Climate predictions indicate a strong likelihood of more frequent, intense heat events. Resourcevulnerable, low-income neighbourhood populations are likely to be strongly impacted by future climate change, especially with respect to an energy burden. In order to identify existing and new vulnerabilities to climate change, local authorities need to understand the dynamics of extreme heat events at the neighbourhood level, particularly to identify those people who are adversely affected. A new comprehensive framework is presented that integrates human and biophysical data: occupancy/behaviour, building energy use, future climate scenarios and near-building microclimate projections. The framework is used to create an urban energy model for a low-resource neighbourhood in Des Moines, Iowa, US. Data were integrated into urban modelling interface (umi) software simulations, based on detailed surveys of residents' practices, their buildings and near-building microclimates (tree canopy effects, etc.). The simulations predict annual and seasonal building energy use in response to different climate scenarios. Preliminary results, based on 50 simulation runs with different variable combinations, indicate the importance of using locally derived building occupant schedules and point toward increased summer cooling demand and increased vulnerability for parts of the population. Practice relevance To support planning responses to increased heat, local authorities need to ascertain which neighbourhoods will be negatively impacted in order to develop appropriate strategies. Localised data can provide good insights into the impacts of human decisions and climate variability in low-resource, vulnerable urban neighbourhoods. A new detailed modelling framework synthesises data on occupant-building interactions with present and future urban climate characteristics. This identifies the areas most vulnerable to extreme heat using future climate projections and community demographics. Cities can use this framework to support decisions and climate-adaptation responses, especially for low-resource neighbourhoods. Fine-grained and locally collected data influence the outcome of combined urban energy simulations that integrate human-building interactions and occupancy schedules as well as microclimate characteristics influenced by nearby vegetation.