:

National Natural Science Foundation of China (61432008, 61532006, 61472423, 61305018)

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [31]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    高时空分辨率晴雨分类与交通、旅游、农业灌溉及人们日常出行都密切相关，然而"天有不测风云"，"东边日头西边雨"，准确的高时空分辨率晴雨分类是极具挑战性的问题.提出了一种基于多源数据的多视角学习晴雨分类方法，其中，多源数据包括雷达、卫星及地面观测因子及晴雨观测数据.该方法表述如下：首先，依据雷达观测因子构造了VisCAPPI视角和VisPPI视角，依据葵花卫星资料构造了VisSat视角，依据地面观测因子构造了VisGround视角；然后，对这4个视角特征进行组合获得组合视角VisCAPPI_PPI，VisRadar_Sat，VisRadar_Groumd，VisSat_Ground，VisRadar_Sat_Ground，应用随机森林机器学习方法分别对这些视角进行样本学习，获得这些视角的晴雨分类模型；最后，对这些视角晴雨分类模型估计进行融合，获得晴雨分类结果.主要贡献在于：（1）提出了雷达、卫星和地面观测因子多视角构建方法，构建了VisCAPPI，VisPPI，VisSat和VisGround晴雨分类视角及其组合视角；（2）提出了一种多视角方法（multi-view weight random forest，简称MVWRF），能够处理雷达、卫星和地面观测因子多源数据融合晴雨分类问题，提高1km×1km和6min时空分辨率晴雨分类准确率.在2016年10月7日和8日，泉州雷达覆盖的393个气象观测站上进行模型训练和测试，结果显示，该方法能够取得较高的晴雨分类准确率和较低的漏报率、空报率，优于对比方法.

    Abstract:

    High spatiotemporal resolution rainfall estimation is closely related to transportation, tourism, agricultural irrigation and people's daily travel. However, accurate high-resolution rain/no-rain classification is a very challenging problem. This paper proposes a multi-source data based multi-view learning method for rain/no-rain classification. The multiple source data used in this paper include radar, satellite and ground observation factors and rain/no-rain observation data. This method can be summarized as follows. Firstly, VisCAPPI view and VisPPI views are constructed according to the radar observation factors. VisSat view is constructed from the sunflower satellite data. VisGround view is constructed according to the ground observation factors. Secondly, the views of VisCAPPI_PPI, VisRadar_Sat, VisRadar_Groumd, VisSat_Ground, and VisRadar_Sat_Ground are obtained by combining features from preconstructed views. Random forest (RF) classification models are trained from these views using RF method. Finally, the rain/no rain classification results are obtained from the estimated results of these RF classification models. The main contributions of this paper arelisted as follows:(1) Present a method for constructing VisCAPPI, VisPPI, VisSat and VisGround views and their feature combined views for radar, satellite and ground observations; (2) A multi-view weight random forest method (MVWRF) is proposed. Multi-source data of radar, satellite and near surface observations are fused for rain/no-rain classification with temporal resolution of 6-minute and spatial resolution of 1km×1km in virtue of the proposed method. The experimental results show that the proposed method in this paper can obtain high precision of rain/no-rain classification after training and testing on 393 meteorological stations covered by radar in Quanzhou on October 7 and 8, 2016.

