Graph Neural Networks for Multivariate Time Series Regression with Application to Seismic Data
This work addresses a domain-specific problem in seismology by improving prediction accuracy for earthquake intensity, though it is incremental as it adapts existing graph neural network methods to a new task.
The authors tackled the problem of multivariate time series regression for long sequences with spatial dependencies, specifically predicting earthquake ground shaking intensity from seismic waveforms, achieving a 16.3% average MSE reduction compared to baselines and matching baseline performance with half the input size.
Machine learning, with its advances in deep learning has shown great potential in analyzing time series. In many scenarios, however, additional information that can potentially improve the predictions is available. This is crucial for data that arise from e.g., sensor networks that contain information about sensor locations. Then, such spatial information can be exploited by modeling it via graph structures, along with the sequential (time series) information. Recent advances in adapting deep learning to graphs have shown potential in various tasks. However, these methods have not been adapted for time series tasks to a great extent. Most attempts have essentially consolidated around time series forecasting with small sequence lengths. Generally, these architectures are not well suited for regression or classification tasks where the value to be predicted is not strictly depending on the most recent values, but rather on the whole length of the time series. We propose TISER-GCN, a novel graph neural network architecture for processing, in particular, these long time series in a multivariate regression task. Our proposed model is tested on two seismic datasets containing earthquake waveforms, where the goal is to predict maximum intensity measurements of ground shaking at each seismic station. Our findings demonstrate promising results of our approach -- with an average MSE reduction of 16.3% - compared to the best performing baselines. In addition, our approach matches the baseline scores by needing only half the input size. The results are discussed in depth with an additional ablation study.