A modelling study for predicting temperature and precipitation variations

作者：Navazi Azadeh; Karbassi Abdolreza^*; Mohammadi Shapour; Monavari Seyed Masoud; Zarandi Saeed Motesaddi

来源：International Journal of Global Warming, 2017, 11(4): 373-389.

DOI：10.1504/IJGW.2017.10004272

• climate change
• global warming
• prediction
• urban environment
• climatic parameters
• artificial neural network
• ANN

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 degrees C and annual precipitation increase of 3.4 mm were also found to be likely to occur in Tehran by 2021.

• 出版日期2017