No abstract

The present study evaluates the capability of a novel optimization method in modeling daily reference evapotranspiration (ET0), a critical issue in water resource management. A hybrid predictive model based on the ANN Algorithm that is embedded within the COOT method (COOT bird natural life model- Artificial Neural Network (COOT-ANN)) is developed and evaluated for its suitability for the prediction of daily ET0 at seven meteorological stations in different states of Australia. Accordingly, a daily statistical period of 12 years (01-01-2010 to 31-12-2021) for climatic data of maximum temperature, minimum temperature, and ET0 were collected. The results are evaluated using six performance criteria metrics: correlation coefficient (R), Root Mean Square Error (RMSE), Nash-Sutcliffe efficiency (NSE), RMSE-observation standard deviation ratio (RSR), Scatter Index (SI), and mean absolute error (MAE) along with the Taylor diagrams. The performance of the COOT-ANN model was compared with those of the conventional ANN model. The results showed that the COOT-ANN hybrid model outperforms the ANN model at all seven stations; and so this study provides an innovative method for prediction in agricultural and water resources studies.

No abstract

Predicting groundwater level (GWL) fluctuations, which act as a reserve water reservoir, Particularly in arid and semi-arid climates, is vital in water resources management and planning. Within the scope of current research, a novel hybrid algorithm is proposed for estimating GWL values in the Tabriz plain of Iran by combining the artificial neural network (ANN) algorithm with newly developed nature-inspired Coot and Honey Badger metaheuristic optimization algorithms. Various combinations of meteorological data such as temperature, evaporation and precipitation, previous GWL values, and the month and year values of the data were used to evaluate the algorithm's success. Furthermore, shannon entropy of performance of models was assessed according to 44 different statistical indicators which is classified into two class: accuracy and error class. Hence, based on high value of Shannon entropy, the best statistical indicator was selected and the results of best model and selecting the best scenario were analyzed. Results indicated that value of Shannon entropy is higher for accuracy class than error class. Also, for accuracy and error class respectively, Akaikes Information Criterion (AIC) and Residual Sum of Squares (RSS) indexes with the highest entropy value which is equal to 12.72 and 7.3 are the best indicators of both classes and Legate-McCabe Efficiency (LME) and Normalized Root Mean Square Error-mean (NRMSE-Mean) indexes with the lowest entropy value which is equal to 3.7 and -8.3 are the worst indicators of both classes. According to the results of evaluation best indicator in the testing phase, AIC indicator value for HBA-ANN, COOT-ANN, and the stand-alone ANN models is equal to -344, -332.8, -175.8, respectively. Furthermore, it was revealed that the proposed metaheuristic algorithms significantly ameliorate the performance of the stand-alone ANN model and offered satisfactory GWL prediction results. Finally, it was concluded that the Honey Badger optimization algorithm showed superior results than the Coot optimization algorithm in GWL prediction.