GLOBUS: GLObal Building heights for Urban Studies

05/24/2022
by   Harsh G. Kamath, et al.
10

Urban weather and climate studies continue to be important as extreme events cause economic loss and impact public health. Weather models seek to represent urban areas but are oversimplified due to data availability, especially building information. This paper introduces a novel Level of Detail-1 (LoD-1) building dataset derived from a Deep Neural Network (DNN) called GLObal Building heights for Urban Studies (GLOBUS). GLOBUS uses open-source datasets as predictors: Advanced Land Observation Satellite (ALOS) Digital Surface Model (DSM) normalized using Shuttle Radar Topography Mission (SRTM) Digital Elevation Model (DEM), Landscan population density, and building footprints. The building information from GLOBUS can be ingested in Numerical Weather Prediction (NWP) and urban energy-water balance models to study localized phenomena such as the Urban Heat Island (UHI) effect. GLOBUS has been trained and validated using the United States Geological Survey (USGS) 3DEP Light Detection and Ranging (LiDAR) data. We used data from 5 US cities for training and the model was validated over 6 cities. Performance metrics are computed at a spatial resolution of 300-meter. The Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) were 5.15 meters and 28.8 standard deviation and histogram of building heights over a 300-meter grid are well represented using GLOBUS.

READ FULL TEXT

page 3

page 5

page 7

research
08/12/2023

Digital elevation model correction in urban areas using extreme gradient boosting, land cover and terrain parameters

The accuracy of digital elevation models (DEMs) in urban areas is influe...
research
06/09/2023

DeepLCZChange: A Remote Sensing Deep Learning Model Architecture for Urban Climate Resilience

Urban land use structures impact local climate conditions of metropolita...
research
08/04/2020

Design and Deployment of Photo2Building: A Cloud-based Procedural Modeling Tool as a Service

We present a Photo2Building tool to create a plausible 3D model of a bui...
research
12/21/2021

Machine Learning Emulation of Urban Land Surface Processes

Can we improve the modeling of urban land surface processes with machine...
research
07/19/2023

Global Inequality in Cooling from Urban Green Spaces and its Climate Change Adaptation Potential

Heat extremes are projected to severely impact humanity and with increas...
research
09/08/2021

Automated LoD-2 Model Reconstruction from Very-HighResolution Satellite-derived Digital Surface Model and Orthophoto

In this paper, we propose a model-driven method that reconstructs LoD-2 ...
research
09/09/2021

Understanding Cycling Mobility: Bologna Case Study

Understanding human mobility in urban environments is of the utmost impo...

Please sign up or login with your details

Forgot password? Click here to reset