Circulation Pattern Classification of Persistent Heavy Rainfall in Jianghuai Region Based on the Transfer Learning CNN Model

Newly reconstructed dataset of regional persistent historical heavy rain events in 1981-2018,corresponding daily rainfall data of 2474 observational stations in China,and NCEP/NCAR global reanalysis data of daily geopotential height field are used to study the persistent heavy rain events in Jianghu...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Ying yong qi xiang xue bao = Quarterly journal of applied meteorology 2021-03, Vol.32 (2), p.233-244
Hauptverfasser:	Cai, Jinqi, Tan, Guirong, Niu, Ruoyun
Format:	Artikel
Sprache:	chi ; eng
Schlagworte:	Analogs Artificial neural networks Atmospheric precipitations Circulation Circulation patterns Classification Coefficients Correlation coefficient Correlation coefficients Daily precipitation Daily rainfall data Datasets Distribution Dynamic height Empirical analysis Fields Geopotential Geopotential height Heavy rainfall analysis heavy rainfall patterns Height Learning Model accuracy Neural networks Orthogonal functions Pattern classification Rain Rainfall Rainfall patterns residual networks Similarity coefficient method Spatial distribution Statistical analysis Statistical methods Training Transfer learning Typing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!