Artificial intelligence (AI) is emerging as a transformative tool for stormwater management with the potential to enhance resilience, efficiency, and equity across urban water systems. This paper examines the opportunities and challenges of integrating AI particularly machine learning (ML) and hybrid physics-ML approaches into stormwater management. This paper categorizes opportunities into three domains: Observation (real-time monitoring, automated inspections, and water quality monitoring that generate continuous, high-resolution datasets); Analysis (predictive modeling, optimize infrastructure design, and simulate system performance and future scenarios to inform decision-making); and Governance (policy formulation, regulatory compliance, and investment decisions). AI in urban and infrastructure systems faces several significant barriers, including data quality and availability, model accuracy, and scalability issues. These challenges are combined with institutional and regulatory frameworks that are not well-suited to adaptive AI systems, as well as ethical concerns related to fairness, transparency, and trust. This study proposes the development of hybrid physical–AI models, standardized data protocols, and governance frameworks that prioritize equity and accountability to address these barriers. This paper argues that the future of AI in stormwater management depends not only on technical innovation but also on thoughtful integration into planning, policy, and community engagement. This study proposes research priorities including standardized data-sharing infrastructure, enhanced transferability methods, and explicit approaches for uncertainty communication. AI Capacity building, stakeholder-inclusive pilot projects, and equity-centered design would be practical steps to shift stormwater management from reactive responses to proactive. The integration of AI into stormwater practice thus represents a critical frontier for advancing urban resilience, environmental sustainability, and social equity. AI can improve how cities plan, monitor, and manage stormwater systems using real-time and historical data. Data gaps, model limits, and outdated regulations remain key barriers to using AI in stormwater practice. Hybrid AI models, shared data standards, and fair policies can shift stormwater management from reactive to proactive.
Rahman et al. (Thu,) studied this question.