<b>Leveraging Machine Learning for Resilient Urban Transport Planning under Deep Uncertainty: A Case Study of Abuja, Nigeria</b>

This paper presents a novel, data-driven framework that uses Machine Learning to tackle the deep uncertainties plaguing urban transport planning in developing cities. Using Abuja, Nigeria, as a case study, it integrates diverse data sources to train predictive models that outperform traditional methods. The core of the approach is using these ML models to stress-test policy interventions against volatile future scenarios—like population surges, economic shocks, and climate disruptions—enabling planners to identify robust, resilient strategies that perform well across a range of plausible futures.