Result: Lightning potential forecast over Nanjing with denoised sounding-derived indices based on SSA and CS-BP neural network

Title:
Lightning potential forecast over Nanjing with denoised sounding-derived indices based on SSA and CS-BP neural network
Authors:
JUN WANG, ZHENG SHENG, BIHUA ZHOU, SHUDAO ZHOU
Source:
Atmospheric research. 137:245-256
Publisher Information:
Amsterdam: Elsevier, 2014.
Publication Year:
2014
Physical Description:
print, 3/4 p
Original Material:
INIST-CNRS
Subject Terms:
Climatology, meteorology, Climatologie, météorologie, Sciences exactes et technologie, Exact sciences and technology, Terre, ocean, espace, Earth, ocean, space, Geophysique externe, External geophysics, Météorologie, Meteorology, Electricité atmosphérique, Atmospheric electricity, Algorithme recherche, Search algorithm, Algoritmo búsqueda, Algorithme rétropropagation, Backpropagation algorithm, Algoritmo retropropagación, Analyse spectre singulier, Singular spectrum analysis, Análisis espectro singular, Eclair, Lightning, Rayo, Electricité atmosphérique, Atmospheric electricity, Electricidad atmosférica, Modèle prévision, Forecast model, Modelo previsión, Orage, Thunderstorm, Tormenta, Pertinence prévision, Forecast skill, Pertinencia previsión, Prévision météorologique, Weather forecast, Predicción meteorológica, Réseau neuronal, neural networks, Red neuronal, Sondage atmosphérique, Atmospheric sounding, Sondeo atmosférico, CS-BP neural network, Cuckoo search algorithm, Lightning forecasting, Sounding-derived indices
Subject Geographic:
Asie, Asia, Chine, China, Extrême Orient, Far East, Extremo Oriente, Chine Est, Eastern China, China Este
Document Type:
Academic journal Article
File Description:
text
Language:
English
Author Affiliations:
National Defense Key Laboratory of Lightning Protection and Electromagnetic Camouflage, PLA Univ. of Sci. & Tech., Nanjing 210007, China
College of Meteorology and Oceanography, PLA Univ. of Sci. & Tech., Nanjing 211101, China
ISSN:
0169-8095
Access URL:
http://pascal-francis.inist.fr/vibad/index.php?action=search&terms=28024820
Rights:
Copyright 2015 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
External geophysics
Accession Number:
edscal.28024820
Database:
PASCAL Archive

Further Information

The method of using the back propagation neural network improved by cuckoo search algorithm (hereafter CS-BP neural network) to forecast lightning occurrence from sounding-derived indices over Nanjing is presented. The general distribution features of lightning activities over Nanjing area are summarized and analyzed first. The sounding data of 156 thunderstorm days and 164 fair-weather days during the years 2007-2012 are used to calculate the values of sounding-derived indices. The indices are pre-filtered using singular spectrum analysis (hereafter SSA) as preprocessing technique and 4 most pertinent indices (namely CAPE, K, JI and SWEAT) are determined as inputs of CS-BP network by a linear bivariate analysis and selection algorithm. The cases of 2007-2010 are used to train CS-BP network and the cases of 2011-2012 are used as an independent sample to test the forecast performance. Some statistical skill score parameters (namely POD, SAR, CSI, et.al.) indicate that the CS-BP model excels in lightning forecasting and has a better performance compared with the traditional BP neural network and linear multiregression method.