Figure - available from: Hydrology
This content is subject to copyright.
Examples of (a) deterministic and (b) probabilistic predictions for streamflow (Q). The months of the year are indicated along the horizontal axis. Bands indicate the percentage of observations expected to fall within their bounds.
Source publication
The transformative potential of deep learning models is felt in many research fields, including hydrology and water resources. This study investigates the effectiveness of the Temporal Fusion Transformer (TFT), a deep neural network architecture for predicting daily streamflow in Portugal, and benchmarks it against the popular Hydrologiska Byråns V...
Citations
... The analysis is based on earlier work, where TFTs were already applied to predict daily streamflow with satisfactory results [22]. Notably, in the task of rainfall-runoff modeling, TFTs surpassed the performance of the classical Hydrologiska Byråns Vattenbalansavdelning (HBV) model [23]. ...
... Corrections were based on the civil year of 2022. We applied similar corrections to the previous work [22]. (2) Hiding information not known at the time of operational decisions. ...
... All predictions were made with an hourly time step. The work conducted on TFTs represents a follow-up of a previous publication that applied them to streamflow prediction [22]. There was an effort to avoid redundant aspects, particularly in the methodology, but also to provide the necessary information for the reader to follow this work independently. ...
This study explores the application of Temporal Fusion Transformers (TFTs) to improve the predictability of hourly potential hydropower production for a small run–of–the–river hydropower plant in Portugal. Accurate hourly power forecasts are essential for optimizing participation in the spot electricity market, where deviations incur penalties. This research introduces the novel application of the TFT, a deep–learning model tailored for time series forecasting and uncovering complex patterns, to predict hydropower production based on meteorological data, historical production records, and plant capacity. Key challenges such as filtering observed hydropower outputs (to remove strong, and unpredictable human influence) and adapting the historical series to installed capacity increases are discussed. An analysis of meteorological information from several sources, including ground information, reanalysis, and forecasting models, was also undertaken. Regarding the latter, precipitation forecasts from the European Centre for Medium–Range Weather Forecasts (ECMWF) proved to be more accurate than those of the Global Forecast System (GFS). When combined with ECMWF data, the TFT model achieved significantly higher accuracy in potential hydropower production predictions. This work provides a framework for integrating advanced machine learning models into operational hydropower scheduling, aiming to reduce classical modeling efforts while maximizing energy production efficiency, reliability, and market performance.
