摘要
2017年12月~2018年2月冬季,在中国长江中下游流域发生了两次强度强、范围广的强雨雪冰冻天气。在第一次强降雪天气中,由于2018年1月3~4日和5~8日两阶段降雪在中国东部落区高度重叠,导致了较为严重的灾害。为了预测日积雪深度,利用2017年12月~2018年2月和2007年12月~2008年2月这两个时间段上的国家测站日值数据,利用CART决策树算法根据各气象要素生成一个预测当天是否有积雪的二元判别决策树模型。从决策树结构中可以看出,前一日的积雪深度、日最高气温、日平均气温、日最低相对湿度等要素对预测结果的影响重大。且两决策树的结构相似度极高,故该模型对是否有积雪的预测存在普适性。随后利用深度学习方法训练两个时间段上所有预测为有积雪的个例,建立预测积雪深度的回归模型,结果表明,利用该模型训练得到的误差较小,但不足之处在于,预测极端降雪个例的误差大于普通降雪个例。将决策树模型与深度学习模型串接,便能得到预测当天是否有积雪,及积雪深度的模型。相比于前人的研究,该模型能拟合更复杂的特征,得到更精确的预测,使用2018年的数据也能更好地模拟当前的气候背景。
During the winter from Dec. 2017 to Feb 2018,two strong rain and snow weather processes along with freezing took place in middle and lower reaches of China’s Yangtze River basin. During the first process,severe disasters were caused by two periods of snowfall during 3-4 Jan 2018 and 5-8 Jan 2018 which overlaps mostly.In order to predict the daily snow depth,national weather station observations during Dec. 2017 to Feb. 2018 and Dec. 2007 to Feb. 2008 were imported respectively to a CART decision tree model to predict whether there were accumulated snow on that day. Both decision trees show that the snow depth on the previous day,daily maximum temperature,daily average temperature,daily minimum relative humidity and so on have primary influence on prediction result. And the structure of both decision trees resemble each other,which implies that the condition to form snow accumulation is universal,and the two decision trees are representative of the rule of snow accumulation.Next,a regression model using deep learning techniques is trained in order to predict the value of snow depth given other meteorlogical variables. The results show that the model is accurate in snow depth prediction while its performance is limited for instances with a larger snow depth. As a result,by combining the decision tree model and deep learning model,a model will be got which predicts snow depth. The new model is more complex to describe the statistical properties of snow accumulation.
作者
张远汀
龚伟伟
叶钰
徐希源
徐勋建
蔡泽林
陆佳政
韩俊浩
叶飞
许婧
ZHANG Yuan-ting;GONG Wei-wei;YE Yu;XU Xi-yuan;XU Xun-jian;CAI Ze-lin;LU Jia-zheng;HAN Jun-hao;YE Fei;XU Jing(Huayun Information Technology Engineering Co.,Ltd.,Beijing 100081,China;State Key Laboratory of Disaster Prevention&Reduction for Power Grid Transmission and Distribution Equipment,Changsha 410129,China;State Grid Hunan Electric Power Company Disaster Prevention and Reduction Center,Changsha 410129,China;Global Energy Interconnection Research Institute Co.,Ltd.,Beijing 102209,China)
出处
《科学技术与工程》
北大核心
2019年第15期58-69,共12页
Science Technology and Engineering
基金
国家电网公司科技项目(5216a01600W5)资助
关键词
电网
强雨雪
决策树
深度学习
power grid
strong rainfall and snowfall
decision tree
deep learning