fuzzy inference system

Since the increase in the depth of groundwater and its intensification can indicate serious limitations in the exploitation of these resources, predicting the changes of this parameter plays an important role in managing these resources and preventing possible damage to them. For this purpose, the use of smart methods has been strongly recommended by researchers. In this research, the methods of multilayer perceptron neural network (MLP), fuzzy inference system (fis), adaptive neural fuzzy inference system (ANFIS), and the combined method of fuzzy neural inference system and particle swarm optimization (ANFIS-PSO) were used for simulation of groundwater Fluctuations depth in Haji Abad area between March 1995 to October 2022 on a monthly scale. The training and testing phases were done with 75 and 25 percent of data, respectively. To measure the accuracy of the models, root mean square error (RMSE), mean absolute percentage error (MAPE) and mean absolute value of error (MAE) indices were used. The best results in the training phase are related to ANFIS-PSO, ANFIS, and MLP models, respectively. Simultaneously with the training of the mentioned models, the testing stage of said models was also implemented. Finally, the best results in this stage belonged to the neural network model with time delay [1 3 5], the ANFIS-PSO model with time delay [1 2 3], and the neural network model with time delay [1 2], respectively. The accuracy indices in the test stage for the best models are (0.1871, 0.1865, 0.1857) for RMSE, (0.7402, 0.6715, 0.6684) for MAPE, and (0.1326, 0.1238, 0.1198) for MAE, respectively. These values show that all three models have an error of less than 20 cm, an error percentage of less than 0.75%, and an absolute error of less than 14 cm, which indicates the acceptable accuracy of these models. Also, the coefficient of determination obtained from the regression relationship of the calculated and measured values of the groundwater depth in the test phase for all three models is around 0.82, which indicates a relatively high linear relationship between these two parameters.

Assessing water quality is an important step toward the optimal and appropriate use of drinking water resources. Therefore, the necessity of studying water quality characteristics in water resource management programs has been highly considered. Ambiguity and lack of inherent certainty governing water resources in the evaluation of goals, criteria, and decision-making units, as inconsistency and carelessness in the opinions and judgments of decision-makers have led to the tendency towards theories of fuzzy sets and, as a result, fuzzy logic as an efficient and useful tool for planning and making decisions. In the present underground water quality water was first classified by international standard methods (definitive evaluation method) for drinking purposes. Then classification was modeled and compared using Mamdani fuzzy inference. For this purpose, the four-year average of quality parameters of underground water sources related to 33 sources including 10 well rings, 22 spring mouths, and an aqueduct in operation in Sardasht Cityre used as inputs in two cases. In the deterministic evaluation method (Schoeller diagram), the characteristics and the water quality determination diagram were determined. In the four-year average fuzzy inference model, eight water quality parameters were classified into three groups, in the first group the parameters of Na+, Ca+2, and Mg+2, in the second group the parameters of HCO3-, SO4-2, and Cl- were placed in the third group of two TH and TDS parameters. After determining each group with two input parameters, each input parameter was considered including three membership functions, so that the rules considered for it were estimated as nine (3x3). The results based on the deterministic method showed that all the studied samples were in the good to acceptable group. But Mamdani's fuzzy findings showed that two samples with a confidence level of 50% were in the acceptable category and other samples with a confidence level of 83-87% were placed in the desirable category for drinking.