Data-driven transport modelling without overfit

TL;DR

This paper introduces a data-driven transport modelling approach that avoids overfitting, uses explainable weights, and relies on easily obtainable traffic count data for infrastructure planning.

Contribution

It proposes a novel, interpretable modelling protocol that reduces reliance on costly surveys and provides a controlled way to enhance model complexity and accuracy.

Findings

Effective on toy and realistic examples

Uses traffic counts as the main data source

Offers a pathway to multimodal system modeling

Abstract

Macroscopic transport modelling aims to predict traffic flows after proposed public policy interventions, such as a new road or railway section or a temporary road closure. As such, it is a vital step in infrastructure planning and development. Traditionally, building a transport model has relied on complex understanding of socio-economic characteristics of the population requiring expensive data collection via surveys, which are prone to biases. Previous numerical frameworks to optimize transport models to fit observed traffic flows are not easily-interpretable and can lead to overfit. We present here an alternative: a data-driven modelling protocol with objective function based on traffic counts, which can be nowadays cheaply and reliably obtained; explainable model weights; and a controlled path to increase model complexity and accuracy. We demonstrate our approach on several toy and realistic examples, and suggest ways to generalize to multimodal systems including public transport.