[1]樊仲欣,陈旭红,谭桂容.基于递归小波神经网络的江苏城镇夏季最高气温预报预警技术[J].自然灾害学报,2019,28(06):056-69.[doi:10.13577/j.jnd.2019.0607]
 FAN Zhongxin,CHEN Xuhong,TAN Guirong.Summer maximum temperature forecast and warning in Jiangsu cities and towns based on recurrent wavelet neural network[J].,2019,28(06):056-69.[doi:10.13577/j.jnd.2019.0607]
点击复制

基于递归小波神经网络的江苏城镇夏季最高气温预报预警技术
分享到:

《自然灾害学报》[ISSN:/CN:23-1324/X]

卷:
28
期数:
2019年06期
页码:
056-69
栏目:
出版日期:
2019-12-28

文章信息/Info

Title:
Summer maximum temperature forecast and warning in Jiangsu cities and towns based on recurrent wavelet neural network
作者:
樊仲欣 陈旭红 谭桂容
南京信息工程大学 大气与环境实验教学中心, 江苏 南京 210044
Author(s):
FAN Zhongxin CHEN Xuhong TAN Guirong
Experimental Teaching Center for Atmospheric and Environmental Sciences, Nanjing University of Information Science & Technology, Nanjing 210044, China
关键词:
地面气温夏季最高气温数值预报产品释用动态因子检验递归小波神经网络
Keywords:
surface air temperaturesummer maximum temperatureinterpretation of numerical forecast productsdynamic factors testrecurrent wavelet neural network
分类号:
P456.8;X43
DOI:
10.13577/j.jnd.2019.0607
摘要:
针对目前数值天气预报产品释用方法上所存在的释用因子固化,无法应对特殊转折性天气的问题,应用一种基于动态因子检验的递归小波神经网络(Recurrent Wavelet Neural Network,RWNN)对江苏城镇夏季最高气温进行释用。该方法可以自动选取气象要素且无需建立回归方程,具有泛用性好、灵活性高的特点。使用该方法基于T639的2017-2018年6-8月资料建立了江苏省南京、徐州、射阳、常州、苏州5地的最高气温预报预警模型。实验结果表明:南京、徐州、射阳3地模型的TT2和HSS35评分较反向传播神经网络方法分别平均提高了9个百分点和0.15,同时较卡尔曼滤波方法分别平均提高了17个百分点和0.2。
Abstract:
To solve the problem that the meteorological factors used in the interpretation of numerical forecast products are fixed and unsuitable for special turning of weather phenomenon, a recurrent wavelet neural network(RWNN) method based on dynamic factors was adopted to interpret the summer maximum temperature in Jiangsu cities and towns. This method could select meteorological factors automatically and with out establishing statistical equations, so could be widely used. Based on the data of five cities and towns of Jiangsu Province including Nanjing, Xuzhou, Sheyang, Changzhou, Suzhou during June-August of 2017-2018 from T639 numerical forecast products, the maximum temperature forecast and warning models were established with the method. Experimental results show that models’ TT2 scores have increased by 9% and HSS35 scores have increased 0.15 compared to back propagation neural network, and models’ TT2 scores have increased by 17% and HSS35 scores have increased 0.2 compared to Kalman filter on average in Nanjing, Xuzhou and Sheyang.

参考文献/References:

