A comprehensive survey on conventional and modern neural networks: application to river flow forecasting

This study appraises different types of conventional (e.g., GRNN, RBNN, & MLPNN) and modern neural networks (e.g., integrative, inclusive, hybrid, & recurrent) in forecasting daily flow in the Thames River located in the United Kingdom. The models are mathematically, statistically, and diagnostically compared based on the forecasted results for ten different time-series assortments. The results indicate that all the neural network models acceptably forecasted the daily flow rate, with mean values of R-2 > 0.92 and RMSE < 18.6 m(3)/s. Despite the fact that the integrative neural network models slightly acted better in forecasting flow rate (mean values of R-2 > 0.94 and RMSE < 15.3 m(3)/s), they were not as computationally effective as the other applied models.

Automated summary

This study compares different types of neural networks in forecasting daily flow in the Thames River, finding that all models effectively predict daily flow rate, with integrative neural networks performing slightly better than others.