Cumulative infiltration and infiltration rate prediction using optimized deep learning algorithms: A study in Western Iran, Journal of Hydrology: Regional Studies, Vol 35, 2021, 100825, https://doi.org/10.1016/j.ejrh.2021.100825. The current study proposed a standalone and optimized deep learning algorithm of a convolutional neural network (CNN) using gray wolf optimization (GWO), a genetic algorithm (GA), and an independent component analysis (ICA) for cumulative infiltration and infiltration rate prediction. With (i) Box plots of developed models : (a) F(t) and (b) f(t), (ii) Quantitative statistical metrics including RMSE (a), MAE (b), NSE (c), and PBIAS (d) in the testing phase for F(t) prediction, (iii) Quantitative statistical metrics including RMSE (a), MAE (b), NSE, (c) and PBIAS (d) in the testing phase for f(t) prediction, and (iv) Percentage of CNN improvement performance by different metaheuristic algorithms for (a) F(t) and (b) f(t). Continue reading...