[1] 张书娟.华东地区高温灾害风险评估研究[D].上海:上海师范大学, 2011. ZHANG Shujuan.Risk Assessment of High Temperature Disaster in East China[D]. Shanghai:Shanghai Normal University, 2011.(in Chinese)
[2] 许遐祯, 郑有飞, 尹继福, 等.南京市高温热浪特征及其对人体健康的影响[J].生态学杂志, 2011, 30(12):2815-2820. XU Xiazhen, ZHENG Youfei, YIN Jifu, et al. Characteristics of high temperature and heat wave in Nanjing City and their impacts on human health[J].Chinese Journal of Ecology, 2011, 30(12):2815-2820. (in Chinese)
[3] 刘建军, 郑有飞, 吴荣军. 热浪灾害对人体健康的影响及其方法研究[J].自然灾害学报, 2008, 17(1):151-156. LIU Jianjun, ZHEN Youfei, WU Rongjun. Impacts of heat waves disaster on human health and its research method[J].Journal of Natural Disasters, 2008, 17(1):151-156. (in Chinese)
[4] 贺山峰, 戴尔阜, 葛全胜, 等. 中国高温致灾危险性时空格局预估[J]. 自然灾害学报, 2010, 19(2):91-97. HE Shanfeng, DAI Erfu, GE Quansheng, et al. Pre-estimation of spatiotemporal pattern of extreme heathazard in China[J]. Journal of Natural Disasters, 2010, 19(2):91-97. (in Chinese)
[5] 吴荣军, 郑有飞, 刘建军, 等.长江三角洲主要城市高温灾害的趋势分析[J].自然灾害学报, 2010, 19(5):56-63. WU Rongjun, ZHEN Youfei, LIU Jianjun, et al. Trand analysis of high temperature disaster in large cities of the Yangtze River Delta[J]. Journal of Natural Disasters, 2010, 19(5):56-63. (in Chinese)
[6] 孙敏, 袁慧玲, 杜予罡.上海地区春季最高气温预报失败案例分析[J].气象, 2018, 44(1):65-79. SUN Min, YUAN Huilin, DU Yugang. Analysis of the spring maximum 2m tempersture forecast failure in Shanghai[J].Meteorological Monthly, 2018, 44(1):65-79. (in Chinese)
[7] Klein W H, Lewis B M, Enger I. Objective prediction of five-day mean temperature during winter[J]. Journal of Atmospheric Sciences, 1959, 16(6):672-682.
[8] Glahn H R, Lowry D A. The use of model output statistics (MOS) in objective weather forecasting[J]. Journal of Applied Meteorology, 1972, 11(8):1203-1211.
[9] Kalman R E. A new approach to linear filtering and prediction problems[J]. Journal of Basic Engineering, 1960, 82(1):35-45.
[10] 刘梅, 濮梅娟, 高苹, 等. 江苏省夏季最高温度定量预报方法[J].气象科技, 2008, 36(6):728-733. LIU Mei, PU Meijuan, GAO Ping, et al. Quantitative forecast methods of highest temperature in summer in Jiangsu[J]. Meteorological Science and Technology, 2008, 36(6):728-733. (in Chinese)
[11] 孙照渤, 谭桂容, 赵振国,等.中国东部夏季雨型的人工神经网络集合预测[J].大气科学学报, 2013, 36(1):1-6. SUN Zhaobo, TAN Guirong, ZHAO Zhenguo, et al. Ensemble prediction of summer rainfall patterns over eastern China based on artifical neural networks[J]. Transactions of Atmospheric Sciences, 2013, 36(1):1-6.(in Chinese)
[12] 张秀年, 曹杰, 杨素雨, 等. 多模式集成MOS方法在精细化温度预报中的应用[J]. 云南大学学报(自然科学版), 2011, 33(1):67-71. ZHANG Xiunian, CAO Jie, YANG Suyu, et al. Multi-model compositive MOS method application of fine temperature forecast[J]. Journal of Yunnan University, 2011, 33(1):67-71. (in Chinese)
[13] 赵云武, 祁杰, 杨福兴, 等. MEOFIS平台的苏州本地化释用和气温检验[J].气象科学, 2011, 31(S):139-144. ZHAO Yunwu, QI Jie, YANG Fuxing, et al. Localized explanation and application of the MEOFIS platform in Suzhou and the quality of temperature forecast[J]. Journal of the Meteorological Sciences, 2011, 31(S):139-144.(in Chinese)
[14] 陆如华, 何于班.卡尔曼滤波方法在天气预报中的应用[J].气象, 1994, 20(9):41-43. LU Ruhua, HE Yuban. The application of Kalman filter in weather forecasts[J]. Meteorological Monthly, 1994, 20(9):41-43. (in Chinese)
[15] 梁钰, 布亚林, 贺哲, 等. 用卡尔曼滤波制作河南省冬春季沙尘天气短期预报[J].气象, 2006, 32(1):62-67. LIANG Yu, BU Yalin, HE Zhe, et al. Application of Kalman Filtering to dust forecast in winter and spring over Henan Province[J]. Meteorological Monthly, 2006, 32(1):62-67. (in Chinese)
