The paper presents an integrated approach to improve the solar radiation modelling on facades in large-scale built-up areas. The modelling of the built environment must first be improved in terms of level of detail. Thus, from aerial oblique images, a digital twin of the urban scene is created, allowing to process the facades as textured objects and to detect windows using an artificial intelligence image processing. Reflected radiation is significant on vertical surfaces, but complex to model on large areas. The developed model is based on a simplified radiosity approach, which reduces the volume of analysis, storage and thus the computation time, while producing reliable results. A demonstration of the integrated tool is presented for an urban area in Geneva (1 km2), including a solar energy balance assessment for one of the buildings using the results from the solar modelling. The perspective is to generalise the approach to a larger scale and to complete the solar cadastre of the roofs of the Greater Geneva area with the facades.