A modelling study for predicting temperature and precipitation variations
by Azadeh Navazi; Abdolreza Karbassi; Shapour Mohammadi; Seyed Masoud Monavari; Saeed Motesaddi Zarandi
International Journal of Global Warming (IJGW), Vol. 11, No. 4, 2017

Abstract: The trends of climate change and consequently global warming have put pressure on the urban environment and have led to serious environmental damages. The main objective of this study is to make a ten-year prediction of climatic parameters in Tehran in order to identify the impacts of climate change on urban environments and provide adaptation strategies to be used in future studies. For this purpose, artificial neural network (ANN) algorithms were employed. For the first time, a 30-year mean data of 'wind speed', 'dry-bulb temperature', 'wet-bulb temperature', 'mean daily temperature', 'dew point temperature', 'relative humidity' and 'precipitation' were investigated for their ten-year prediction using feed-forward ANN and back propagation algorithm. The root mean square error (RMSE) of the mentioned parameters in optimisation model was obtained to be 0.0307, 0.0625, 0.0566, 0.0382, 0.0214, 0.0758 and 0.0466, respectively. Annual temperature rise of 0.04°C and annual precipitation increase of 3.4 mm were also found to be likely to occur in Tehran by 2021.

Online publication date: Wed, 19-Apr-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Global Warming (IJGW):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com