Robust Spatiotemporal Forecasting Using Adaptive Deep-Unfolded Variational Mode Decomposition
By: Osama Ahmad , Lukas Wesemann , Fabian Waschkowski and more
Potential Business Impact:
Predicts future events with much less error.
Accurate spatiotemporal forecasting is critical for numerous complex systems but remains challenging due to complex volatility patterns and spectral entanglement in conventional graph neural networks (GNNs). While decomposition-integrated approaches like variational mode graph convolutional network (VMGCN) improve accuracy through signal decomposition, they suffer from computational inefficiency and manual hyperparameter tuning. To address these limitations, we propose the mode adaptive graph network (MAGN) that transforms iterative variational mode decomposition (VMD) into a trainable neural module. Our key innovations include (1) an unfolded VMD (UVMD) module that replaces iterative optimization with a fixed-depth network to reduce the decomposition time (by 250x for the LargeST benchmark), and (2) mode-specific learnable bandwidth constraints ({\alpha}k ) adapt spatial heterogeneity and eliminate manual tuning while preventing spectral overlap. Evaluated on the LargeST benchmark (6,902 sensors, 241M observations), MAGN achieves an 85-95% reduction in the prediction error over VMGCN and outperforms state-of-the-art baselines.
Similar Papers
VMDNet: Time Series Forecasting with Leakage-Free Samplewise Variational Mode Decomposition and Multibranch Decoding
Machine Learning (CS)
Predicts future patterns better by understanding repeating cycles.
Robust and Noise-resilient Long-Term Prediction of Spatiotemporal Data Using Variational Mode Graph Neural Networks with 3D Attention
Machine Learning (CS)
Predicts traffic better even with bad data.
Deep Learning-Based Financial Time Series Forecasting via Sliding Window and Variational Mode Decomposition
Machine Learning (CS)
Predicts stock prices more accurately using smart math.