Geo AI-Assisted Housing Growth Planning and Architectural Neighbourhood Design in Nigerian Secondary Cities Through an Integrated Framework

Nigeria's secondary cities face fragmented expansion, under-serviced housing layouts, environmental exposure and uneven infrastructure provision. This critical structured narrative review examines how GeoAI and complementary geospatial decision-support methods can support housing-growth planning and architectural neighbourhood design in Nigerian secondary cities through an integrated architecture-planning lens. The analytical corpus comprises 46 peer-reviewed articles published between 2010 and 2025, supplemented by methodological, policy, statutory and governance sources. Evidence is synthesised across urban-growth modelling, conventional remote sensing and GIS, GeoAI/machine-learning applications, planning-support systems, housing-location suitability, infrastructure sequencing, Nigerian urbanisation and responsible-AI governance. The synthesis indicates that geospatial analysis can identify growth pressure, service gaps, environmental constraints and candidate housing locations, while GeoAI-specific methods may additionally support classification, prediction and pattern recognition where suitable data and validation procedures are available. Spatial suitability, however, does not itself produce a liveable neighbourhood. Within the proposed framework, Urban and Regional Planning interprets land-use suitability, infrastructure sequencing, participation and development-control requirements. At the same time, Architecture translates preferred planning options into climate-responsive, service-aware and socially liveable neighbourhood alternatives. The paper proposes a testable staged adoption pathway beginning with verified spatial data, explicit decision criteria, professional interpretation, architectural design testing and participatory validation before advanced predictive GeoAI functions are institutionalised. Ado-Ekiti is used only as an illustrative application, not an empirical case study.