|本期目录/Table of Contents|

 Lu Zhiying,Ren Yimo,Sun Xiaolei,et al.Recognition of Short-Time Heavy Rainfall Based on Deep Learning[J].Journal of Tianjin University,2018,(02):111-119.[doi:10.11784/tdxbz201703106]





Recognition of Short-Time Heavy Rainfall Based on Deep Learning
路志英1 任一墨1 孙晓磊2 贾惠珍3
1. 天津大学电气自动化与信息工程学院,天津 300072;2. 天津市海洋中心气象台,天津 300074;3. 天津市气象台,天津 300074
Lu Zhiying 1 Ren Yimo 1 Sun Xiaolei 2 Jia Huizhen 3
1. School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
2. Tianjin Marine Meteorological Center, Tianjin 300074, China
3. Tianjin Meteorological Bureau, Tianjin 300074, China
One of the key studies for meteorological practitioners is how to recognize and predict short-time heavy rainfall accurately and effectively. The short-time heavy rainfall is a severe meteorological disaster that is mainly caused by strong convective weather, which is related to such physical parameters as air humidity, moisture in the atmosphere, temperature and humidity. In this paper, a recognition model of the short-time heavy rainfall based on physical parameters and deep learning model DBNs is constructed. Firstly, SMOTE algorithm is used to synthesize a few samples of the short-time heavy rainfall, which is much less than normal weather, to adjust the distribution of the original data set. Secondly, a deep learning model with a Gaussian Boltzmann machine is constructed based on the observed data from automatic monitoring stations on a local ground and the physical quantities commonly used in weather forecast analysis. Finally, the automatic recognition model of short-term heavy rainfall is obtained. Through the analysis of the experimental results, the model can accurately recognize the short-time heavy rainfall, and have a good performance in the POD, FAR and CSI of short-time heavy rainfall recognition.


