Artificial intelligence (AI) is increasingly applied to climate finance as a tool for modeling risks, forecasting environmental changes, and supporting sustainability metrics. This study presents a scoping review of 38 peer-reviewed articles to examine how AI methods are used in financial modeling for climate resilience. Using PRISMA guidelines, articles were sourced from Scopus, Web of Science, and Google Scholar and analyzed through thematic coding. The results show that AI techniques, particularly machine learning, deep learning, and hybrid models, are widely adopted for applications including emissions forecasting, carbon pricing, ESG investment analysis, and climate adaptation planning. Four major thematic areas emerged: (1) predictive modeling of climate-related financial risk, (2) AI-driven ESG and carbon finance tools, (3) long-term environmental impact assessment, and (4) AI-supported strategies for business and infrastructure resilience. Despite progress, challenges persist around data access, model interpretability, and integration with financial decision-making frameworks. Few studies fully assess the environmental footprint of AI systems or their deployment in under-resourced regions. The review identifies gaps in empirical validation, regional diversity, and ethical standards. It calls for a collaborative research agenda focused on explainable AI, standardized indicators, and inclusive data systems. Findings provide a roadmap for integrating AI responsibly into climate finance, enabling more resilient economic planning and environmental governance.
Ukatu et al. (Sat,) studied this question.