Composite Travel Generative Adversarial Networks for Tabular and Sequential Population Synthesis

TL;DR

This paper introduces a novel deep generative model called CTGAN for synthesizing comprehensive population data, including both tabular attributes and sequential mobility patterns, to improve agent-based transportation simulations.

Contribution

The paper proposes a new composite travel GAN that effectively models joint distributions of population attributes and mobility sequences, outperforming existing methods like VAE.

Findings

Accurately reproduces population attribute distributions

Generates realistic trip trajectories and sequences

Performs well across different spatial scales

Abstract

Agent-based transportation modelling has become the standard to simulate travel behaviour, mobility choices and activity preferences using disaggregate travel demand data for entire populations, data that are not typically readily available. Various methods have been proposed to synthesize population data for this purpose. We present a Composite Travel Generative Adversarial Network (CTGAN), a novel deep generative model to estimate the underlying joint distribution of a population, that is capable of reconstructing composite synthetic agents having tabular (e.g. age and sex) as well as sequential mobility data (e.g. trip trajectory and sequence). The CTGAN model is compared with other recently proposed methods such as the Variational Autoencoders (VAE) method, which has shown success in high dimensional tabular population synthesis. We evaluate the performance of the synthesized outputs based on distribution similarity, multi-variate correlations and spatio-temporal metrics. The results show the consistent and accurate generation of synthetic populations and their tabular and spatially sequential attributes, generated over varying spatial scales and dimensions.