multi-linear regression

Prediction of groundwater level fluctuations is an essential for planning in arid and semi-arid regions. In this study, artificial neural network models, ARIMA time series and multivariate linear regression models were used to predict groundwater fluctuations of two piezometers located in Kerman plain. In order to achieve this goal, the depth of groundwater of the monthly piezometers was used during the years 2002-2013. The results of studying different models of ARIMA model showed that the ARIMA (0,1,1) and (2,0,2) for south Baghin piezometer and ARIMA (1,1,1) and (2,0,0) for Airport areas piezometer are the best-fit time series model with the data. In the model of MLP and RBF artificial neural network, MLP with 2 and 4 layers of hidden and RBF with 8 and 10 hidden layers for southern Baghin piezometers and the airport areas have the best fit with the data. In multivariate linear regression modeling, for each of the two piezometers, the best correlations of the multivariable linear regression model show that the multivariate linear regression relationship of groundwater depth of the current month is a function of groundwater depth of one month prior; in other words, the depth of water the ground water level has the highest dependence on groundwater depth of its prior month. The results showed that prediction of groundwater depth by multivariate linear regression model is better than Neural Network and ARIMA model.

The base for hydrology studies is accurate data. However, the gaps and shortage of sufficient data exist n the most hydrology data such as  underground water data as the most important and cheapest water source,  lack of  data  take places due to various reasons such as Inability to measure and faille to register statistics. Missing data or incorrect statistics, Therefore, estimating the missing data is necessary which depending on the conditions of each station may demand a specific method to yield the best solution. In this article regression methods were applied in restoring underground water contour of piezometer stations of Lorestan province. In this regards, after deliberate deletion of about 15% the monthly observation data for four consecutive years in 22 piezometer stations in Alashtar of Lorestan province, their values are estimated and assessed them through RMSE and percentage of relative deviation of mean module. Finally, the obtained results are show that the simple linear regression method outperforms other methods.

This Paper Investigates and estimates the variations of sea surface salinity (SSS) in the Persian Gulf using moderate resolution imaging spectro-radiometer (MODIS) data on the Aqua satellite and the advanced microwave sounding Unit-B (AMSU-B) sensor on the NOAA-16 satellite in order to use remote sensing science for a more efficient and with more time distribution of salinity in the Persian Gulf. In this research a multiple-linear regression model in R software was developed using the data of MODIS and AMSU-B sensors. The data were obtained during a period of one year and fed to the R software. After processing the data in the R software, the correlation coefficient (R2) for salinity was calculated between field data and MODIS and AMSU-B sensors data. The correlation coefficients for MODIS and AMSU-B sensors were 0.86 and 0.85, respectively. Also, root mean square error (RMSE) between satellite data and in Situ data for salinity using MODIS and AMSU-B sensors were 0.62 Psu and 0.07 Psu respectively. The results show the accuracy of sensors for determining the sea surface salinity pattern in this study.