Artificial Intelligence for Climate Adaptation: Reinforcement Learning for Climate Change-Resilient Transport

Miguel Costa; Arthur Vandervoort; Carolin Schmidt; João Miranda; Morten W. Petersen; Martin Drews; Karyn Morrisey; Francisco C. Pereira

cs.AIMar 6, 2026

Artificial Intelligence for Climate Adaptation: Reinforcement Learning for Climate Change-Resilient Transport

Authors: Miguel Costa, Arthur Vandervoort, Carolin Schmidt, João Miranda, Morten W. Petersen, Martin Drews, Karyn Morrisey, Francisco C. Pereira

Organizations: Department of Technology, Management and Economics, Technical University of Denmark, 2800 Kgs. Lyngby, Denmark · Present address: School of Management, Technical University of Munich, 80333 Munich, Germany. · Present address: Saint-Gobain Distribution Denmark, 2605 Brøndby, Denmark. · J.E. Cairnes School of Business and Economics, University of Galway, Galway, H91 TK33, Ireland

Abstract

Climate change is expected to intensify rainfall and, consequently, pluvial flooding, leading to increased disruptions in urban transportation systems over the coming decades. Designing effective adaptation strategies is challenging due to the long-term, sequential nature of infrastructure investments, deep climate uncertainty, and the complex interactions between flooding, infrastructure, and mobility impacts. In this work, we propose a novel decision-support framework using reinforcement learning (RL) for long-term flood adaptation planning. Formulated as an integrated assessment model (IAM), the framework combines rainfall projection and flood modeling, transport simulation, and quantification of direct and indirect impacts on infrastructure and mobility. Our RL-based approach learns adaptive strategies that balance investment and maintenance costs against avoided impacts. We evaluate the framework through a case study of Copenhagen's inner city over the 2024-2100 period, testing multiple adaptation options, and different belief and realized climate scenarios. Results show that the framework outperforms traditional optimization approaches by discovering coordinated spatial and temporal adaptation pathways and learning trade-offs between impact reduction and adaptation investment, yielding more resilient strategies. Overall, our results showcase the potential of reinforcement learning as a flexible decision-support tool for adaptive infrastructure planning under climate uncertainty.

Figures & tables

Panel of Figure 1 — Figure 1: Integrated Assessment Model using reinforcement learning to find the best sequence of transport-related adaptation policies for rainfall events in Copenhagen from 2024–2100.

Exp.	Climate Scenario	BO	RL
A	RCP2.6	-119.58 ± 0.25	-118.84 ± 1.10
	RCP4.5	-120.10 ± 0.38	-119.01 ± 0.85
	RCP8.5	-121.24 ± 0.30	-119.23 ± 1.28
B	RCP2.6	-121.19 ± 1.45	-117.87 ± 0.57
	RCP4.5	-120.51 ± 1.71	-117.09 ± 0.64
	RCP8.5	-123.71 ± 1.42	-119.88 ± 1.54

Table 1: Total reward comparing the BO vs. our RL-based strategy. Average results over three runs are reported ± standard deviations for the two experiments (Exp. A and B) and the three climate scenarios (RCP2.6, 4.5, and 8.5).

Figure 2: Comparison of different adaptation strategies. Total reward (top-left, scaled by $10^{8}$ ), and reward components are shown: infrastructure damage costs (top-middle), travel delays (top-right), travel cancellations (bottom-left), actions direct costs (bottom-middle), and action maintenance costs (bottom-right). All values correspond to Danish Krone (DKK). Please note the different y-axis scale across figures.

Figure 3: Average (and standard deviations shaded) for all five reward components over the period 2024–2100 under the RCP4.5 climate scenario. While Random Control reduces impacts through high and persistent investment costs, the RL policy achieves sustained impact reduction with substantially lower and more stable adaptation expenditures. All values correspond to Danish Krone (DKK). Please note the different y-axis scale across subfigures.

Figure 4: Adaptation measures taken over time per zone in Copenhagen’s city center for one episode (run) for a RCP4.5 scenario.

Figure 5: Density of actions used over time for 10 runs for a RCP4.5 scenario. Bioretention Planters are shown in top-left, Soakaways in top-right, Storage Tanks in bottom-left, and Porous Asphalt in bottom-right.

	RCP2.6	RCP4.5	RCP8.5
Infrastructure damage	8.00 ± 0.18 $\times 10^{8}$	7.90 ± 0.13 $\times 10^{8}$	8.05 ± 0.19 $\times 10^{8}$
Travel delays	6.55 ± 0.10 $\times 10^{9}$	6.01 ± 0.06 $\times 10^{9}$	5.54 ± 0.17 $\times 10^{9}$
Travel cancellations	1.63 ± 0.10 $\times 10^{9}$	1.61 ± 0.09 $\times 10^{9}$	1.49 ± 0.10 $\times 10^{9}$
Action costs	1.73 ± 0.09 $\times 10^{9}$	2.32 ± 0.11 $\times 10^{9}$	3.27 ± 0.34 $\times 10^{9}$
Action maintenance costs	3.46 ± 0.32 $\times 10^{7}$	4.23 ± 0.21 $\times 10^{7}$	1.88 ± 0.57 $\times 10^{8}$
Total reward	1.07 ± 0.02 $\times 10^{11}$	1.08 ± 0.01 $\times 10^{11}$	1.13 ± 0.02 $\times 10^{11}$

Table 2: Total reward and costs per reward component using different climate scenarios (RCP2.6, RCP4.5, and RCP8.5) over different 10 runs. Average results are reported ± standard deviations.

