Mobility Network Forecasting: A Trajectory-based Contact Prediction Approach
Open Access
- 21 October 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (9) , 1-38
Abstract
Predicting human mobility patterns is crucial for various applications, including urban planning, traffic management, and public health. A key challenge in this domain is identifying when and where interactions, or contacts , occur between moving individuals (i.e., objects) based on their recent positions. To address this, we represent object movement using a mobility network , where individuals establish connections when they come into close physical proximity. This network framework enables the analysis of individual interactions within a given time frame, providing valuable insights into mobility dynamics. Traditional methods for predicting future interactions typically focus on predicting static snapshots of the mobility network at future time points. These temporal link prediction methods are limited because they do not provide detailed insights into short-term mobility dynamics. In a mobility network, being able to predict both long-term and short-term contacts is crucial in many scenarios: for instance, health authorities may require daily forecasts to plan resource allocation and anticipate disease spread, whereas emergency response teams rely on hour-by-hour (or even minute-by-minute) predictions for real-time outbreak control. In this article, we present MobiNetForecast , a two‐stage framework that (i) individually predicts each user’s next \( k \) locations using a Transformer‐based decoder with constrained beam search to enforce spatial continuity and (ii) infers future contacts by identifying spatiotemporal co‐locations in the predicted trajectories. By unifying short‐ and long‐term forecasts in a single pipeline, our approach can anticipate both recurring and previously unseen interactions. Empirical evaluation on real‐world ( GeoLife ) and large‐scale synthetic ( SFCO‐3K ) trajectory datasets demonstrates that MobiNetForecast outperforms state‐of‐the‐art temporal link prediction methods (e.g., EvolveGCN , ROLAND , DyTed , AGCRN ) by up to two orders of magnitude in F1‐score, and improves over leading sequence models (e.g., Flashback++ ) by 15–20% on key metrics across multiple granularities. These results validate the effectiveness of trajectory‐driven contact prediction for accurate, multi‐scale mobility network forecasting.
Keywords
Funding Information
- Sponsor Natural Sciences and Engineering Research Council of Canada (#RGPIN-2022-04586)
- NSERC CREATE training program in Dependable Internet of Things Applications
This publication has 61 references indexed in Scilit:
- PreCLN: Pretrained-based contrastive learning network for vehicle trajectory predictionWorld Wide Web, 2022
- Joint multi-label learning and feature extraction for temporal link predictionPattern Recognition, 2022
- Epidemic Spreading in Trajectory NetworksBig Data Research, 2021
- GC-LSTM: graph convolution embedded LSTM for dynamic network link predictionApplied Intelligence, 2021
- STGSN — A Spatial–Temporal Graph Neural Network framework for time-evolving social networksKnowledge-Based Systems, 2021
- dyngraph2vec: Capturing network dynamics using dynamic graph representation learningKnowledge-Based Systems, 2020
- A versatile computational framework for group pattern mining of pedestrian trajectoriesGeoInformatica, 2019
- Graph regularized nonnegative matrix factorization for temporal link prediction in dynamic networksPhysica A: Statistical Mechanics and its Applications, 2018
- Inferring hybrid transportation modes from sparse GPS data using a moving window SVM classificationComputers, Environment and Urban Systems, 2012
- Clustering and aggregating clues of trajectories for mining trajectory patterns and routesThe VLDB Journal, 2011