Efficacy of Temporal Fusion Transformers for Runoff Simulation
This work addresses hydrological prediction for water resource management, but it is incremental as it applies an existing method (TFT) to a new domain with modest gains.
The study compared Temporal Fusion Transformers (TFTs) to LSTMs for rainfall-runoff modeling across multiple datasets, finding that TFT slightly outperforms LSTM, particularly in simulating midsections and peaks of hydrographs, and handles longer sequences better.
Combining attention with recurrence has shown to be valuable in sequence modeling, including hydrological predictions. Here, we explore the strength of Temporal Fusion Transformers (TFTs) over Long Short-Term Memory (LSTM) networks in rainfall-runoff modeling. We train ten randomly initialized models, TFT and LSTM, for 531 CAMELS catchments in the US. We repeat the experiment with five subsets of the Caravan dataset, each representing catchments in the US, Australia, Brazil, Great Britain, and Chile. Then, the performance of the models, their variability regarding the catchment attributes, and the difference according to the datasets are assessed. Our findings show that TFT slightly outperforms LSTM, especially in simulating the midsection and peak of hydrographs. Furthermore, we show the ability of TFT to handle longer sequences and why it can be a better candidate for higher or larger catchments. Being an explainable AI technique, TFT identifies the key dynamic and static variables, providing valuable scientific insights. However, both TFT and LSTM exhibit a considerable drop in performance with the Caravan dataset, indicating possible data quality issues. Overall, the study highlights the potential of TFT in improving hydrological modeling and understanding.