Learning from Polar Representation: An Extreme-Adaptive Model for Long-Term Time Series Forecasting


  • Yanhong Li Santa Clara University, Santa Clara, CA, USA
  • Jack Xu Santa Clara Valley Water District, San Jose, CA, USA
  • David Anastasiu Santa Clara University, Santa Clara, CA, USA




APP: Natural Sciences, APP: Other Applications, ML: Time-Series/Data Streams


In the hydrology field, time series forecasting is crucial for efficient water resource management, improving flood and drought control and increasing the safety and quality of life for the general population. However, predicting long-term streamflow is a complex task due to the presence of extreme events. It requires the capture of long-range dependencies and the modeling of rare but important extreme values. Existing approaches often struggle to tackle these dual challenges simultaneously. In this paper, we specifically delve into these issues and propose Distance-weighted Auto-regularized Neural network (DAN), a novel extreme-adaptive model for long-range forecasting of stremflow enhanced by polar representation learning. DAN utilizes a distance-weighted multi-loss mechanism and stackable blocks to dynamically refine indicator sequences from exogenous data, while also being able to handle uni-variate time-series by employing Gaussian Mixture probability modeling to improve robustness to severe events. We also introduce Kruskal-Wallis sampling and gate control vectors to handle imbalanced extreme data. On four real-life hydrologic streamflow datasets, we demonstrate that DAN significantly outperforms both state-of-the-art hydrologic time series prediction methods and general methods designed for long-term time series prediction.



How to Cite

Li, Y., Xu, J., & Anastasiu, D. (2024). Learning from Polar Representation: An Extreme-Adaptive Model for Long-Term Time Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 38(1), 171-179. https://doi.org/10.1609/aaai.v38i1.27768



AAAI Technical Track on Application Domains