جستجوی مقالات مرتبط با کلیدواژه « سیستم استنتاج فازی-عصبی تطبیقی » در نشریات گروه « آب و خاک »

In this study, the accuracy of the Adaptive Network-Based Fuzzy Inference System (ANFIS) in integrating with the Gray Wolf Algorithm (ANFIS-GWO) in predicting groundwater level was evaluated for the first time using unpublished observational data from 1998 to 2018 in the Zarandieh aquifer, central Iran. Three observational wells were randomly selected for analysis. Assessment of evaluation criteria demonstrated that among the proposed scenarios using the hybrid model, the D scenario was selected as the optimal scenario with input data including the previous month's groundwater level, precipitation, temperature, and groundwater extraction. In the D scenario, parameters including MAPE, RMSE, and NASH were 0.29 m, 0.47 m, and 0.99, respectively for the first observational well. Also, C scenario with input data including the previous month's groundwater level, precipitation, and groundwater extraction for the second observational well, for the same parameters mentioned above equal to 0.20 m, 0.26 m, and 0.99. As well for the third observational well, the A scenario with input data including the previous month's groundwater level for the same parameters equal to 0.29 m, 0.41 m, and 0.99 as the optimal scenarios were selected using the ANFIS-GWO model. Based on the results, the Gray wolf algorithm in training the ANFIS model was able to reduce the average forecast error by equal to 0.03 (RMSE) and 0.02 (MAPE) meter and increased the average NASH value equal to 0.01 and increased the accuracy of predictions.

The concern of the present research was to do a comparative study between the GEP, ANN and ANFIS models to estimate monthly global solar radiation. For this purpose, long-term (24-years) monthly data of global solar radiation (RS, MJ m−2), sunshine hours and air temperature (°C), from Tabriz synoptic station were used. To perform the artificial intelligence models, a new combination of inputs including monthly mean clearness index (KT), monthly temperature range (ΔT), relative sunshine hours (n/N) and extraterrestrial global solar radiation (Ra) were employed. Since the lowest values of MBE and RMSE (0. 13 and 1.97 MJ m−2 respectively) and the highest value of R2 (0.92) were obtained for ANN model, and therefore, the ANN model was selected as the best model to estimate the monthly global solar radiation. Using quarter-quarter (Q-Q) plots revealed that although the ANN model generally presents the best fit for monthly global solar radiation data, this model is found to be not successful in estimating the higher values of monthly global solar radiation data. Therefore, the application of ANN model is recommended for regions with lower solar radiation values. The performance of the ANFIS model was better than other models in covering the highest and lowest values (the first and fourth quarter). Therefore, it can be concluded that the ANFIS model gives more accurate results in the areas with the higher values of solar radiation. The findings also show that unlike previous researches which were carried out in daily scale, the performance of GEP technique for modeling monthly global solar radiation is satisfactory especially in the ranges of 250 to 800 MJ m−2. Thus, it can be inferred that GEP can be more powerful in modeling the phenomena which have low fluctuations or a limited range.

Water scarcity and subsequent social and economic crises have doubled the need to use new interdisciplinary knowledge-based approaches in reforming water resources management structures and policies and implementing water resources plans and projects. In the meantime, recognizing the interrelationships of the social sciences and their water resources systems has become a problem that its solution help us to correct existing dysfunctional structures. Therefore, the main purpose of this study is to prove the interrelationship of some social parameters and water resources on a continental scale with the use of software modeling tools. In this study, per capita data on renewable water resources and social parameters including the ratio of rural population to urban population, population density, number of Internet users and education index on an annual scale are considered. The statistical period of the data was 13 years (2005-2007) and this study was performed for 42 countries in Asia whose per capita water resources were declining. Then, using soft copmuting methods such as Artificial Neural Network (ANN), Decision Tree (M5) and Adaptive Fuzzy-neural Inference System (ANFIS), the interrelationship between per capita water resources and social parameters was modeled. Modeling results were evaluated by the criteria of determination coefficient (R2), root mean square error (RMSE) and mean absolute error (MAE) values. Finally, the results indicate the superior performance of ANFIS method compared to the other two models in evaluating the interaction of per capita water resources and social parameters. Also, after the ANFIS model, the M5 and ANN models had better performance, respectively.