[1]覃卫坚,廖雪萍,陈思蓉.延伸期暴雨过程的神经网络预报技术应用初探[J].气象研究与应用,2018,39(04):1-4.
 Qin Weijian,Liao Xueping,Chen Sirong.Preliminary Study on Neural Network Forecasting Technology Application for Extended Rainstorm Process[J].Journal of Meteorological Research and Application,2018,39(04):1-4.
点击复制

延伸期暴雨过程的神经网络预报技术应用初探()
分享到:

气象研究与应用[ISSN:1673-8411/CN:45-1356/P]

卷:
第39卷
期数:
2018年04期
页码:
1-4
栏目:
天气气候
出版日期:
2018-12-31

文章信息/Info

Title:
Preliminary Study on Neural Network Forecasting Technology Application for Extended Rainstorm Process
作者:
覃卫坚1 廖雪萍2 陈思蓉1
1. 广西壮族自治区气候中心, 广西 南宁 530022;
2. 广西壮族自治区气象减灾研究所, 广西 南宁 530022
Author(s):
Qin Weijian1 Liao Xueping2 Chen Sirong1
1. Guangxi Climate Center, Nanning Guangxi 530022;
2. Guangxi Institute of Meteorological Disaster Reduction, Nanning Guangxi 530022
关键词:
延伸期暴雨过程粒子群-神经网络暴雨综合强度
Keywords:
extended rainstorm processParticle Swarm Optimization-Artificial Neural Networkcomprehensive rainstorm intensity
分类号:
P466
摘要:
利用DERF2.0延伸期环流预报数据资料,首先使用暴雨过程信号指标就一般降水和暴雨过程进行分类,结果延伸期逐日降水分类预报准确率为65%。最后利用逐步回归和粒子群-神经网络方法就延伸期暴雨综合强度进行建模预报,逐步回归方法在F=3条件下对广西暴雨综合强度预报误差最小;粒子群-神经网络预报误差均小于逐步回归方法,相对误差较逐步回归方法预报效果最好的方程减小了32.5%,可见粒子群-神经网络在延伸期定量化预报中具有很好的应用前景。
Abstract:
This paper used DERF 2.0 circulation forecasting data in the extended period. Firstly, the general precipitation and rainstorm were classified by using the signal indices of rainstorm process. The accuracy of daily precipitation classification forecast in extended period is 65%. Finally, the stepwise regression method and Particle Swarm Optimization-Artificial Neural Network (PSO-ANN) were used to model and forecast the comprehensive intensity of rainstorm in the extended period. Under the condition of F=3, the stepwise regression method has the smallest error in the comprehensive intensity prediction. The prediction error of PSO-ANN is less than that of stepwise regression, and the relative error of PSO-ANN is 32.5% less than that of equations with the best forecasting effect by stepwise regression, which shows that PSO-ANN has a good application prospect in quantitative prediction of extended period.

参考文献/References:

[1] 丁一汇, 梁萍. 基于MJO的延伸预报[J]. 气象, 2010, 36(7):111-122.
[2] 陈官军, 魏凤英. 基于低频振荡特征的夏季江淮持续性降水延伸期预报方法[J]. 大气科学, 2012, 36(3):633-644.
[3] 孙国武, 李震坤, 信飞, 等. 延伸期天气过程预报的一种新方法-低频天气图[J]. 大气科学, 2013, 37(4):945-954.
[4] 覃卫坚, 李耀先, 廖雪萍.MJO活动对广西6月阶段性降水的影响研究[J].气象研究与应用, 2015, 36(1):25-30.
[5] 覃卫坚, 李耀先, 陈思蓉.同期MJO对广西汛期强降水过程的影响[J].气象研究与应用, 2017, 38(4):18-21.
[6] 覃卫坚, 李耀先, 廖雪萍, 等.大气低频振荡对广西持续性区域性暴雨的可能影响[J]. 气象研究与应用, 2015, 36(3):1-7.
[7] Kennedy J, Eberhart R C. Particle Swarm Optimization[A]. In:Proc IEEE International Conference on Neural Networks[C]. IV Piscataway, NJ:IEEE Service Center,1995,1942-1948.
[8] 金龙, 陈宁, 林振山.基于人工神经网络的集成预报方法研究和比较[J].气象学报, 1999, 57(2):198-207.
[9] Hua-sheng Zhao, Long Jin and Ying Huang. An Objective Prediction Model for Typhoon Rainstorm Using Particle Swarm Optimization-Neural Network Ensemble[J]. Natural Hazards. 2014, 73(2):427-437.
[10] 覃卫坚, 李耀先, 陈思蓉, 等.粒子群-神经网络在华南夏季降水短期气候预测中应用研究[J]. 气象研究与应用, 2015, 36(2):1-7.
[11] 覃卫坚, 陆虹, 黄志, 等.粒子群-神经网络在广西寒露风日数预报中的应用[J].气象与环境学报, 2015, 31(6):158-162.
[12] 覃卫坚, 李耀先, 廖雪萍.广西热带气旋的暴雨统计分析及数值模拟[J].气象研究与应用, 2013, 34(1):1-6.
[13] 覃卫坚, 李耀先, 覃志年.广西暴雨的区域性和连续性研究[J].气象研究与应用, 2012, 33(4):1-4.

相似文献/References:

[1]覃卫坚,李耀先,陈思蓉,等.粒子群-神经网络在华南夏季降水短期气候预测中应用研究[J].气象研究与应用,2015,36(02):1.
 Qin Wei-jian,Li Yao-xian,Chen Si-rong,et al.Application on the prediction of the summer precipitation in South China basing on PSO-Artificial Neutral Network[J].Journal of Meteorological Research and Application,2015,36(04):1.
[2]覃卫坚,何莉阳,蔡悦幸.基于两种机器学习方法的广西后汛期降水预测模型[J].气象研究与应用,2022,43(01):8.[doi:10.19849/j.cnki.CN45-1356/P.2022.1.02]
 Qin Weijian,He Liyang,Cai Yuexing.Prediction model of post-flood season precipitation in Guangxi based on two machine learning methods[J].Journal of Meteorological Research and Application,2022,43(04):8.[doi:10.19849/j.cnki.CN45-1356/P.2022.1.02]
[3]覃卫坚,何莉阳,蔡悦幸.广西暴雨集中度智能气候预测方法研究[J].气象研究与应用,2024,45(03):12.[doi:10.19849/j.cnki.CN45-1356/P.2024.3.02]
 QIN Weijian,HE Liyang,CAI Yuexing.Research on intelligent climate prediction methods of rainstorm concentration in Guangxi[J].Journal of Meteorological Research and Application,2024,45(04):12.[doi:10.19849/j.cnki.CN45-1356/P.2024.3.02]

备注/Memo

备注/Memo:
收稿日期:2018-07-15。
基金项目:中国气象局预报员专项“延伸期暴雨过程的神经网络预报技术应用”(项目编号:CMAYBY2018-057)、“广西延伸期气候预测创新团队”项目资助。
作者简介:覃卫坚(1971-),男,广西上林县人,在读博士,正高,主要从事气候变化与气候预测研究,E-mail:qinweijian2008@126.com。
更新日期/Last Update: 1900-01-01