Ali M. AL-Salihi - Department of Atmospheric Sciences, College of Science, Al-Mustansiriyah University, Baghdad, Iraq.
Safaa A. AL-Kinani - Department of Environment and Water, Ministry of Science and Technology, Baghdad, Iraq.

The present paper involves Outgoing longwave radiation (OLR) under clear-sky condition modeling employing three measured meteorological parameters (Air surface temperature, Relative humidity and Cloud fraction). Dataset retrieved from NASA Atmospheric Infrared Sounder (AIRS), from 2003 to 2015 was employed to develop two models to estimate OLR values in Iraq using the multiple linear regression (MLR) and Artificial Neural Network (ANN) approach. For the entire period, the mentioned meteorological parameters were highly correlated with estimated OLR. Comparisons among selected cities (Mosul, Baghdad, and Basrah) for the year 2016 showed close agreement between the estimated and measured OLR. Mosul at the north of the Iraq, showed the lowest root mean square error (RMSE) and correlation coefficient (R) ranged between (1.3853 and 4.4966) and (0.9929 and 0.9993), respectively for the two developed models (MLR and ANN) respectively, indicating model s efficiency and accuracy. Statistical analysis in term of β showed that surface temperature (1.823 to 2.311) tended to provide a high contribute to OLR values. These results indicate the advantage of using the AIRS data and both of correlation analysis and computing system to investigate the impact of the meteorological parameters on OLR over the study area

longwave,Air surface temperature,AIRS,Neural Network,