EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Reinforcement learning–based adaptive strategies for climate change adaptation: An application for coastal flood risk management

Kairui Feng iD, Ning Lin iD, Robert E Kopp iD, Siyuan Xian, Michael Oppenheimer iD

Proceedings of the National Academy of Sciences · 25.03.2025 · 122 (12)

DOI: 10.1073/pnas.2402826122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 18.03.2025. Verfasst von Kairui Feng und 4 weiteren Autor:innen. Beteiligte Einrichtung: National Key Laboratory of Autonomous Intelligent Unmanned Systems, Tongji University, Shanghai 201210, China. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Science Foundation (NSF), MOST | National Natural Science Foundation of China (NSFC), Shanghai Municipal Science and Technology Major Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional computational models of climate adaptation frameworks inadequately consider decision-makers’ capacity to learn, update, and improve decisions. Here, we investigate the potential of reinforcement learning (RL), a machine learning technique that efficaciously acquires knowledge from the environment and systematically optimizes dynamic decisions, in modeling and informing adaptive climate decision-making. We consider coastal flood risk mitigations for Manhattan, New York City, USA (NYC), illustrating the benefit of continuously incorporating observations of sea-level rise into systematic designs of adaptive strategies. We find that when designing adaptive seawalls to protect NYC, the RL-derived strategy significantly reduces the expected net cost by 6 to 36% under the moderate emissions scenario SSP2-4.5 (9 to 77% under the high emissions scenario SSP5-8.5), compared to conventional methods. When considering multiple adaptive policies, including accomodation and retreat as well as protection, the RL approach leads to a further 5% (15%) cost reduction, showing RL’s flexibility in coordinatively addressing complex policy design problems. RL also outperforms conventional methods in controlling tail risk (i.e., low probability, high impact outcomes) and in avoiding losses induced by misinformation about the climate state (e.g., deep uncertainty), demonstrating the importance of systematic learning and updating in addressing extremes and uncertainties related to climate adaptation.

Schlagwörter

Stichwörter der Autor:innen

climate adaptationcoastal protectionflexible adaptationreinforcement learningsea-level rise

Autor:innen und Institutionen

  • National Key Laboratory of Autonomous Intelligent Unmanned Systems, Tongji University, Shanghai 201210, China.
  • Department of Civil and Environmental Engineering, Princeton University, Princeton, NJ 08544.
  • Department of Earth and Planetary Sciences, Rutgers University, New Brunswick, NJ 08854.
  • Rutgers Climate and Energy Institute, Rutgers University, New Brunswick, NJ 08901.
  • School of Public and International Affairs, Princeton University, Princeton, NJ 08544.
  • Department of Geosciences, Princeton University, Princeton, NJ 08544.

ORCID-Profile: Kairui Feng, Ning Lin, Robert E Kopp, Michael Oppenheimer

Förderung

  • National Science Foundation (NSF)
  • MOST | National Natural Science Foundation of China (NSFC)
  • Shanghai Municipal Science and Technology Major Project

Zitieren

APA

Feng, K., Lin, N., Kopp, R. E., Xian, S., & Oppenheimer, M. (2025). Reinforcement learning–based adaptive strategies for climate change adaptation: An application for coastal flood risk management. Proceedings of the National Academy of Sciences, 122(12). https://doi.org/10.1073/pnas.2402826122

Vancouver

Feng K, Lin N, Kopp RE, Xian S, Oppenheimer M. Reinforcement learning–based adaptive strategies for climate change adaptation: An application for coastal flood risk management. Proceedings of the National Academy of Sciences. 2025;122(12). doi:10.1073/pnas.2402826122

BibTeX
@article{Feng2025,
  author = {Feng, Kairui and Lin, Ning and Kopp, Robert E and Xian, Siyuan and Oppenheimer, Michael},
  title = {Reinforcement learning–based adaptive strategies for climate change adaptation: An application for coastal flood risk management},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2025},
  volume = {122},
  number = {12},
  doi = {10.1073/pnas.2402826122}
}
Kostenlos starten →