6 papers
AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting
Binqing Wu, Zongjiang Shang, Shiyu Liu +3
Accurate air quality forecasting is essential for public health and environmental sustainability, but remains challenging due to the complex pollutant dynamics. Existing deep learn…
Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysis
Zongjiang Shang, Dongliang Cui, Binqing Wu +1
Recently, there has been great success in leveraging pre-trained large language models (LLMs) for time series analysis. The core idea lies in effectively aligning the modality betw…
MillGNN: Learning Multi-Scale Lead-Lag Dependencies for Multi-Variate Time Series Forecasting
Binqing Wu, Zongjiang Shang, Jianlong Huang +1
Multi-variate time series (MTS) forecasting is crucial for various applications. Existing methods have shown promising results owing to their strong ability to capture intra- and i…
ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecasting
Binqing Wu, Jianlong Huang, Zongjiang Shang +1
In multivariate time series (MTS) forecasting, many deep learning based methods have been proposed for modeling dependencies at multiple spatial (inter-variate) or temporal (intra-…
Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting
Yingtao Luo, Shikai Fang, Binqing Wu +2
Weather forecasting is essential but remains computationally intensive and physically incomplete in traditional numerical weather prediction (NWP) methods. Deep learning (DL) model…
Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
Zongjiang Shang, Ling Chen, Binqing wu +1
Although transformer-based methods have achieved great success in multi-scale temporal pattern interaction modeling, two key challenges limit their further development: (1) Individ…