TY - JOUR
T1 - DeepUrbanDownscale
T2 - A physics informed deep learning framework for high-resolution urban surface temperature estimation via 3D point clouds
AU - Chen, Linwei
AU - Fang, Bowen
AU - Zhao, Lei
AU - Zang, Yu
AU - Liu, Weiquan
AU - Chen, Yiping
AU - Wang, Cheng
AU - Li, Jonathan
N1 - Publisher Copyright:
© 2021
PY - 2022/2
Y1 - 2022/2
N2 - Accurate high-resolution downscaling of surface climate variables (such as surface temperature) over urban areas has long been a critical yet unresolved research problem in the field of urban climate and environmental sciences. In this paper, we propose a novel physics informed neural network (PINN) based framework: DeepUrbanDownscale (DUD) for high-resolution urban surface temperature estimation. Anchored in process-based modeling and satellite remote sensing, the DUD network leverages the high-precision 3D point clouds to achieve accurate urban land surface temperature (LST) estimation at an ultra-high spatial resolution. This network, ingesting the high-precision land surface geometry information derived from 3D point clouds and guided by the atmospheric physics related to surface temperature, constructs a physics informed data-driven framework to fit high-resolution temperature distribution, which is otherwise difficult to be obtained by physical (numerical) simulations or traditional machine learning. Specifically, the proposed DUD network contains two branches: The Global Feature Perception (GPFP) branch and Local Urban Surface Perception (LUSP) branch. The former considers the broader-scale urban physical parameters, constraining the estimation results in accordance with the relevant physical laws. The latter, by employing a proposed local spatial coefficient index (LSCI), which is based on 3D point clouds, the estimation performance is further improved at a very high resolution. Results from designed experiments demonstrate that the proposed DUD network predicts the urban LST on a 30-by-30 m grid with the estimated error less than 0.2 Kelvin compared to the satellite measurement, which is well below the errors of other traditional methods.
AB - Accurate high-resolution downscaling of surface climate variables (such as surface temperature) over urban areas has long been a critical yet unresolved research problem in the field of urban climate and environmental sciences. In this paper, we propose a novel physics informed neural network (PINN) based framework: DeepUrbanDownscale (DUD) for high-resolution urban surface temperature estimation. Anchored in process-based modeling and satellite remote sensing, the DUD network leverages the high-precision 3D point clouds to achieve accurate urban land surface temperature (LST) estimation at an ultra-high spatial resolution. This network, ingesting the high-precision land surface geometry information derived from 3D point clouds and guided by the atmospheric physics related to surface temperature, constructs a physics informed data-driven framework to fit high-resolution temperature distribution, which is otherwise difficult to be obtained by physical (numerical) simulations or traditional machine learning. Specifically, the proposed DUD network contains two branches: The Global Feature Perception (GPFP) branch and Local Urban Surface Perception (LUSP) branch. The former considers the broader-scale urban physical parameters, constraining the estimation results in accordance with the relevant physical laws. The latter, by employing a proposed local spatial coefficient index (LSCI), which is based on 3D point clouds, the estimation performance is further improved at a very high resolution. Results from designed experiments demonstrate that the proposed DUD network predicts the urban LST on a 30-by-30 m grid with the estimated error less than 0.2 Kelvin compared to the satellite measurement, which is well below the errors of other traditional methods.
KW - 3D point cloud
KW - Deep urban downscale
KW - Physics informed neural network
UR - http://www.scopus.com/inward/record.url?scp=85121985711&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85121985711&partnerID=8YFLogxK
U2 - 10.1016/j.jag.2021.102650
DO - 10.1016/j.jag.2021.102650
M3 - Article
AN - SCOPUS:85121985711
SN - 1569-8432
VL - 106
JO - International Journal of Applied Earth Observation and Geoinformation
JF - International Journal of Applied Earth Observation and Geoinformation
M1 - 102650
ER -