---

Solar radiation data play an important role in solar energy relevant researches. These data are not available for some locations due to the absence of the meteorological stations. Therefore, solar radiation data have to be predicted by using solar radiation estimation models. This study presents an integrated Artificial Neural Network (ANN) approach for estimating solar radiation potential over Iran based on geographical and meteorological data. For this aim, the measured data of 31 stations spread over Iran were used to train Multi-Layer Perceptron (MLP) neural networks with different input variables, and solar radiation was the output. The accuracy of the models was evaluated using the statistical indicators of Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and Correlation Coefficient (R); hence, the best model in each category was identified. The Stepwise Multi NonLinear Regression (MNLR) method was used to determine the most suitable input variables. The results obtained from the ANN models were compared with the measured data. The MAPE and RMSE were found to be 2.98% and 0.0224, respectively. The obtained R value was about 99.85% for the testing data set. The results testify to the generalization capability of the ANN model and its excellent ability to predict solar radiation in Iran.

---

Geographic information and analysis provide a wide range of data and techniques to monitor and manage natural resources. As an important case, in arid and semi-arid areas, water management is critical for both local governance and citizens. As a result, the estimation of water potential brought by snowmelt runoff and rainfalls seems to be very useful and important for these areas. Hydrological modeling needs vast knowledge about integrating all relating parameters. In this work, different data sources including the remote sensing observations, meteorological and geological data are integrated to supply spatially detailed inputs for Snowmelt Runoff Modeling in a watershed, located in Simin-Dasht basin in the northeast of Tehran, Iran. Because of high temporal frequency and suitable spatial coverage, MODIS optical images have been chosen to map snow cover. The MODIS 8-day snow map product with spatial resolution of 500m (MOD10A2.5) is used to compute the snow cover area. In addition, during the snowmelt period in 2006-2007, archived meteorological and geological data are used to provide snow runoff modeling (SRM) parameters and variables. Also Landsat ETM+ images with better spatial resolution (30m) and less temporal coverage (16 days) are used in 2007 snowmelt period to compare the model accuracy with same conditions. Evaluation of the runoff outputs in both of models reveals good agreement with real data that prove SRM capability in modeling basin’s daily and weekly runoff. Model accuracy shows better satisfactory of snow runoff modeling results within snow cover area derived from Landsat ETM+ data and MODIS snow product was less accurate in modeling. Although using MODIS model accuracy was less, but still it is recommended due to less further process and providing better temporal coverage during snowfall and snowmelt season. Future works in this criterion could be concentrated on SRM forecast improvement using fusion with other measurements or combining physical models.

---

Geographic information and analysis provide a wide range of data and techniques to monitor and manage natural resources. As an important case, in arid and semi-arid areas, water management is critical for both local governance and citizens. As a result, the estimation of water potential brought by snowmelt runoff and rainfalls seems to be very useful and important for these areas. Hydrological modeling needs vast knowledge about integrating all relating parameters. In this work, different data sources including the remote sensing observations, meteorological and geological data are integrated to supply spatially detailed inputs for Snowmelt Runoff Modeling in a watershed, located in Simin-Dasht basin in the northeast of Tehran, Iran. Because of high temporal frequency and suitable spatial coverage, MODIS optical images have been chosen to map snow cover. The MODIS 8-day snow map product with spatial resolution of 500m (MOD10A2.5) is used to compute the snow cover area. In addition, during the snowmelt period in 2006-2007, archived meteorological and geological data are used to provide snow runoff modeling (SRM) parameters and variables. Also Landsat ETM+ images with better spatial resolution (30m) and less temporal coverage (16 days) are used in 2007 snowmelt period to compare the model accuracy with same conditions. Evaluation of the runoff outputs in both of models reveals good agreement with real data that prove SRM capability in modeling basin’s daily and weekly runoff. Model accuracy shows better satisfactory of snow runoff modeling results within snow cover area derived from Landsat ETM+ data and MODIS snow product was less accurate in modeling. Although using MODIS model accuracy was less, but still it is recommended due to less further process and providing better temporal coverage during snowfall and snowmelt season. Future works in this criterion could be concentrated on SRM forecast improvement using fusion with other measurements or combining physical models.

---

In this study, two widely used artificial intelligence techniques, i.e. Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS), were applied for global solar radiation (GSR) prediction in Isfahan Province, Iran. Different sets of meteorological data were used as inputs to specify the best set of inputs. Relative humidity and precipitation had an unfavorable effect on radiation prediction, while the number of days, sunshine duration, minimum temperature, maximum temperature, daylight hours and clear-sky radiation were effective parameters to determine GSR. Using the mentioned parameters as inputs, 6-5-1 architecture had the best performance without overtraining. In ANFIS models, ' triangular-shaped' had the highest performance amongst different types of membership functions. Resulted correlation coefficients and errors showed that ANN was generally better than ANFIS for this purpose.