Application of Neural Network Models and ANFIS for Water Level Forecasting of the Salve Faccha Dam in the Andean Zone in Northern Ecuador

Despite the importance of dams for water distribution various uses, adequate forecasting on a day-to-day scale is still in great need intensive study worldwide. Machine learning models have had wide application resource studies and shown satisfactory results, including time series levels dam flows. In this study, neural network (NN) adaptive neuro-fuzzy inference systems (ANFIS) were generated to forecast level Salve Faccha reservoir, which supplies Quito, Capital Ecuador. For NN, non-linear input–output net with maximum delay 13 days was used variation number nodes hidden layers. ANFIS, after up four delay, subtractive clustering algorithm hyperparameter from 0.5 0.8. The results indicate that precipitation not influencing input prediction reservoir level. best ANFIS showed high performance, r > 0.95, Nash index RMSE < 0.1. model t + 4, 6.