基于朴素贝叶斯算法的流域降水预测方法.pdfVIP

第36卷第4期 水 利 水 电科 技 进 展 2016年7月 Vol.36 No.4 Advances in Science and Technology of Water Resources Jul. 2016 DOI:10.3880/ j.issn.1006 7647.2016.04.012 基于朴素贝叶斯算法的流域降水预测方法 1 2 2 2 2 黄  炜 ,李雪真 ,赵  嘉 ,赵丽华 ,李臣民 (1.江苏省水文水资源勘测局,江苏 南京  210029;2.河海大学计算机与信息学院,江苏 南京  210098) 摘要:为了在降水成因尚不明确的情况下有效利用相关历史资料提高降水预报水平,提出了基于朴 素贝叶斯算法的流域降水预测方法。 以东江流域为例,通过构造不同降水数据特征集预测流域内 降水情况,并与传统时间序列方法和BP神经网络方法进行预测准确率对比验证,结果表明,基于 朴素贝叶斯算法的降水预测方法取得了比传统时间序列方法和BP神经网络方法更好的降水预测 效果。 关键词:降水预测;朴素贝叶斯算法;贝叶斯估计;F-measure评价方法 中图分类号:TV125;P338      文献标志码:A      文章编号:1006 7647(2016)04 0065 05 1 2 A precipitation forecasting method for a river basinbased on naiveBayes algorithm/ / HUANGWei ,LIXuezhen , 2 2 2 ZHAOJia ,ZHAOLihua ,LIChenmin (1.JiangsuProvinceHydrology and WaterResourcesInvestigationBureau,Nanjing 210029,China;2. College of Computer and Information Technology Engineering, Hohai University, Nanjing 210098, China) Abstract:In order to effectively use available historical observation data for precipitation forecasting in the case of an uncertain cause of precipitation,a precipitation forecasting method was developed based on the naive Bayes algorithm. UsingtheDongjiangBasinasanexample,arichsetoffeatureswasconstructedbasedonthebasin’sprecipitationdataand meteorological knowledge. Theforecasting accuracy of theproposedmethodwascomparedwiththoseof thetraditional time series method and the BP neural network method. The result shows that the proposed method outperformed both the traditional time series method and the BP neural network method. Key words:precipitation forecasting;naive Bayes algorithm;Bayes estimati