Search papers, labs, and topics across Lattice.
This paper introduces the Extreme-Adaptive Transformer (Exformer), a novel framework for time series forecasting that specifically addresses the challenge of modeling rare extreme events in hydrologic data. By incorporating an extreme-adaptive attention mechanism with Local, Stride, and Extreme components, Exformer effectively captures both normal and extreme temporal dependencies, leading to improved forecasting accuracy. Experiments on four real-world hydrologic datasets reveal that Exformer outperforms state-of-the-art baselines in 3-day forecasting performance, highlighting the importance of extreme-aware attention in handling imbalanced time series data.
Explicitly modeling rare extreme events in time series forecasting can significantly enhance predictive accuracy, as shown by Exformer's superior performance over traditional models.
Time series forecasting remains challenging when the underlying data contain rare but critical extreme events. This issue is particularly important in hydrologic forecasting, where streamflow distributions are often highly skewed and extreme peaks can have substantial impacts on flood monitoring, water resource management, and early warning systems. Although Transformer-based forecasting models have achieved strong performance by modeling long-range temporal dependencies, they typically treat all time points uniformly and may therefore underrepresent rare extreme patterns. In this paper, we propose the Extreme-Adaptive Transformer (Exformer), a forecasting framework designed to explicitly model temporal dependencies involving both normal and extreme events. Exformer introduces an extreme-adaptive attention mechanism composed of three sparse components: Local, Stride, and Extreme. The Local and Stride components capture short-term and periodic temporal dependencies, respectively, while the Extreme component selectively models event-aware dependencies between normal and extreme streamflow patterns. Experiments on four real-world hydrologic streamflow datasets show that Exformer achieves superior 3-day forecasting performance compared with state-of-the-art baselines. Our findings demonstrate that explicitly incorporating extreme-aware attention improves the forecasting capacity of Transformer models on imbalanced time series with rare but consequential events.
