Scalable Spatiotemporal Modeling for Bicycle Count Prediction

2025-06-09

AI Summary

To address the dual challenges of modeling high-dimensional spatiotemporal data and inefficient Bayesian inference in urban bicycle flow forecasting, this paper proposes a scalable sparse spatiotemporal dynamic generalized linear model. The method jointly models time-varying spatial intercepts and dynamic covariate coefficients, integrating the stochastic partial differential equation (SPDE) sparse approximation with a customized hybrid MCMC sampler to enable efficient, uncertainty-quantified Bayesian inference under a Poisson counting framework. It supports missing-data imputation, cross-station interpolation, short-term forecasting, and annual average daily bicycling (AADB) estimation. Evaluated on real-world Montreal bicycle flow data, the model significantly outperforms conventional spatiotemporal approaches—achieving high predictive accuracy, real-time kriging capability, and computational scalability. This work establishes a new paradigm for large-scale urban traffic sensing and inference.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

We propose a novel sparse spatiotemporal dynamic generalized linear model for efficient inference and prediction of bicycle count data. Assuming Poisson distributed counts with spacetime-varying rates, we model the log-rate using spatiotemporal intercepts, dynamic temporal covariates, and site-specific effects additively. Spatiotemporal dependence is modeled using a spacetime-varying intercept that evolves smoothly over time with spatially correlated errors, and coefficients of some temporal covariates including seasonal harmonics also evolve dynamically over time. Inference is performed following the Bayesian paradigm, and uncertainty quantification is naturally accounted for when predicting bicycle counts for unobserved locations and future times of interest. To address the challenges of high-dimensional inference of spatiotemporal data in a Bayesian setting, we develop a customized hybrid Markov Chain Monte Carlo (MCMC) algorithm. To address the computational burden of dense covariance matrices, we extend our framework to high-dimensional spatial settings using the sparse SPDE approach of Lindgren et al. (2011), demonstrating its accuracy and scalability on both synthetic data and Montreal Island bicycle datasets. The proposed approach naturally provides missing value imputations, kriging, future forecasting, spatiotemporal predictions, and inference of model components. Moreover, it provides ways to predict average annual daily bicycles (AADB), a key metric often sought when designing bicycle networks.

Problem

• Predict bicycle counts using spatiotemporal modeling
• Address high-dimensional inference with Bayesian MCMC
• Estimate average annual daily bicycles (AADB)

Innovation

• Sparse spatiotemporal dynamic generalized linear model
• Customized hybrid MCMC algorithm for Bayesian inference
• SPDE approach for scalable high-dimensional spatial modeling