A decision support toolkit for deep learning application in Southern vitality research

Urban vitality in the Global South remains underexplored, despite rapid growth in urban big data that enables observation at increasingly fine spatial and temporal scales. Deep learning (DL) methods offer powerful means to analyse such data and capture complex spatiotemporal patterns of urban life; however, existing applications are heavily concentrated in China and the Global North, often overlooking the data constraints and contextual challenges faced by Southern cities. To address this imbalance, this study introduces a decision-support toolkit designed to guide the integration of DL into urban vitality research in Global South contexts. The toolkit combines three structured decision trees (covering the selection of urban vitality variables (across built environment and activity dimensions), big-data sources, and DL task types) with a Weighted Sum Model that ranks DL algorithms based on their frequency and relevance in the literature. A Global South applicability labelling system highlights issues related to data accessibility, contextual suitability, and potential bias. The toolkit is validated through multiple grounded case studies drawn from the literature. Rather than prescribing optimal methods, the toolkit lowers entry barriers by supporting informed, context-sensitive methodological decisions, offering a practical pathway for expanding DL-based urban vitality research in underrepresented contexts.