Quantifying Uncertainty in Deep Spatiotemporal Forecasting

Abstract

Deep learning is gaining increasing popularity for spatiotemporal forecasting. However, prior works have mostly focused on point estimates without quantifying the uncertainty of the predictions. In high stakes domains, being able to generate probabilistic forecasts with confidence intervals is critical to risk assessment and decision making. Hence, a systematic study of uncertainty quantification (UQ) methods for spatiotemporal forecasting is missing in the community. In this paper, we describe two types of spatiotemporal forecasting problems: regular grid-based and graph-based. Then we analyze UQ methods from both the Bayesian and the frequentist point of view, casting in a unified framework via statistical decision theory. Through extensive experiments on real-world road network traffic, epidemics, and air quality forecasting tasks, we reveal the statistical and computational trade-offs for different UQ methods: Bayesian methods are typically more robust in mean prediction, while confidence levels obtained from frequentist methods provide more extensive coverage over data variations. Computationally, quantile regression type methods are cheaper for a single confidence interval but require re-training for different intervals. Sampling based methods generate samples that can form multiple confidence intervals, albeit at a higher computational cost.

arXiv commentarXiv admin note: text overlap with arXiv:2102.06684

References in corpus (16)

• Semi-Supervised Classification with Graph Convolutional Networks
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• A universal model for mobility and migration patterns
• Multiscale mobility networks and the large scale spreading of infectious diseases
• Deep and Confident Prediction for Time Series at Uber
• Deep Ensembles: A Loss Landscape Perspective
• Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
• A Multi-Horizon Quantile Recurrent Forecaster
• Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization
• A Simple Baseline for Bayesian Uncertainty in Deep Learning
• Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors
• Single-Model Uncertainties for Deep Learning
• Adaptive, Distribution-Free Prediction Intervals for Deep Networks
• Natural-Parameter Networks: A Class of Probabilistic Neural Networks
• Bayesian Inference for Large Scale Image Classification