Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zachos, Ioannis, Girolami, Mark, Damoulas, Theodoros
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2410.07352
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915278848262144
author Zachos, Ioannis
Girolami, Mark
Damoulas, Theodoros
author_facet Zachos, Ioannis
Girolami, Mark
Damoulas, Theodoros
contents Agent-based models (ABMs) are proliferating as decision-making tools across policy areas in transportation, economics, and epidemiology. In these models, a central object of interest is the discrete origin-destination matrix which captures spatial interactions and agent trip counts between locations. Existing approaches resort to continuous approximations of this matrix and subsequent ad-hoc discretisations in order to perform ABM simulation and calibration. This impedes conditioning on partially observed summary statistics, fails to explore the multimodal matrix distribution over a discrete combinatorial support, and incurs discretisation errors. To address these challenges, we introduce a computationally efficient framework that scales linearly with the number of origin-destination pairs, operates directly on the discrete combinatorial space, and learns the agents' trip intensity through a neural differential equation that embeds spatial interactions. Our approach outperforms the prior art in terms of reconstruction error and ground truth matrix coverage, at a fraction of the computational cost. We demonstrate these benefits in large-scale spatial mobility ABMs in Cambridge, UK and Washington, DC, USA.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07352
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generating Origin-Destination Matrices in Neural Spatial Interaction Models
Zachos, Ioannis
Girolami, Mark
Damoulas, Theodoros
Machine Learning
Agent-based models (ABMs) are proliferating as decision-making tools across policy areas in transportation, economics, and epidemiology. In these models, a central object of interest is the discrete origin-destination matrix which captures spatial interactions and agent trip counts between locations. Existing approaches resort to continuous approximations of this matrix and subsequent ad-hoc discretisations in order to perform ABM simulation and calibration. This impedes conditioning on partially observed summary statistics, fails to explore the multimodal matrix distribution over a discrete combinatorial support, and incurs discretisation errors. To address these challenges, we introduce a computationally efficient framework that scales linearly with the number of origin-destination pairs, operates directly on the discrete combinatorial space, and learns the agents' trip intensity through a neural differential equation that embeds spatial interactions. Our approach outperforms the prior art in terms of reconstruction error and ground truth matrix coverage, at a fraction of the computational cost. We demonstrate these benefits in large-scale spatial mobility ABMs in Cambridge, UK and Washington, DC, USA.
title Generating Origin-Destination Matrices in Neural Spatial Interaction Models
topic Machine Learning
url https://arxiv.org/abs/2410.07352