    参考文献
    [1] Wang JH, Liang L, Wang B. Analysis of imbalanced weather data based on branch-and-bound approach. Application Research of Computers, 2016,33(6):1648-1652(in Chinese with English abstract).
    [2] Yoo C, Kang M, Ro Y. Applicability of precipitable water for enhancing radar accuracy on identification of rain and no rain. Journal of Korean Society of Hazard Mitigation, 2015,15(1):111-121.[doi:10.9798/KOSHAM.2015.15.1.111]
    [3] He N, Fu ZY, Zhao W, Wu J, Wu JK, Liao XN. Application of SVM method to summer clear-rain forecast in Beijing region. Torrential Rain and Disasters, 2013,32(3):284-288(in Chinese with English abstract).
    [4] Seto S, Takahashi N, Iguchi T. Rain/No-Rain classification methods for microwave radiometer observations over land using statistical information for brightness temperatures under no-rain conditions. Journal of Applied Meteorology, 2005,44(44):1243-1259.[doi:10.1175/JAM2263.1]
    [5] Xu LM, Sorooshian S, Gao XG, Gupta HV. A cloud-patch technique for identification and removal of no-rain clouds from satellite infrared imagery. Journal of Applied Meteorology, 2010,38(8):1170-1181.[doi:10.1175/1520-0450(1999)038<1170:ACPTFI>2.0. CO;2]
    [6] Kida S, Shige S, Kubota T, Aonashi K, Okamoto K. Improvement of rain/no-rain classification methods for microwave radiometer observations over the ocean using a 37GHz emission signature. Journal of the Meteorological Society of Japan.Ser.Ⅱ, 2009,87:165-181.[doi:10. 2151/jmsj.87A.165]
    [7] Islam T, Rico-Ramirez MA, Srivastava PK, Dai Q. Non-Parametric rain/no rain screening method for satellite-borne passive microwave radiometers at 19~85GHz channels with the random forests algorithm. Int'l Journal of Remote Sensing, 2014,35(9):3254-3267.[doi:10.1080/01431161.2014.903444]
    [8] Araki K, Murakami M, Ishimoto H, Tajiri T. Ground-Based microwave radiometer variational analysis during no-rain and rain conditions. Scientific Online Letters on the Atmosphere Sola, 2015,11:108-112.[doi:10.2151/sola.2015-026]
    [9] Xiao RR, Chandrasekar V, Liu H, Gorgucci E. Detection of rain/no rain condition on ground from radar data using a Kohonen neural network. In:Proc. of the IEEE Int'l Symp. on Geoscience and Remote Sensing. IEEE, 1998. 159-161.[doi:10.1109/IGARSS.1998.702834]
    [10] Liu H, Chandrasekar V, Gorgucci E. Detection of rain/no rain condition on the ground based on radar observations. IEEE Trans. on Geoscience and Remote Sensing, 2001,39(3):696-699.[doi:10.1109/36.911127]
    [11] Li ZL. A short-term weather forecast method for rain/no rain classification. Journal of Meteorological Research and Application, 1980,(4):25-29(in Chinese).
    [12] Zhou MF, Xiong W, Liu HZ. Forecast experiments of rain/no rain in Guizhou using KNN method. JournM of Guizhou Meteorology, 2010,34(6):3-5(in Chinese).
    [13] Xu C, Tao D, Xu C. A survey on multi-view learning. In:Proc. of the Computer Science. 2013. 1304-5634.
    [14] Bickel S, Scheffer T. Multi-View clustering. In:Proc. of the IEEE Int'l Conf. on Data Mining, Vol.4. 2004. 19-26.[doi:10.1109/ICDM.2004.10095]
    [15] Ho TK. The random subspace method for constructing decision forests. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998,20(8):832-844.[doi:10.1109/34.709601]
    [16] Tao DC, Tang XO, Li XL, Wu XD. Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2006,28(7):1088-1099.[doi:10.1109/TPAMI.2006.134]
    [17] Di W, Crawford MM. View generation for multiview maximum disagreement based active learning for hyperspectral image classification. IEEE Trans. on Geoscience and Remote Sensing, 2012,50(5):1942-1954.[doi:10.1109/TGRS.2011.2168566]
    [18] Fernández-Delgado M, Cernadas E, Barro S, Amorim D. Do we need hundreds of classifiers to solve real world classification problems? Journal of Machine Learning Research, 2014,15(1):3133-3181.
    [19] Breiman L. Random forests. Machine Learning, 2001,45(1):5-32.[doi:10.1023/A:1010933404324]
    [20] Río SD, López V, Benítez JM, Herrera F. On the use of MapReduce for imbalanced big data using random forest. Information Sciences, 2014,285:112-137.[doi:10.1016/j.ins.2014.03.043]
    [21] Yang XH, Xie XJ, Liu DL, Ji F, Wang L. Spatial interpolation of daily rainfall data for local climate impact assessment over greater Sydney region. In:Advances in Meteorology. 2015. 1-12.[doi:10.1155/2015/563629]
    [22] Fritsch FN, Carlson RE. Monotone piecewise cubic interpolation. SIAM Journal on Numerical Analysis, 1980,17(2):238-246.
    [23] Kuang QM, Yang XB, Zhang WS, Zhang GP. Spatiotemporal modeling and implementation for radar-based rainfall estimation. IEEE Geoscience and Remote Sensing Letters, 2016,13(11):1601-1605.[doi:10.1109/LGRS.2016.2597170]
    [24] Biau G. Analysis of a random forests model. The Journal of Machine Learning Research, 2012,13(1):1063-1095.
    [25] Zhang L, Zhu PF, Hu QH, Zhang D. A linear subspace learning approach via sparse coding. In:Proc. of the IEEE Int'l Conf. on Computer Vision. 2011. 755-761.[doi:10.1109/ICCV.2011.6126313]
    [26] Wang S. Relaxed collaborative representation for pattern classification. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2012. 2224-2231.[doi:10.1109/CVPR.2012.6247931]
    附中文参考文献:
    [1] 王剑辉,梁路,王彪.基于分支限界的不平衡气象数据晴雨分析.计算机应用研究,2016,33(6):1648-1652.
    [3] 何娜,付宗钰,赵玮,吴进,吴剑坤,廖晓农.SVM方法在北京地区夏季晴雨预报中的初步应用.暴雨灾害,2013,32(3):284-288.
    [11] 李志陆.一个短期晴雨天气预报方法.气象研究与应用,1980,(4):25-29.
    [12] 周明飞,熊伟,刘还珠.KNN方法在贵州晴雨预报中的实验.贵州气象,2010,34(6):3-5.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

匡秋明,杨雪冰,张文生,何险峰,惠建忠.多源数据融合高时空分辨率晴雨分类.软件学报,2017,28(11):2925-2939

复制
分享
文章指标
  • 点击次数:2717
  • 下载次数: 5411
  • HTML阅读次数: 1446
  • 引用次数: 0
历史
  • 收稿日期:2017-01-10
  • 最后修改日期:2017-04-11
  • 在线发布日期: 2017-11-03
文章二维码
友情链接:中国科学院软件研究所中国计算机学会中国科学院国家自然科学基金委员会CCF数字图书馆Int'l J of Softw Info计算机系统应用
您是第19831126位访问者
版权所有：中国科学院软件研究所 京ICP备05046678号-3
地址：北京市海淀区中关村南四街4号,邮政编码：100190
电话：010-62562563 传真：010-62562533 Email：jos@iscas.ac.cn
技术支持：北京勤云科技发展有限公司

京公网安备 11040202500063号