Learning long term climate-resilient transport adaptation pathways under direct and indirect flood impacts using reinforcement learning

TL;DR

This paper introduces a reinforcement learning-based decision-support framework that helps urban planners develop long-term, climate-resilient transport adaptation strategies by accounting for uncertainties and complex interactions from climate change impacts.

Contribution

It presents a novel integrated approach combining climate projections, hazard modeling, and reinforcement learning to optimize multi-decade infrastructure investment pathways under uncertainty.

Findings

Learned adaptive strategies improve robustness over baseline methods.

Framework successfully applied to Copenhagen's flood management from 2024 to 2100.

Demonstrates transferability to other hazards and urban settings.

Abstract

Climate change is expected to intensify rainfall and other hazards, increasing disruptions in urban transportation systems. Designing effective adaptation strategies is challenging due to the long-term, sequential nature of infrastructure investments, deep uncertainty, and complex cross-sector interactions. We propose a generic decision-support framework that couples an integrated assessment model (IAM) with reinforcement learning (RL) to learn adaptive, multi-decade investment pathways under uncertainty. The framework combines long-term climate projections (e.g., IPCC scenario pathways) with models that map projected extreme-weather drivers (e.g. rain) into hazard likelihoods (e.g. flooding), propagate hazards into urban infrastructure impacts (e.g. transport disruption), and value direct and indirect consequences for service performance and societal costs. Embedded in a reinforcement-learning loop, it learns adaptive climate adaptation policies that trade off investment and maintenance expenditures against avoided impacts. In collaboration with Copenhagen Municipality, we demonstrate the approach on pluvial flooding in the inner city for the horizon of 2024 to 2100. The learned strategies yield coordinated spatial-temporal pathways and improved robustness relative to conventional optimization baselines, namely inaction and random action, illustrating the framework's transferability to other hazards and cities.