Spatiotemporal Modeling and Forecasting at Scale with Dynamic Generalized Linear Models

TL;DR

This paper introduces a scalable, flexible approach using dynamic generalized linear models to accurately forecast human mobility patterns from large-scale spatiotemporal data, addressing noise and uneven sampling challenges.

Contribution

The paper presents a novel application of DGLMs for large-scale spatiotemporal modeling, demonstrating robustness, scalability, and accuracy in occupancy count forecasting.

Findings

DGLMs provide accurate forecasts across various spatial resolutions.

The approach scales linearly with data size, handling hundreds of millions of observations.

Robust to sensor noise and uneven sampling rates.

Abstract

Spatiotemporal data consisting of timestamps, GPS coordinates, and IDs occurs in many settings. Modeling approaches for this type of data must address challenges in terms of sensor noise, uneven sampling rates, and non-persistent IDs. In this work, we characterize and forecast human mobility at scale with dynamic generalized linear models (DGLMs). We represent mobility data as occupancy counts of spatial cells over time and use DGLMs to model the occupancy counts for each spatial cell in an area of interest. DGLMs are flexible to varying numbers of occupancy counts across spatial cells, are dynamic, and easily incorporate daily and weekly seasonality in the aggregate-level behavior. Our overall approach is robust to various types of noise and scales linearly in the number of spatial cells, time bins, and agents. Our results show that DGLMs provide accurate occupancy count forecasts over a variety of spatial resolutions and forecast horizons. We also present scaling results for spatiotemporal data consisting of hundreds of millions of observations. Our approach is flexible to support several downstream applications, including characterizing human mobility, forecasting occupancy counts, and anomaly detection for aggregate-level behaviors.