干旱区生态环境知识资源中心(Arid): Using deep learning for precipitation forecasting based on spatio-temporal information: a case study

Arid

DOI	10.1007/s00382-021-05916-4
	Using deep learning for precipitation forecasting based on spatio-temporal information: a case study
	Li, Weide; Gao, Xi; Hao, Zihan; Sun, Rong
通讯作者	Li, WD (corresponding author), Lanzhou Univ, Ctr Data Sci, Sch Math & Stat, Lab Appl Math & Complex Syst, Lanzhou 730000, Peoples R China.
来源期刊	CLIMATE DYNAMICS
ISSN	0930-7575
EISSN	1432-0894
出版年	2021-08
英文摘要	Accurate precipitation prediction is very important for social life and economical activity. Prediction of the quantitative precipitation in semi-arid areas is difficult because of rain scarcity and volatility. In this study, the 3-h precipitation situation in the semi-arid region of Lanzhou is predicted, that is, the precipitation status after 3 h is forecasted on 5 levels: 'no rain', 'light rain', 'moderate rain', 'heavy rain' and 'torrential rain'. We selected the meteorological data from 25 stations in and nearby Lanzhou, and processed the data with lag, difference and multiplication. Due to the large number of features, we use Mutual Information (MI) feature extraction method to reduce feature dimension, extract the features that are highly correlated with the target variable, and introduce spatio-temporal information in this way. Precipitation in semi-arid areas also has the problem of sample imbalance. We oversampled the data using Adaptive Synthetic (ADASYN) sampling approach and generated some minority class samples. Based on the MI feature extraction method and the ADASYN oversampling method, we constructed an Adaptive Synthesis and Mutual Information extraction Matrix (ASMI-M), which is the feature matrix used for model training. Then we proposed a Convolutional Neural Network and Long Short Term Memory (CNN-LSTM) model based on deep learning to predict the 3-h precipitation in Lanzhou City, which has achieved better prediction performance than traditional machine learning methods.
英文关键词	Precipitation forecasting Spatio-temporal information Deep learning Feature extraction Semi-arid area
类型	Article ; Early Access
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000682633800001
WOS关键词	MODEL
WOS类目	Meteorology & Atmospheric Sciences
WOS研究方向	Meteorology & Atmospheric Sciences
来源机构	兰州大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/362873
作者单位	[Li, Weide; Gao, Xi; Hao, Zihan; Sun, Rong] Lanzhou Univ, Ctr Data Sci, Sch Math & Stat, Lab Appl Math & Complex Syst, Lanzhou 730000, Peoples R China
推荐引用方式 GB/T 7714	Li, Weide,Gao, Xi,Hao, Zihan,et al. Using deep learning for precipitation forecasting based on spatio-temporal information: a case study[J]. 兰州大学,2021.
APA	Li, Weide,Gao, Xi,Hao, Zihan,&Sun, Rong.(2021).Using deep learning for precipitation forecasting based on spatio-temporal information: a case study.CLIMATE DYNAMICS.
MLA	Li, Weide,et al."Using deep learning for precipitation forecasting based on spatio-temporal information: a case study".CLIMATE DYNAMICS (2021).