Enhancing system resilience to climate change through artificial intelligence: a systematic literature review

Renforcer la résilience face au changement climatique grâce à l’intelligence artificielle: une revue systématique de la littérature

Rym Ayadi, Yeganeh Forouheshfar and Omid Moghadas ()
Additional contact information
Rym Ayadi: City University of London
Yeganeh Forouheshfar: LEDA-DIAL - Développement, Institutions et Modialisation - LEDa - Laboratoire d'Economie de Dauphine - IRD - Institut de Recherche pour le Développement - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres - CNRS - Centre National de la Recherche Scientifique, Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres
Omid Moghadas: REGARDS - Recherches en Economie Gestion Agroressources Durabilité et Santé - CRIEG - Centre de Recherche Interdisciplinaire Economie Gestion - MSH-URCA - Maison des Sciences Humaines de Champagne-Ardenne - URCA - Université de Reims Champagne-Ardenne, CRIEG - Centre de Recherche Interdisciplinaire Economie Gestion - MSH-URCA - Maison des Sciences Humaines de Champagne-Ardenne - URCA - Université de Reims Champagne-Ardenne

Post-Print from HAL

Abstract: The growing urgency of climate change necessitates innovative strategies to enhance system resilience across many sectors. Artificial Intelligence (AI) emerges as a transformative tool in this regard, yet existing research remains fragmented across sectors and regions. We conducted a systematic literature review of 385 peer-reviewed articles published between 2000 and early 2025, following the PRISMA protocol. The analysis classifies AI applications across nine key sectors and evaluates their relevance to adaptation, mitigation, or both. AI methodologies and regional distribution were also assessed. The findings show a dominant focus on adaptation (64.4%), with only 16% of studies addressing mitigation, and 19.4% engaging both. Classical Machine Learning techniques are the most used (51.4%), followed by deep learning models (22.3%). Regional disparities are evident: Asia and global-scale studies account for two-thirds of the literature, while Africa and South America are underrepresented. Sectorally, agriculture and urban infrastructure receive the most attention. Despite the promise of AI, major challenges persist in data access, model transparency, and equitable deployment, particularly in vulnerable regions. This review distinguishes itself by offering a comprehensive, cross-sectoral synthesis and emphasizing system-level resilience. It highlights the need for regionally tailored AI solutions, interdisciplinary collaboration, and ethical frameworks to ensure AI contributes meaningfully to global climate resilience efforts.

Keywords: artificial intelligence (AI); system resilience; climate change; green transition; sustainable development; climate adaptation; machine learning (search for similar items in EconPapers)
Date: 2025
Note: View the original document on HAL open archive server: https://hal.science/hal-05268750v1
References: Add references at CitEc
Citations:

Published in Frontiers in Climate, 2025, 7, pp.1585331. ⟨10.3389/fclim.2025.1585331⟩

Downloads: (external link)
https://hal.science/hal-05268750v1/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-05268750

DOI: 10.3389/fclim.2025.1585331

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().