<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE ArticleSet PUBLIC "-//NLM//DTD PubMed 2.6//EN" "http://www.ncbi.nlm.nih.gov/corehtml/query/static/PubMed.dtd">
<ArticleSet>
<Article>
<Journal>
				<PublisherName>University of Tehran</PublisherName>
				<JournalTitle>International Journal of Environmental Research</JournalTitle>
				<Issn>1735-6865</Issn>
				<Volume>6</Volume>
				<Issue>3</Issue>
				<PubDate PubStatus="epublish">
					<Year>2012</Year>
					<Month>06</Month>
					<Day>16</Day>
				</PubDate>
			</Journal>
<ArticleTitle>Prediction of Climate Change Induced Temperature Rise in Regional
Scale Using Neural Network</ArticleTitle><FirstPage>677</FirstPage>
			<LastPage>688</LastPage>
			<Language>en</Language>
<AuthorList>
<Author>
					<FirstName>Kh. </FirstName>
					<LastName>Ashrafi</LastName>
					<Affiliation>Graduate Faculty of Environment, University of Tehran, P.O.BOX 14155-6135, Tehran, Iran</Affiliation>
				</Author>
<Author>
					<FirstName>M. </FirstName>
					<LastName>Shafiepour</LastName>
					<Affiliation>Graduate Faculty of Environment, University of Tehran, P.O.BOX 14155-6135, Tehran, Iran</Affiliation>
				</Author>
<Author>
					<FirstName>L. </FirstName>
					<LastName>Ghasemi</LastName>
					<Affiliation>Graduate Faculty of Environment, University of Tehran, P.O.BOX 14155-6135, Tehran, Iran</Affiliation>
				</Author>
<Author>
					<FirstName>B. </FirstName>
					<LastName>Araabi</LastName>
					<Affiliation>Faculty of Electrical and Computer Engineering, University of Tehran, Tehran, Iran</Affiliation>
				</Author>
</AuthorList>
			<History>
				<PubDate PubStatus="received">
					<Year>2012</Year>
					<Month>06</Month>
					<Day>16</Day>
				</PubDate>
			</History>
		<Abstract><![CDATA[The objective of this paper is to develop an artificial neural network (ANN) model which can beused to predict temperature rise due to climate change in regional scale. In the present work data recorded overyears 1985-2008 have been used at training and testing steps for ANN model. The multilayer perceptron(MLP) network architecture is used for this purpose. Three applied optimization methods are backpropagation(BP) (in both input selection and weight optimization), genetic algorithm (GA) (in both input selection andweight optimization) and combined GA-particle swarm optimization (PSO) (input selection by GA andweight optimization by PSO). In this framework, natural and anthropogenic parameters which affect theincoming solar radiation are considered in order to predict the climate change induced temperature rise inregional scale. Inputs of ANN model are mean temperature, dew point temperature, relative humidity, windspeed, solar radiation, cloudiness, rainfall, station-level pressure (QFE) and greenhouse gases. For predictingmonthly mean temperature, input data include one month, six months, 12 months and 24 months beforerecorded data. In this work, nine stations namely Tehran, Mashhad, Ramsar, Orumiyeh, Sanandaj, Yazd,Ahwaz, Bandar Abbas and Chabahar in nine different climatic region of Iran are chosen to determine thetemperature rise over Iran. Results show that the averaged minimum square errors (MSE) are 0.0196, 0.0224and 0.0228 for ANN-BP, ANN-GA and ANN-GA-PSO methods, respectively. The ANN model associatedwith BP optimization method predict annual mean temperature rise as 0.44, 0.49, 0.20, 0.12, 0.17, 0.46, 0.41,0.06 and 0.01°C after 10 years for mentioned stations, respectively. These values show the averagetemperature rise of 0.26 °C after 10 years (the base year is 2008) for Iran.]]></Abstract>
		<ObjectList>
			<Object Type="keyword">
			<Param Name="value">Climate change</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Temperature rise</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Neural network</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Back propagation</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Genetic algorithm</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Particle swarm optimization</Param>
			</Object>
		</ObjectList>
</Article>
</ArticleSet>