[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):1-7.
　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(02):1-7.
点击复制

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()
分享到：

气象研究与应用[ISSN:1673-8411/CN:45-1356/P]

卷:
第36卷
期数:
2015年02期
页码:
1-7
栏目:
天气气候
出版日期:
2015-12-21

文章信息/Info

Title:
Application on the prediction of the summer precipitation in South China basing on PSO-Artificial Neutral Network
作者:
覃卫坚1;  李耀先2;  陈思蓉1;  谢敏1
1. 广西区气候中心, 广西南宁 530022;
2. 广西气象减灾研究所, 广西南宁 530022
Author(s):
Qin Wei-jian1;  Li Yao-xian2;  Chen Si-rong1;  Xie Min1
1. Guangxi Climate Center, Nanning Guangxi 530022;
2. Guangxi Meteorological Disaster Reduction, Nanning Guangxi 530022
关键词:
粒子群-神经网络; 夏季降水;  EOF分析; 华南
Keywords:
Particle Swarm Optimization (PSO)-Artificial Neutral Network; summer (JJA) precipitation; empirical orthogonal function (EOF); South China
分类号:
P466
摘要:
使用1961~2013年广东、广西、海南三省共110个气象观测站的日降水资料、CMAP格点降水、国家气候中心74项和美国NOAA CPC 40项指数资料、NCEP/NCAR再分析资料,利用经验正交公式(EOF)等方法分析华南夏季降水气候变化特征,查找其影响关键因子,使用粒子群-神经网络建模预报。结果表明:利用高相关因子的粒子群-神经网络建模预报,从近10a华南夏季降水回报结果对比来看,粒子群-神经网络效果略好于国家气候中心第二代海-陆-冰-气耦合的气候系统动力模式,动力模式好于逐步回归方法。从7年华南出现异常降水年份的预报试验来看,利用异常因子的粒子群-神经网络建模预报误差均小于动力模式预报,预报与实况同号率高达到85.7%,高于动力模式,可见粒子群-神经网络建模预测具有很好的应用前景。
Abstract:
Based on daily precipitation data of 110 stations from Guangdong, Guangxi and Hainan, CMAP precipitation data, 74 indices from NCC and 40 indices from NCC and NOAA CPC and NCEP/NCAR reanalysis data during 1961-2013, the climatic characteristics of raining in summer (June-August) of South China was analyzed by using EOF to find the key influencing index and use PSO-Artificial Neutral Network modeling. The results show that:From comparison of perdition results of summer precipitation of recent 10 years in the south China, The prediction effect of PSO-Artificial Neutral Network which uses 27 predictors is slightly better than the NCC_CSM model; meanwhile, NCC_CSM is better than the stepwise regression method. The prediction error of PSO-Artificial Neutral Network by using the abnormal predictors is less than the NCC_CSM model, and the consistency proportion between the prediction and observation of summer precipitation anomaly percentage reached 85.7%, far higher than the NCC_CSM model. PSO-Artificial Neutral Network which uses the abnormal predictors has a good result to correct the prediction of the NCC_CSM model in the abnormal precipitation years and has good application prospects.

相似文献/References:

[1]植江玲.西太平洋暖池热含量年代际变化及其与东北夏季降水关系[J].气象研究与应用,2015,36(04):8.
　Zhi Jiang-ling.Interdecadal variation of thermal content of Western pacific warm pool and its relationship with summer precipitation in northeastern of China[J].Journal of Meteorological Research and Application,2015,36(02):8.
[2]黎燚隆,章新平,尚程鹏.洞庭湖流域夏季降水特征及旱涝年份大气环流分析[J].气象研究与应用,2018,39(01):1.
　Li Yanyi,Zhang Xinping,Shang Chengpeng.Characteristics of summer precipitation in Dongting Lake basin and analysis of atmospheric circulation in drought and flood years[J].Journal of Meteorological Research and Application,2018,39(02):1.
[3]桑林,余乐福.华北地区夏季降水的气候特征分析[J].气象研究与应用,2018,39(01):24.
　Sang Lin,Yu Lefu.Analysis of summer precipitation characteristics in North China[J].Journal of Meteorological Research and Application,2018,39(02):24.
[4]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.
　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(02):1.
[5]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(02):8.[doi:10.19849/j.cnki.CN45-1356/P.2022.1.02]

备注/Memo

备注/Memo:
收稿日期:2014-11-25。
基金项目:广西自然科学基金资助(2013GXNSFBB053010);广西自然科学基金资助(2013GXNSFAA019273);2013年度公益性行业(气象)科研项目"亚洲地区动力-统计相结合的月-季节尺度降水客观预测系统的研究与应用"资助
作者简介:覃卫坚(1971-),男,广西上林县人,博士研究生,高工,主要从事天气气候动力学研究,(E-mail) qinweijian2008@126.com
更新日期/Last Update: 1900-01-01