文章基本信息

标题：The Potential of Artificial Neural Network Technique in Daily and Monthly Ambient Air Temperature Prediction
本地全文：下载
作者：Mahboubeh Afzali ; Afsaneh Afzali ; Gholamreza Zahedi 等
期刊名称：International Journal of Environmental Science and Development
印刷版ISSN：2010-0264
出版年度：2012
卷号：3
期号：1
页码：33-38
DOI：10.7763/IJESD.2012.V3.183
摘要：Ambient air temperature prediction is of a concern in environment, industry and agriculture.The increase of average temperature results in natural disasters, higher energy consumption, damage to plants and animals and global warming.Ambient air temperature predictions are notoriously complex and stochastic models are not able to learn the non-linear relationships among the considered variables.Artificial Neural Network (ANN) has potential to capture the complex relationships among many factors which contribute to prediction.The aim of this study is to develop ANN for daily and monthly ambient air temperature prediction in Kerman city located in the south east of Iran.The mean, minimum and maximum ambient air temperature during the years 1961-2004 was used as the input parameter in Feed Forward Network and Elman Network.The values of R, MSE and MAE variables in both networks showed that ANN approach is a desirable model in ambient air temperature prediction, while the results of one day ahead mean temperature and one month ahead maximum temperature are more precise using Elman network.
关键词：Artificial neural network; feed forward network; elman network; temperature