AI-Assisted Passive Design Strategies for Climate-Responsive Affordable Housing in Nigeria: A Systematic Literature Review and Conceptual Framework

The increasing demand for affordable housing, environmental concerns, and rapid urbanization have increased the need for sustainable design solutions in developing countries. The conventional housing design in Nigeria is often not climatically responsive, which leads to excessive operational energy consumption and reduced indoor thermal comfort. Artificial Intelligence (AI) provides new opportunities to improve early-stage design decisions, enabling passive strategies that reduce environmental impacts while maintaining affordability. This paper presents a Systematic Literature Review (SLR) on the potential of AI-assisted passive design strategies for climate-responsive affordable housing in Nigeria. The review discusses the most used technologies for optimizing building orientation, natural ventilation, daylighting, solar shading and material selection: machine learning, generative design, predictive analytics, artificial neural networks, and AI-integrated Building Information Modeling (BIM). Research activity is expanding globally but little evidence exists related to affordable housing in tropical developing countries. Based on the review results, the research proposes an AI-assisted passive design framework to integrate climate and site data, AI-based design analysis, passive design optimization, building performance evaluation and iterative decision support. The framework offers architects, housing developers, and policymakers a systematic approach to improve energy efficiency, occupant comfort, and climate resilience in affordable housing. The study contributes to the practice of sustainable architecture by demonstrating how AI can improve climate-responsive design and contribute to the general goals of digital innovation and sustainable development in Nigeria’s built environment.