François Anctil

TL;DR: In this paper, the most relevant approach to calculate potential evapotranspiration (PE) for use in a daily rainfall-runoff model, while answering the following question: How can we use available atmospheric variables to represent the evaporative demand at the basin scale?

TL;DR: The results show that the proposed early stopped training approach (STA) is effective for improving prediction accuracy and offers an alternative when dynamic adaptive forecasting is desired.

TL;DR: Simulation results suggest that the RNN is the most efficient of the ANN models tested for a calibration period as short as 7 years, and shows that RNN may offer a robust framework for improving water supply planning in semiarid areas where aquifer information is not available.

TL;DR: The field is now firmly established and the research community involved has much to offer hydrological science, but it will be necessary to converge on more objective and consistent protocols for selecting and treating inputs prior to model development; extracting physically meaningful insights from each proposed solution; and improving transparency in the benchmarking and reporting of experimental case studies.

TL;DR: In this paper, the authors investigated the validity of using mean PE instead of temporally varying PE as input to four different daily rainfall-runoff models, and concluded that the insensitivity of rainfall runoff models to detailed evapotranspiration knowledge may bring into question the very concept of PE.