Arid
DOI10.1007/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
Corresponding AuthorLi, WD (corresponding author), Lanzhou Univ, Ctr Data Sci, Sch Math & Stat, Lab Appl Math & Complex Syst, Lanzhou 730000, Peoples R China.
JournalCLIMATE DYNAMICS
ISSN0930-7575
EISSN1432-0894
Year Published2021-08
Abstract in EnglishAccurate 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.
Keyword in EnglishPrecipitation forecasting Spatio-temporal information Deep learning Feature extraction Semi-arid area
SubtypeArticle ; Early Access
Language英语
Indexed BySCI-E
WOS IDWOS:000682633800001
WOS KeywordMODEL
WOS SubjectMeteorology & Atmospheric Sciences
WOS Research AreaMeteorology & Atmospheric Sciences
Source Institution兰州大学
Document Type期刊论文
Identifierhttp://119.78.100.177/qdio/handle/2XILL650/362873
Affiliation[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
Recommended Citation
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).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Weide]'s Articles
[Gao, Xi]'s Articles
[Hao, Zihan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Weide]'s Articles
[Gao, Xi]'s Articles
[Hao, Zihan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Weide]'s Articles
[Gao, Xi]'s Articles
[Hao, Zihan]'s Articles
Terms of Use
No data!
Social Bookmark/Share

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.