Statistical and machine learning methods applied to the prediction of different tropical rainfall types
Statistical and machine learning methods applied to the prediction of different tropical rainfall types
复制标题
统计和机器学习方法应用于不同热带降雨类型的预测
DOI：
10.1088/2515-7620/ac371f
复制
发表时间：
2021
影响因子：
2.9
通讯作者：
Sun, Chunmei
中科院分区：
文献类型：
--
作者：
Wang, Jiayi;Wong, Raymond K. W.;Jun, Mikyoung;Schumacher, Courtney;Saravanan, R.;Sun, Chunmei
从大尺度环境变量预测降雨仍然是气候模式面临的一个挑战性问题，目前还不清楚数值方法在没有较小（风暴）尺度信息的情况下如何预测降雨的真实特征。这项研究探讨了三种统计和机器学习方法预测热带太平洋3小时降雨发生和强度的能力，使用降雨观测，全球降水测量（GPM）卫星雷达和MERRA-2再分析的温度和湿度的大尺度环境剖面。我们还将雨分为不同类型（深对流，层状和浅对流），因为它们不同的运动学和热力学结构，可能会以不同的方式响应大尺度环境。我们的期望是，流行的机器学习方法（即神经网络和随机森林）将优于标准的统计方法（广义线性模型），因为它们的结构更灵活，特别是在预测每种降雨类型的降雨率的高度偏斜分布方面。然而，这些方法都没有明显的区别，而且每种方法仍然存在预测降雨过于频繁和不能完全捕捉降雨率分布高端的问题，这两个问题都是气候模型中的常见问题。这项研究的一个意义是，机器学习工具必须仔细评估，并不一定适用于解决所有的大数据问题。另一个含义是，传统的气候模型方法不足以预测极端降雨事件，需要寻求其他途径。
Predicting rain from large-scale environmental variables remains a challenging problem for climate models and it is unclear how well numerical methods can predict the true characteristics of rainfall without smaller (storm) scale information. This study explores the ability of three statistical and machine learning methods to predict 3-hourly rain occurrence and intensity at 0.5 resolution over the tropical Pacific Ocean using rain observations the Global Precipitation Measurement (GPM) satellite radar and large-scale environmental profiles of temperature and moisture from the MERRA-2 reanalysis. We also separated the rain into different types (deep convective, stratiform, and shallow convective) because of their varying kinematic and thermodynamic structures that might respond to the large-scale environment in different ways. Our expectation was that the popular machine learning methods (ie, the neural network and random forest) would outperform a standard statistical method (a generalized linear model) because of their more flexible structures, especially in predicting the highly skewed distribution of rain rates for each rain type. However, none of the methods obviously distinguish themselves from one another and each method still has issues with predicting rain too often and not fully capturing the high end of the rain rate distributions, both of which are common problems in climate models. One implication of this study is that machine learning tools must be carefully assessed and are not necessarily applicable to solving all big data problems. Another implication is that traditional climate model approaches are not sufficient to predict extreme rain events and that other avenues need to be pursued.
登录
查看更多内容
使用广义线性模型观测和模拟降雨的预测统计表示。
影响因子：
4.9
作者：
Yang,Junho;Jun,Mikyoung;Schumacher,Courtney;Saravanan,R
通讯作者：
Saravanan,R
影响因子：
6.8
作者：
O'Gorman, Paul A.;Dwyer, John G.
通讯作者：
Dwyer, John G.
机器学习辅助开发对流云和层状云群模型
影响因子：
6.8
作者：
Hagos S
通讯作者：
Hagos S
中尺度对流系统的形成、特征和变化性质
影响因子：
42.1
作者：
Schumacher, Russ S.;Rasmussen, Kristen L.
通讯作者：
Rasmussen, Kristen L.
影响因子：
4.9
作者：
Benjamin A. Stephens;C. Jackson;B. Wagman
通讯作者：
Benjamin A. Stephens;C. Jackson;B. Wagman