Prediction of lake water-level fluctuations using adaptive neuro-fuzzy inference system hybridized with metaheuristic optimization algorithms

Autor: Quoc Bao Pham, Babak Mohammadi, Roozbeh Moazenzadeh, Salim Heddam, Ramiro Pillco Zolá, Adarsh Sankaran, Vivek Gupta, Ismail Elkhrachy, Khaled Mohamed Khedher, Duong Tran Anh
Jazyk: angličtina
Rok vydání: 2022
Předmět:
Zdroj: Applied Water Science, Vol 13, Iss 1, Pp 1-17 (2022)
Druh dokumentu: article
ISSN: 2190-5487
2190-5495
DOI: 10.1007/s13201-022-01815-z
Popis: Abstract Lakes help increase the sustainability of the natural environment and decrease food chain risk, agriculture, ecosystem services, and leisure recreational activities locally and globally. Reliable simulation of monthly lake water levels is still an ongoing demand for multiple environmental and hydro-informatics engineering applications. The current research aims to utilize newly developed hybrid data-intelligence models based on the ensemble adaptive neuro-fuzzy inference system (ANFIS) coupled with metaheuristics algorithms for lake water-level simulation by considering the effect of seasonality on Titicaca Lake water-level fluctuations. The classical ANFIS model was trained using three metaheuristics nature-inspired optimization algorithms, including the genetic algorithm (ANFIS-GA), particle swarm optimizer (ANFIS-PSO), and whale optimization algorithm (ANFIS-WOA). For determining the best set of the input variables, an evolutionary approach based on several lag months has been utilized prior to the lake water-level simulation process using the hybrid models. The proposed hybrid models were investigated for accurately simulating the monthly water levels at Titicaca Lake. The ANFIS-WOA model exhibited the best prediction performance for lake water-level pattern measurement in this study. For the best scenario (the inputs were $${X}_{t-1},\; {X}_{t-2}, \;{X}_{t-3}, \;{X}_{t-4}, \; {X}_{t-12}$$ X t - 1 , X t - 2 , X t - 3 , X t - 4 , X t - 12 ) the ANFIS-WOA model attained root mean square error (RMSE $$\approx$$ ≈ 0.08 m), mean absolute error (MAE $$\approx$$ ≈ 0.06 m), and coefficient of determination (R 2 $$\approx$$ ≈ 0.96). Also, the results showed that long-term seasonal memory for this lake is suitable input for lake water-level models so that the long-term dynamic memory of 1-year time series for lake water-level data is the best input for estimating the water level of Titicaca Lake.
Databáze: Directory of Open Access Journals