Belief Scenario	Reality Scenario	Reward
RCP2.6	RCP2.6	-107.42 ± 1.55
	RCP4.5	-107.53 ± 1.54
	RCP8.5	-109.94 ± 1.19
RCP4.5	RCP2.6	-107.42 ± 1.55
	RCP4.5	-107.67 ± 1.29
	RCP8.5	-109.45 ± 1.15

Table 3: Total reward using an RL strategy that was designed using various climate beliefs and reality scenario pairs. Average results are reported ± standard deviations.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Adaptation Measure	Effect	Implementation details	Implementation costs (DKK)	Maintenace costs (DKK/year)	Lifetime (years)
Bioretention planter	Captures 2 $m^{3}$ of water runoff	Applied every 30m of road	14312 per planter	24 per planter	40
Soakaway	Captures 5.4 $m^{3}$ of water runoff	Applied once per road	7273	1.9	30
Storage tank	Captures 15 $m^{3}$ of water runoff	Applied once per road	104896	5	50
Porous asphalt	Captures 0.3m of water depth	Replaces the road with this pavement type	995.77 per m2 of surface area	0.635 per $m^{2}$ of surface area	30
Pervious concrete	Captures 0.45m of water depth	Replaces the road with this pavement type	1199.81 per m2 of surface area	0.635 per $m^{2}$ of surface area	30
PICP	Captures 0.25m of water depth	Replaces the road with this pavement type	1046.78 per m2 of surface area	5.195 per $m^{2}$ of surface area	50

Appendix

Table 4: Adaptation measure details used in our framework.

Reinforcement Learning

Reinforcement learning studies how agents learn sequential decisions from rewards and interaction, balancing exploration, performance, safety, and adaptation.

See all 1,717 papers

Instance-Conditioned Adaptation for Large-scale Generalization of Neural Routing Solver
May 3, 2024Changliang Zhou, Xi Lin, Zhenkun Wang +3Neural Network Generalization Intelligent Transportation Systems
Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology, School of Automation and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen 518055, China · School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an 710049, China · Huawei Noah’s Ark Lab, Hong Kong SAR, China +1
ADORN: Adaptive Drift handling for Open RAN using Reinforcement Learning
Jul 9, 2026Ashit Kumar Subudhi, Bhargav Chirumamilla, Shubham Vaishnav +5Concept Drift Open Radio Access Network
Indian Institute of Technology Dharwad, Karnataka, India · Johns Hopkins University, USA · Stockholm University, Sweden +2
From Rainfall to Road-Network Functionality: Transferable Graph Forecasting for Flood-Disrupted Transportation Networks
Oct 10, 2026Junyan Wang, Naiyu WangSpatiotemporal Forecasting Spatiotemporal GNNs
College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China

May 3, 2024J/K move · Enter open · S save

Instance-Conditioned Adaptation for Large-scale Generalization of Neural Routing Solver

Changliang Zhou, Xi Lin, Zhenkun Wang, Xialiang Tong+2

Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology, School of Automation and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen 518055, China · School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an 710049, China · Huawei Noah’s Ark Lab, Hong Kong SAR, China+1

Neural Network Generalization Intelligent Transportation Systems Vehicle Routing Neural Combinatorial Optimization

Open paper AskPDF arXiv

In modern intelligent transportation systems (ITS), particularly in freight transportation and logistics, real-time route planning is crucial. It presents unique challenges driven by high uncertainty in service requests, where the number of service customers can vary drastically, ranging from hundreds to thousands. Existing neural methods struggle to maintain performance under such significant variations, which severely limits their practical applicability. To address this crucial shortcoming, this work proposes a novel Instance-Conditioned Adaptation Model (ICAM) designed for better large-scale generalization. In particular, we design a simple yet efficient instance-conditioned adaptation function that adjusts the policy based on the specific geometry and density of the current traffic scenario to improve model adaptability with minimal computational overhead. Furthermore, we propose a powerful yet low-complexity instance-conditioned adaptation module to generate better solutions for instances across various scales. Extensive experiments on synthetic, benchmark, and real-world instances demonstrate that ICAM can consistently achieve promising generalization performance across four widely studied large-scale route planning scenarios. Notably, our proposed method delivers high-quality solutions with remarkably fast inference speed, providing a scalable and efficient solution for real-time intelligent transportation operations. Our code is available at https://github.com/CIAM-Group/ICAM.

Abstract

Reinforcement Learning

Explore similar work

Instance-Conditioned Adaptation for Large-scale Generalization of Neural Routing Solver

ADORN: Adaptive Drift handling for Open RAN using Reinforcement Learning

From Rainfall to Road-Network Functionality: Transferable Graph Forecasting for Flood-Disrupted Transportation Networks