[16] 史创社.卡尔曼滤波在咸阳极端温度预报中的应用[J]. 陕西气象, 2007(1):15-17. SHI Chuangshe. Application of Kalman filtering in prediction of extreme temperature in Xianyang[J]. Journal of Shaanxi Meteorology, 2007(1):15-17. (in Chinese)
[17] 林健玲, 金龙, 彭海燕.区域降水数值预报产品人工神经网络释用预报研究[J].气象科技, 2006, 34(1):12-17. LIN Jianling, JING Long, PENG Haiyan. Application of numerical forecast products to regional rainfall forecasting by artificial neural network[J]. Meteorological Science and Technology, 2006, 34(1):12-17. (in Chinese)
[18] 马旭林,于月明,姜胜,等.基于集合卡尔曼变换的目标观测敏感区识别系统优化及影响试验[J].大气科学学报, 2014, 37(6):749-757. MA Xulin, YU Yueming, JIANG Sheng, et al. Optimization and influence experiment to identify sensitive areas for target observations on ETKF method[J].Transactions of Atmospheric Sciences, 2014, 37(6):749-757. (in Chinese)
[19] 傅德胜, 肖晨, 谭畅, 等. RBF神经网络在雷达定量估测降水中的应用研究[J].气象科学, 2015, 35(2):199-203. FU Deshen, XIAO Chen, TAN Chang, et al. Application of RBF neural network in radar quantitative precipitation estimation[J]. Journal of the Meteorological Sciences, 2015, 35(2):199-203.(in Chinese)
[20] 黎玥君,郭品文.基于BP神经网络的浙北夏季降尺度降水预报方法的应用[J]. 大气科学学报, 2017, 40(3):425-432. LI Yuejun, GUO Pinwen. Application of downscaling forecast for the North of Zhejiang precipitation in summer based on the BP neural network model[J]. Transactions of Atmospheric Sciences, 2017, 40(3):425-432. (in Chinese)
[21] 吴君, 裴洪芹, 石莹, 等.基于数值预报产品的地面气温BP_MOS预报方法[J].气象科学, 2007, 27(4):430-435. WU Jun, PEI Hongqin, SHI Ying, et al. The forecasting of surface air temperature using BP_MOS method based on the numerical forecasting results[J]. Journal of the Meteorological Sciences, 2007, 27(4):430-435. (in Chinese)
[22] 王彬滨, 吴息, 余江, 等.风电场两种超短期风速预报方法的效果对比[J].气象科学, 2015, 35(1):71-76. WANG Binbin, WU Xi, YU Jiang, et al. Comparison of two wind speed prediction methods in ultra short-term at wind farm[J].Journal of the Meteorological Sciences, 2015, 35(1):71-76.(in Chinese)
[23] 匡晓迪, 王兆毅, 张苗茵, 等.基于BP神经网络方法的近岸数值海温预报释用技术[J].海洋与湖沼, 2016, 47(6):1107-1115. KUANG Xiaodi, WANG Zhaoyi, ZHANG Miaoyin, et al. An interpretation scheme of numerical near-shore sea-water temperature forecast based on BPNN[J]. Oceanologia et Limnologia Sinica, 2016, 47(6):1107-1115. (in Chinese)
[24] 赵冬玉, 王利伟.BP神经网络算法在数值预报产品释用中的应用[J].科技视界, 2016(20):300-301. ZHAO Dongyu, WANG Liwei. Application of BP neural network algorithm in the interpretation of numerical forecast products[J]. Science & Technology Vision, 2016(20):300-301. (in Chinese)
[25] 白永清, 陈正洪, 王明欢, 等.基于WRF模式输出统计的逐时太阳总辐射预报初探[J].大气科学学报, 2011, 34(3):363-369. BAI Yongqing, CHEN Zhenghong, WANG Minghuan, et al. Preliminary research on prediction of hourly solar radiation based on WRF model output statistics[J].Transactions of Atmospheric Sciences, 2011, 34(3):363-369.(in Chinese)
[26] 王艺橙.基于卡尔曼滤波和MOS方法的江苏地区夏季最高气温预报[D].南京:南京信息工程大学, 2018. WANG Yicheng. Summer Maximum Temperature Forecast in Jiangsu Based on Kalman Filter and MOS Method[D]. Nanjing:Nanjing University of Information Science & Technology, 2018.(in Chinese)
[27] 李华, 宫明晓, 刘春涛, 等. T639预报气温产品误差分析与订正[J]. 气象科技, 2017, 45(6):1065-1069, 1105. LI Hua, GONG Mingxiao, LIU Chuntao, et al. Error analysis and correction of T639 forecast temperature products[J]. Meteorological Science and Technology, 2017, 45(6):1065-1069, 1105. (in Chinese)
