蒋薇,刘芸芸,陈鹏,张志薇. 2021. 基于先兆信号的江苏夏季降水客观预测方法研究[J]. 气象学报, (0):-, doi:10.11676/qxxb2021.057
基于先兆信号的江苏夏季降水客观预测方法研究
Prediction of summer precipitation based on the Precursory Factors in Jiangsu Province
投稿时间:2020-11-25  修订日期:2021-06-10
DOI:10.11676/qxxb2021.057
中文关键词:  夏季降水,季节预测,先兆信号,深度神经网络,动态权重集合方案
英文关键词:Summer precipitation  Seasonal prediction  Precursory signals  Deep Neural Network (DNN)  Dynamic weight set scheme
基金项目:中国气象局预报员专项(CMAYBY2020-164)、江苏省气象局科研项目重点项目(KZ202004)和江苏省气象局科研项目面上项目(KM202009)共同资助
作者单位邮编
蒋薇 江苏省气候中心 210008
刘芸芸 国家气候中心 100081
陈鹏 江苏省气象信息中心
江苏省气象信息中心 
210008
张志薇 江苏省气象科学研究所 210008
摘要点击次数: 140
全文下载次数: 113
中文摘要:
      利用1961-2019年江苏省67个站点降水量和气候指数数据集等资料,选取大气环流、海温和积雪等先兆信号的不同组合作为预测因子方案,使用不同的机器学习方法建立预测模型,开展对江苏夏季降水的预测试验,对预测效果进行了对比分析,并探讨了不同预测因子方案对江苏省夏季降水预测结果的潜在影响。研究结果表明,利用深度神经网络(Deep Neural Network, DNN)方法对江苏夏季降水的预测效果较传统统计方法和其他机器学习方法有一定优势。进一步通过对比5种不同的预测方案与DNN方法相结合的预测结果,发现DNN结合动态权重集合方案对江苏省夏季降水的预测技巧最高,其独立样本预测检验结果稳定,2015-2019年的平均PS评分为76.0分,距平符号一致率为62%,ACC达0.35,尤其在江苏中南部的预测技巧更高,具有业务应用价值。不同预测因子方案对比分析表明,大气环流因子在江苏夏季降水预测中占主要贡献,海温因子和积雪等其他因子有正贡献。因此DNN结合动态权重集合的方案预测效果最好,说明使用综合性预测因子以及集合方案有助于提升季节预测准确性。
英文摘要:
      Based on precipitation data of 67 national stations in Jiangsu Province and a series of climatic indices from 1961 to 2019, the prediction experiments on summer precipitation in Jiangsu Province is carried out through different machine learning methods accompanied by five prediction schemes with different combinations of precursor signals, including atmospheric circulation, sea surface temperature, snow cover, etc. It is shown that the deep neural network (DNN) method has certain advantages over traditional statistical methods and other machine learning methods on the prediction of summer precipitation in Jiangsu Province. The comparison of the prediction results of five different prediction schemes with the DNN method further indicated that the model of DNN mixed dynamic weight set scheme (DMDW) has the highest prediction skills for summer precipitation in Jiangsu Province. The results of the independent sample test by DMDW are stable, with the five-year average PS score of 76.0, the symbol consistent rate of 62%, and the ACC of 0.35. The Model in the operational application shows its higher accuracy of precipitation forecasting over central and southern Jiangsu province. Furthermore, the potential impacts of the precursor signals in the prediction factor schemes on the prediction accuracy of the summer precipitation in Jiangsu Province are also investigated in this work. The atmospheric circulation factors play a major role in the summer precipitation prediction in Jiangsu province, while other factors such as SST and snow cover have positive contributions. Therefore, the DMDW model with the comprehensive precursory factors has the best prediction effect, which can improve effectively the accuracy of seasonal prediction in summer precipitation in Jiangsu Province.
查看全文   查看/发表评论  下载PDF阅读器
分享按钮