Modelling mean radiant temperature in complex urban areas using a convolutional network approach

We present a novel method to model spatial maps of mean radiant temperature (T_mrt) in complex urban areas using a special type of fully convolutional networks - U-Net - for image to image processing. T_mrt is one of the driving factors of daytime human thermal comfort and underlies great spatial and temporal variabilities, especially in complex urban areas. Various micro scale (building-resolving) models exist to model T_mrt in urban settings. However, these models are computational expensive, albeit to varying degrees. This means, study area and time might be limited depending on spatial and temporal resolution. While this is sufficient for case studies where micro-level processes are modelled for different neighbourhoods in limited time periods, accurate calculations over a long time period are not possible (e.g. downscaling global climate projections). To overcome these computational drawbacks of physical models, we present a U-net approach for modelling T_mrt in complex urban areas.

U-Nets are special types of encoder-decoder networks and allow precise image to image processing. In this study, T_mrt (at 1.1 m a.g.l.) is modelled by SOLWEIG model for 62 areas (500 x 500 m²) and on 54 days for the city of Freiburg, Germany. Training data is sampled randomly after clustering. The spatial and temporal input of SOLWEIG are in turn used as input features for the U-Net. The U-Net is trained on 56 areas and on 45 days and tested on the remaining areas and days. In addition, data from a T_mrt measurement campaign is used to validate SOLWEIG and U-Net model output.

Results indicate that the proposed U-Net approach is capable to provide T_mrt in complex urban areas sufficiently. A correlation of > 0.9 and a MAE of 1.53°C between SOLWEIG and the U-Net is observed. Results show a higher MAE during day than night, which can be partly explained by the difference of absolute T_mrt values at day and night, but also by more complex prediction conditions during day: cloud cover and thus varying radiation, but also low sun angle in the morning / evening. In addition, computing times for T_mrt map predictions are significantly faster than physical models.