Simulating satellite urban land surface temperatures: sensitivity to sensor view angle and assumed landscape complexity

Abstract

Urban land surface temperature (LST) from satellite earth observation (EO) varies with sensor view angle. Where these variations are not accounted for, urban LST products are inconsistent through time, limiting their use in urban weather and climate model evaluations and process studies (e.g. urban heat island, building energy balance, human thermal comfort). Obstacle-resolving numerical models (ORM) of urban form and radiation exchanges are being used to: (a) understand relations between EO view angle, the 3-dimensional urban surface, and the surface temperatures from urban land surface models, and (b) evaluate parameterisations (parametric models) that aim to account for LST angular effects for the next operational satellite products. Most ORM are limited to simplified buildings (e.g. cuboids) and surface temperatures by lack of datasets. Novelly, we use both a realistic urban form model and observed surface temperatures to assess the impact of simplifying the urban form and temperature on the modelled LST anisotropy. We test various sets of assumptions in central London by combining ground-based thermal camera observations and the state-of-the-art Discrete Anisotropic Radiative Transfer (DART) model. The high resolution realistic model (< 1 m) includes thermal (surface temperatures varying by sun-surface geometry, shadow history and materials every 30 min) and geometry (sloped roofs, chimneys and vegetation) data. These data are used to simulate brightness temperatures of EO pixels to quantify LST view angle variations.During daytime, a change of view angle of 47° off-nadir corresponds to a difference in LST of up to 5.1 K for the realistic building model. The intermediate-complexity landscape (easily obtainable building geometry/footprints and more idealised surface temperature distributions driven only by shadow patterns) gives the best agreement in simulated LST to the realistic landscape. The directional variations are still captured in total (daytime mean absolute error 0.44 K) when using an idealised ORM representation of the same landscape (cuboid buildings, simplified surface temperature) except for roofs which are near-isotropic. Results suggest that geometry assumptions used in current ORM are suited for evaluation of parametric models used to develop and verify operational LST sensor view angle corrections. Future work should consider more realistic materials and scattering processes including low emissivity glass and metals with challenging specular properties.