Neural Network Development for the Forecasting of Upper Atmosphere Parameter Distributions

dc.contributor.author	Zhou, Qihou
dc.contributor.author	Morton, Yu
dc.contributor.author	Jeffrey, Martin
dc.date.accessioned	2008-12-15T22:09:24Z
dc.date.available	2008-12-15T22:09:24Z
dc.date.created	2003-12
dc.date.issued	2008-12-15T22:09:24Z
dc.identifier.uri	http://hdl.handle.net/2374.MIA/276
dc.description	This paper presents a neural network modeling approach to forecast electron concentration distributions in the 150â 600 km altitude range above Arecibo, Puerto Rico. The neural network was trained using incoherent scatter radar data collected at the Arecibo Observatory during the past two decades, as well as the Kp geomagnetic index provided by the National Space Science Data Center. The data set covered nearly two solar cycles, allowing the neural network to model daily, seasonal, and solar cycle variations of upper atmospheric parameter distributions. Two types of neural network architectures, feedforward and Elman recurrent, are used in this study. Topics discussed include the network design, training strategy, data analysis, as well as preliminary testing results of the networks on electron concentration distributions.	en
dc.language.iso	en	en
dc.title	Neural Network Development for the Forecasting of Upper Atmosphere Parameter Distributions	en
dc.type	Text	en_US
dc.type.genre	Article	en_US

Files in this item

Files	Size	Format	View
Neural Network ... ing of Upper Atmospher.pdf	315.4Kb	PDF