Incorporating Quality of Life in Climate Adaptation Planning via Reinforcement Learning

2025-11-05

AI Summary

Climate change intensifies urban flooding, threatening long-term habitability and quality of life (QoL). To address this, we propose the first reinforcement learning (RL) framework explicitly optimizing for QoL, integrating an integrated assessment model (IAM), climate-informed rainfall projections, high-resolution urban flood simulation, transportation accessibility analysis, and a multidimensional QoL index. This end-to-end framework enables automated discovery of dynamically adaptive pathways under deep uncertainty. Unlike conventional static planning approaches, our method autonomously identifies superior long-term adaptation strategies, yielding statistically significant QoL improvements in controlled simulations. The implementation is fully open-source, ensuring full reproducibility and facilitating direct policy application. By unifying physical modeling, behavioral metrics, and sequential decision-making under uncertainty, our work establishes a data-driven, human-centered paradigm for climate adaptation planning.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Learning to Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Urban flooding is expected to increase in frequency and severity as a consequence of climate change, causing wide-ranging impacts that include a decrease in urban Quality of Life (QoL). Meanwhile, policymakers must devise adaptation strategies that can cope with the uncertain nature of climate change and the complex and dynamic nature of urban flooding. Reinforcement Learning (RL) holds significant promise in tackling such complex, dynamic, and uncertain problems. Because of this, we use RL to identify which climate adaptation pathways lead to a higher QoL in the long term. We do this using an Integrated Assessment Model (IAM) which combines a rainfall projection model, a flood model, a transport accessibility model, and a quality of life index. Our preliminary results suggest that this approach can be used to learn optimal adaptation measures and it outperforms other realistic and real-world planning strategies. Our framework is publicly available: https://github.com/MLSM-at-DTU/maat_qol_framework.

Problem

• Addressing urban flooding impacts on Quality of Life using Reinforcement Learning
• Developing climate adaptation strategies under climate change uncertainty
• Identifying optimal long-term adaptation pathways for urban resilience

Innovation

• Using reinforcement learning for climate adaptation planning
• Integrating multiple models into an assessment framework
• Learning optimal adaptation measures to enhance quality of life