[1] Jeon S S. Damage pattern recognition of spatially distributed slope damages and rainfall using optimal GIS mesh dimensions[J]. Journal of Mountain Science, 2014, 11(2):336-344.
[2] Luino F. Sequence of instability processes triggered by heavy rainfall in the Northern Italy[J]. Geomorphology, 2005, 66(1/2/3/4):13-39.
[3] You C H, Lee D I, Kang M Y, et al. Classification of rain types using drop size distributions and polarimetric radar:Case study of a 2014 flooding event in Korea[J]. Atmospheric Research, 2016, 181:211-219.
[4] Root B, Yu T Y, Yeary M. Consistent clustering of radar reflectivities using strong point analysis:A prelude to storm tracking[J]. Geoscience and Remote Sensing Letters IEEE, 2011, 8:273-277.
[5] 胡文东, 杨侃, 黄小玉, 等. 一次阵风锋触发强对流过程雷达资料特征分析[J]. 高原气象, 2015, 34(5):1452-1464.
Hu Wendong, Yang Kan, Huang Xiaoyu, et al. Analysis on a severe convection triggered by gust front in Yinchuan with radar data[J]. Plateau Meteorology, 2015, 34(5):1452-1464(in Chinese).
[6] 张家国, 王珏, 黄治勇, 等. 几类区域性暴雨雷达回波模型[J]. 气象, 2011, 37(3):285-290.
Zhang Jiaguo, Wang Jue, Huang Zhiyong, et al. Several kinds of region rainstorm radar echo models[J]. Meteorological Monthly, 2011, 37(3):285-290(in Chinese).
[7] Arel I, Rose D C, Karnowski T P. Deep machine learning—A new frontier in artificial intelligence research [research frontier][J]. IEEE Computational Intelligence Magazine, 2010, 5(4):13-18.
[8] Kalal Z, Mikolajczyk K, Matas J. Tracking-learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7):1409-1422.
[9] Wan J, Liu J, Ren G, et al. Day-ahead prediction of wind speed with deep feature learning[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2016, 30(5):433-438.
[10] Zhang C Y, Chen C L P, Gan M, et al. Predictive deep Boltzmann machine for multipored wind speed forecasting[J]. IEEE Transactions on Sustainable Energy, 2015, 6(4):1416-1425.
[11] 尹剑, 陆程敏, 杨贵军. 判别分析与Logistic回归组合分类[J]. 数理统计与管理, 2014, 33(2):256-265.
Yin Jian, Lu Chengmin, Yang Guijun. Combinations of discriminatory analysis and logistic regression for classification[J]. Journal of Applied Statistics and Management, 2014, 33(2):256-265(in Chinese).
[12] 刘健文. 天气分析预报物理量计算基础[M]. 北京:气象出版社, 2005.
Liu Jianwen. Calculation of Physical Quantities Based on Weather Forecast[M]. Beijing:China Meteorological Press, 2005(in Chinese).
[13] 杨景梅, 邱金桓. 用地面湿度参量计算我国整层大气可降水量及有效水汽含量方法的研究[J]. 大气科学, 2002, 26(1):9-22.
Yang Jingmei, Qiu Jinhuan. A method for estimating perceptible water and water vapor content from ground humidity parameters[J]. Chinese Journal of Atmospheric Sciences, 2002, 26(1):9-22(in Chinese).
[14] 李超, 魏合理, 刘厚通, 等. 合肥整层大气可降水量与地面露点相关性分析[J]. 高原气象, 2009, 28(2):452-457.
Li Chao, Wei Heli, Liu Houtong, et al. Correlation analyses on total perceptible water and surface dew point temperature over Hefei[J]. Plateau Meteorology, 2009, 28(2):452-457(in Chinese).
[15] Chawla N V, Bowyer K W, Hall L O, et al. SMOTE:Synthetic minority over-sampling technique [J]. Journal of Artificial Intelligence Research, 2002, 16(1):321-357.
[16] Hinton G, Osindero S, Teh Y. A fast learning algorithm for deep belief nets[J]. Neural Computation, 1989, 18(7):1527-1554.
[17] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504.
[18] Chabiron O, Malgouyres F, Tourneret J Y, et al. Toward fast transform learning[J]. International Journal of Computer Vision, 2015, 114(2/3):195-216.
[19] Pelillo M, Refice M. Learning compatibility coefficients for relaxation labeling processes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(9):933-945.
[20] Najafabadi M M, Villanustre F, Khoshgoftaar T M, et al. Deep learning applications and challenges in big data analytics[J]. Journal of Big Data, 2015, 2(1):1-10.
[21] Roux N L, Bengio Y. Representational power of restricted Boltzmann machines and deep belief networks [J]. Neural Computation, 2008, 20(6):1631-1632.
[22] Hinton G E. A practical guide to training restricted Boltzmann machines[J]. Momentum, 2012, 9(1):599-619.
[23] Yamashita T, Tanaka M, Yoshida E, et al. To be Bernoulli or to be Gaussian, for a restricted Boltzmann machine[C]//International Conference on Pattern Recognition, IEEE Computer Society. Sweden, 2014:1520-1525.
[24] Hinton G E. Training products of experts by minimizing contrastive divergence[J]. Neural Computation, 2002, 14(8):1771-1800.
[25] Karakida R, Okada M, Amari S I. Dynamical analysis of contrastive divergence learning:Restricted Boltzmann machines with Gaussian visible units[J]. Neural Networks, 2016, 79(C):78-87.
[26] Hinton G E, Dayan P, Frey B J, et al. The "wake-sleep" algorithm for unsupervised neural networks[J]. Science, 1995, 268(268):1158-1161.
[27] 路志英, 刘海, 贾惠珍, 等. 基于雷达反射率图像特征的冰雹暴雨识别[J]. 物理学报, 2014, 63(18):485-496.
Lu Zhiying, Liu Hai, Jia Huizhen, et al. Recognition of hail and rainstorm based on the radar reflectivity image features[J]. Acta Physica Sinica, 2014, 63(18):485-496(in Chinese).


收稿日期: 2017-03-31; 修回日期: 2017-08-22.
作者简介: 路志英(1964—), 女, 博士, 教授.
通讯作者: 路志英, luzy@tju.edu.cn.
基金项目: 国家自然科学基金资助项目(41575049); 天津市自然科学基金青年项目(16JQNJC07500).
Supported by the National Natural Science Foundation of China(No.,41575049)and the Youth Project of Natural Science Foundation of Tianjin, China(No.,16JQNJC07500).
更新日期/Last Update: 2018-02-10