This study aims to investigate how changes in meteorological indicators affect groundwater resources, and hence to predict groundwater levels using these indicators, particularly in regions experiencing drought and subsidence. Precipitation, temperature, evapotranspiration and precipitable water vapor (PWV) are important meteorological parameters to predict groundwater levels. Two subsidence areas with different weather conditions were selected to conduct a comprehensive study on the effect of temperature and precipitation on groundwater level changes. The correct locations of the two subsidence areas were determined by analyzing Interferometric Synthetic Aperture Radar (InSAR) images of Sentinel-1A using the small baseline subset algorithm. The interferograms were processed to correct tropospheric effects using the advanced integration method. Specifying the exact locations of the two areas, the meteorological parameters were downscaled using the Statistical DownScaling Model (SDSM), synoptic observations, meteorological data, and the General Circulation Model (GCM). An Artificial Neural Network (ANN) was then employed to predict the groundwater level changes as a function of meteorological data, including Global Positioning System (GPS)-based PWV and the evapotranspiration index. The trained ANN, along with the downscaled meteorological indicators, was used to predict groundwater level changes over two time periods. In the first period, the prediction was performed over the current years to investigate the performance of the method using the available data, whereas in the second period, the prediction was performed for the coming years, up until 2030. The results confirmed the high performance of the prediction algorithm, and the importance of including PWV and evapotranspiration in groundwater level predictions. The Pearson correlation coefficient was used to check the relationship between groundwater level changes and meteorological variables. The statistical significance of these coefficients was tested at the significance level α=0.05. In more than 80% of the cases, the correlation coefficients were statistically significant, reaching more than 0.70 in some of the months. It is also observed that an increase in the depth of groundwater level has an obvious relationship with an increase in temperature and a decrease in rainfall.@en

Precipitation is an important meteorological indicator that has a direct and significant impact on ecology, agriculture, hydrology, and other vital areas of human health and life. It is therefore essential to monitor variations of this parameter at a global and local scale. To monitor and predict long-term changes in climate elements, Global Circulation Models (GCMs) can provide simulated global-scale climatic processes. Due to the low spatial resolution of these models, downscaling methods are required to convert such large-scale information to regional-scale data for local applications. Among the downscaling methods, the Statistical DownScaling Model (SDSM) and the Artificial Neural Networks (ANNs) are widely used due to their low computational volume and suitable output. These models mainly require training data, and generally, the reanalysis data obtained from the National Center for Environmental Prediction (NCEP) and European Centre for Medium-range Weather Forecasts (ECMWF) are used for this purpose. With an optimal downscaling method, instead of applying the humidity indices extracted from ECMWF data, the outputs of the function-based tropospheric tomography technique obtained from the Global Navigation Satellite System (GNSS) will be used. The reconstructed function-based tropospheric data is then fed to the SDSM and ANN methods used for downscaling. The results of both methods indicate that the tomography can increase the accuracy of the downscaling process by about 20 mm in the wet months of the year. This corresponds to an average improvement of 38% with regard to the root mean square error (RMSE) of the monthly precipitation.@en