Target Population Synthesis using CT-GAN
Tanay Rastogi, Daniel Jonsson
TL;DR
The paper tackles the challenge of generating target populations for agent-based transportation and urban planning models under user-defined aggregated marginals. It introduces CT-GAN, a deep generative model for tabular data, and evaluates both stand-alone CT-GAN and a hybrid CT-GAN+FBS-CO approach using Swedish travel surveys and zonal marginals. Results show that stand-alone CT-GAN best reproduces conditioned marginals and joint distributions, while the hybrid method improves zone convergence and marginal accuracy over a traditional FBS-CO baseline. The study demonstrates the practicality of integrating deep generative models with classical population-synthesis techniques to enhance scalability and fidelity for target-population synthesis.
Abstract
Agent-based models used in scenario planning for transportation and urban planning usually require detailed population information from the base as well as target scenarios. These populations are usually provided by synthesizing fake agents through deterministic population synthesis methods. However, these deterministic population synthesis methods face several challenges, such as handling high-dimensional data, scalability, and zero-cell issues, particularly when generating populations for target scenarios. This research looks into how a deep generative model called Conditional Tabular Generative Adversarial Network (CT-GAN) can be used to create target populations either directly from a collection of marginal constraints or through a hybrid method that combines CT-GAN with Fitness-based Synthesis Combinatorial Optimization (FBS-CO). The research evaluates the proposed population synthesis models against travel survey and zonal-level aggregated population data. Results indicate that the stand-alone CT-GAN model performs the best when compared with FBS-CO and the hybrid model. CT-GAN by itself can create realistic-looking groups that match single-variable distributions, but it struggles to maintain relationships between multiple variables. However, the hybrid model demonstrates improved performance compared to FBS-CO by leveraging CT-GAN ability to generate a descriptive base population, which is then refined using FBS-CO to align with target-year marginals. This study demonstrates that CT-GAN represents an effective methodology for target populations and highlights how deep generative models can be successfully integrated with conventional synthesis techniques to enhance their performance.