Interpretable Water Level Forecaster with Spatiotemporal Causal Attention Mechanisms
This addresses the need for interpretable water level forecasting for traffic management and disaster mitigation, but it is incremental as it builds on existing transformer architectures with specific modifications for interpretability.
The study tackled the problem of forecasting river water levels by proposing a deep learning model that quantifies interpretability, using a transformer with spatiotemporal causal attention mechanisms. The results showed enhanced interpretability consistent with common knowledge and improved robustness against distribution shift on the Han River dataset from 2016 to 2021.
Accurate forecasting of river water levels is vital for effectively managing traffic flow and mitigating the risks associated with natural disasters. This task presents challenges due to the intricate factors influencing the flow of a river. Recent advances in machine learning have introduced numerous effective forecasting methods. However, these methods lack interpretability due to their complex structure, resulting in limited reliability. Addressing this issue, this study proposes a deep learning model that quantifies interpretability, with an emphasis on water level forecasting. This model focuses on generating quantitative interpretability measurements, which align with the common knowledge embedded in the input data. This is facilitated by the utilization of a transformer architecture that is purposefully designed with masking, incorporating a multi-layer network that captures spatiotemporal causation. We perform a comparative analysis on the Han River dataset obtained from Seoul, South Korea, from 2016 to 2021. The results illustrate that our approach offers enhanced interpretability consistent with common knowledge, outperforming competing methods and also enhances robustness against distribution shift.