[28] 任文斌, 杨新, 孙潇棵, 等.T639数值预报产品订正方案[J].气象科技, 2014, 42(1):145-150. REN Wenbin, YANG Xin, SUN Xiaoke, et al. Correcting scheme for T639 numerical products[J]. Meteorological Science and Technology, 2014, 42(1):145-150. (in Chinese)
[29] 屠妮妮, 何光碧, 张利红.成都区域气象中心业务数值预报产品检验分析[J].高原山地气象研究, 2010, 30(1):21-28. TU Nini, HE Guangbi, ZHANG Lihong. The examination and analysis of operational numerical forecast products in Chengdu regional meteorological center[J]. Plateau and Mountain Meteorology Research, 2010, 30(1):21-28. (in Chinese)
[30] 任宏昌. 2017年6-8月T639, ECMWF及日本模式中期预报性能检验[J].气象, 2017, 43(11):1440-1445. REN Hongchang. Performance verification of medium-range forecasts by T639, ECMWF and Japan models from June to August 2017[J]. Meteorological Monthly, 2017, 43(11):1440-1445. (in Chinese)
[31] Jordan M I. Attractor dynamics and parallelism in a connectionist sequential machine[C]//Proceedings of the Eighth Annual Conference of the Cognitive Science Society. Hillsdale, New Jersey, USA:CSS, 1986:531-546.
[32] Elman J L. Finding structure in time[J]. Cognitive Science, 1990(14):179-211.
[33] 陈伟根, 潘翀, 王有元, 等.利用小波神经网络的电力变压器故障诊断方法[J].高电压技术, 2007, 33(8):52-55. CHEN Weigen, PAN Chong, WANG Youyuan, et al. Fault diagnostic mothed using wavelet neural network for power transformers[J]. High Voltage Engineering, 2007, 33(8):52-55. (in Chinese)
[34] 赵凤遥, 马震岳. 基于递归小波神经网络的非线性动态系统仿真[J]. 系统仿真学报, 2007, 19(7):1453-1455, 1539. ZHAO Fengyao, MA Zhenyue. Nonlinear dynamical system simulation based on recurrent wavelet neural network[J]. Journal of System Simulation, 2007, 19(7):1453-1455, 1539. (in Chinese)
[35] 周泽华, 胡学友, 谭敏, 等. 基于神经网络的印刷体数字字符的识别[J].自动化与仪器仪表, 2009(5):110-112. ZHOU Zehua, HU Xueyou, TAN Min, et al. Recognition of printed digital characters based on neural network[J]. Automation & Instrumentation, 2009(5):110-112. (in Chinese)
[36] 陶砾,杨朔,杨威. 深度学习的模型搭建及过拟合问题的研究[J]. 计算机时代, 2008(2):14-21. TAO Li, YANG Shuo, YANG Wei. Research on the model building and over-fitting of deep learning[J]. Computer Era, 2008(2):14-21. (in Chinese)
[37] 周文娟.江苏省近34年气候舒适度精细化评价[D].南京:南京信息工程大学, 2017. ZHOU Wenjuan. Fine Evaluation of Climatic Comfort in Recent 34 years in Jiangsu Province[D]. Nanjing:Nanjing University of Information Science & Technology, 2017.(in Chinese)
[38] 徐曼, 乔颖, 鲁宗相. 短期风电功率预测误差综合评价方法[J]. 电力系统自动化, 2011, 35(12):20-26. XU Man, QIAO Ying, LU Zongxiang. A comprehensive error evaluation method for short-term wind power prediction[J]. Automation of Electric Power Systems, 2011, 35(12):20-26. (in Chinese)
[39] Heidke P. Calculation of the success and goodness of strong wind forecasts in the storm warning service[J]. Geografiska Annaler, 1926, 8:301-349.
[40] 郑有飞, 丁雪松, 吴荣军, 等. 近50年江苏省夏季高温热浪的时空分布特征分析[J].自然灾害学报, 2012, 21(2):43-50. ZHENG Youfei, DING Xuesong, WU Rongjun, et al. Temporal and spatial feature analyses of summer high temperature and heat wave in Jiangsu Province in past 50 years[J]. Journal of Natural Disasters, 2012, 21(2):43-50. (in Chinese)

备注/Memo

备注/Memo:
收稿日期:2019-04-09;改回日期:2019-06-23。
基金项目:国家重点研发计划(2018YFC1505804);国家自然科学基金项目(41575085)
作者简介:樊仲欣(1981-),男,工程师,硕士研究生,主要从事气象信息技术研究.E-mail:fan_zhong_xin@qq.com
通讯作者:陈旭红(1968-),女,工程师,主要从事短期及灾害性天气预报,数值预报产品释用研究.E-mail:1843526075@qq.com
更新日期/Last Update: 1900-01-01