Abstract
Traditional models deliberately simplify millions of consumers into a single, homogeneous, representative agent with perfect market knowledge and rational expectations, limiting their capacity to capture real-world complexities. To address this limitation in mainstream models, this article provides global datasets to parametrise energy consumers within climate-energy-economy models considering climate-driven energy demand, socioeconomic and demographic factors. The datasets emerge from applying geospatial artificial intelligence, machine learning and big data analytics on a range of geospatial parameters at 1 km(2) resolution. Twenty distinctive energy consumers are defined using three heterogeneous geospatial features, eight diverse and two evolving parameters. This parametrisation of consumers strengthens the applicability of climate-energy-economy models to guide effective, equitable and just climate policy design. This comprehensive analysis of complex interactions between climate, socioeconomic and demographic factors supports more realistic decision-making for a sustainable transition reset. This research emphasises the geospatial distribution of energy consumers to enhance technoeconomic assessment, understanding consumer dynamics for consumer-led resource allocation and informed policy implementation. These datasets can be used in climate-energy-economy models to parametrise consumers beyond traditional approaches.