Deep learning models have shown strong potential for time series forecasting; however, their deployment in real-world environmental monitoring remains challenging due to non-stationary dynamics and limited explainability. This work investigates explainability as a central tool for understanding continual learning in adaptive time series forecasting, utilizing Experience Replay strategies.
We study neural forecasting architectures such as PatchMixer, PatchTST, and DLinear, augmented with attention-based sampling mechanisms to support model adaptation over time. Explainability is leveraged through attention rollout and gradient-based attribution methods (Grad-CAM) to analyze both predictive behavior and sampling strategies within a continual learning framework.
Experiments conducted on real-world hydrological time series exhibiting heterogeneous patterns and regime shifts show that analyzing model and sampling behaviors provides valuable insights into the dynamics of the continual learning framework. Beyond predictive performance, our results highlight the challenges and opportunities of using explainability to understand continual learning behaviors, revealing how attribution patterns evolve over time and how they can inform data selection and adaptation strategies in non-stationary forecasting scenarios.
Blogger's Review: This paper delves into the crucial issue of explainability in deep learning for time series forecasting, emphasizing the importance of understanding model behavior in dynamic environments. By integrating Experience Replay and attention mechanisms, the study offers new perspectives for future model design, making it a worthy read.