Concerns about water quality have widely increased in the last three decades; thus, water quality is now as important as its quantity. To study and model the quality of the Gamasiab River, its data, including chemical oxygen demand (COD), biological oxygen demand (BOD), dissolved oxygen (DO), total dissolved solids (TDS), total suspended solids in water, acidity, temperature, turbidity, and cations and anions were measured at four stations. Then, the correlations between these parameters and COD were measured using Pearson’s correlation coefficient and modeled by multilayer perceptron artificial neural network. In order to minimize the cost of the experiments performed and to provide the input parameters to the artificial neural network based on the correlations between the data and COD, the number of input parameters was reduced and finally, model No.3, with the Momentum training function and the TanhAxon activation function with the validation correlation coefficient of 0.97, mean absolute error of 2.88, and normalized root mean square error of 0.11 was identified as the most accurate model with the lowest cost. The results of the present study showed that the multilayer perceptron neural network has high ability in modeling the COD of the river, and those data correlated with each other have the greatest effect on the model. Moreover, the number of input parameters can be reduced in order to lower the cost of experiments while the performance of the model is not undermined.

A reliable model for any wastewater treatment plant (WWTP) is essential to predict its performance and form a basis for controlling the operation of the process. This would minimize the operation costs and assess the stability of environmental balance. This study applied artificial neural network-genetic algorithm (ANN-GA) and co-active neuro-fuzzy logic inference system (CANFIS) in comparison with ANN for predicting the performance of WWTP. The result indicated that the GA produces more accurate results than fuzzy logic technique. It was found that GA components increased the ANN ability in predicting WWTP performance. The normalized root mean square error (NRMSE) for ANN-GA in predicting chemical oxygen demand (COD), total suspended solids (TSS) and biochemical oxygen demand (BOD) were 0.15, 0.19 and 0.15, respectively. The corresponding correlation coefficients were 0.891, 0.930 and 0.890, respectively. Comparing these results with other studies showed that despite the slightly lower performance of the current model, its requirement for a lower number of input parameters can save the extra cost of sampling.

Grape is a strategic product in the county of Malayer. Despite the great importance and existence of polluted resources in the vicinity of vineyards in Malayer, there are few studies conducted in this regard. To evaluate the pollution level of toxic elements in these vineyards, 20 sampling stations were selected randomly and samples of garden soil and leaves of grapevine species were collected. After the acidic digestion of the samples, the concentrations of the heavy metals were measured using atomic absorption spectrometer. Then, the indices of contamination factor (Cf), geoaccumulation index (Igeo), biological accumulation coefficient (BAC), and ecological risk index (RI) were calculated. According to the results obtained for Igeo and Cf indices, the soil in the study region was moderately contaminated with copper. However, the ecological risk index and BAC of the studied region were low. To investigate the spatial distribution of copper in the studied region, the spatial distribution map was prepared. To locate the source of copper contamination and investigate the effect of various land uses on the amount of contamination, land use map (LUM) of vineyards was generated. To this end, images were downloaded from Landsat Satellite, and after the exertion of various corrections on the images based on the supervised classification method, the LUM with agricultural, residential, vineyard, brick furnace and pasture classes was prepared. The comparison of the LUM and the copper contamination map illustrated that the copper contamination was higher in the places with urban and adobe furnace land-use types.

Background: The improper exploitation of water resources by humans has disrupted the natural balance of groundwater. Given the water resources restriction, it is crucial to manage these resources properly, recognize the current situation, and anticipate the harvesting or feeding effects. In this regard, simulators or models can act as valuable tools. Methods: In this research, we performed quantitative modeling of groundwater flow in the Quar-Maharlu plain, Fars Province, Iran using the PMWIN software. The model included three years’ calibration (2011-2014) for hydraulic conductivity coefficient and one year’s verification (2014-2015). To evaluate the model error in calibration and verification, the root mean square deviation (RMSD) was used. After simulating the aquifer to optimize the artificial recharge location by the flood spreading method, different scenarios were defined and examined by considering the natural and artificial factors. Results: The RMSD values for calibration were 1.55, 1.49, and 1.56 m for 2011, 2012, and 2013, respectively. The RMSD for verification of one year was 1.77 m, indicating the acceptable ability of the model to predict groundwater flow parameters. The stock variation for the whole aquifer was -8.88 mm3 in 2014. In the next step, the best recharging location was selected to create the maximum head increase (5.3cm) in the entire area of the plain. Conclusion: One of the effective ways to offset the negative balance is to strengthen the aquifer through artificial recharge.