Abstract
In hydrological modelling, artificial neural network (ANN) models have been popular in the scientific community for at least two decades. The current paper focuses on short-term streamflow forecasting, 1 to 7 days ahead, using an ANN model in two northeastern American watersheds, the Androscoggin and Susquehanna. A virtual modelling environment is implemented, where data used to train and validate the ANN model were generated using a deterministic distributed model over 16 summers (2000–2015). To examine how input variables affect forecast accuracy, we compared streamflow forecasts from the ANN model using four different sets of inputs characterizing the watershed state—surface soil moisture, deep soil moisture, observed streamflow the day before the forecast, and surface soil moisture along with antecedent observed streamflow. We found that the best choice of inputs consists of combining surface soil moisture with observed streamflow for the two watersheds under study. Moreover, to examine how the spatial distribution of input variables affects forecast accuracy, we compared streamflow forecasts from the ANN using surface soil moisture at three spatial distributions—global, fully distributed, and single pixel-based—for the Androscoggin watershed. We show that model performance was similar for both the global and fully distributed representation of soil moisture; however, both models surpass the single pixel-based models. Future work includes evaluating the developed ANN model with real observations, quantified in situ or remotely sensed.
Highlights
Among natural disasters, hydrological-related damage has the greatest impact on humanity and its activities [1]
We found that hydrological forecasts are better across a 7-day forecast window when combining streamflow and soil moisture as watershed state variables inputs instead compared to forecasts made using them separately as inputs
We aggregated the Nash–Sutcliffe efficiency (NSE) results across the 1 to 7-day forecast horizon and for the 16 different years used in cross-validation from the artificial neural network (ANN) model in which surface soil moisture was the input watershed state variable (2-SMP, Table 3)
Summary
Hydrological-related damage has the greatest impact on humanity and its activities [1]. Floods are typically caused by: (i) snowmelt in the spring, which can be compounded by ice jams and/or rainfall, and (ii) high rainfall due to severe thunderstorms or very active low-pressure systems during the summer and fall. Large rainfalls events are associated with the tail of hurricanes, originating from the Atlantic Ocean and reaching the Caribbean and the Gulf of Mexico. In this context, flood forecasting agencies and research centers are developing and improving hydrological models and forecasting systems to anticipate floods and mitigate their impacts [3,4,5]. Hydropower companies are involved in model development and contribute to knowledge in hydrological modelling
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
