|
Prediction of groundwater level fluctuations using fuzzy inference system, Adaptive Neuro – Fuzzy Inference System and neural network
|
Abbas Sedghamiz *    , Farid Foroughi |
| Assistant Professor, Department of Water Engineering, Collage of Agriculture and Natural Resources of Darab, Shiraz University, Darab, Iran |
|
|
Abstract: (266 Views) |
| 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. |
Article number: 3 |
| Keywords: Error index, Fuzzy inference system, Groundwater, Prediction multilayer perceptron neural network |
|
|
Full-Text [PDF 2329 kb]
(94 Downloads)
|
|
Type of Study: Research |
Subject:
Special
|
|
|
|
|
|
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
