Predicting Air Temperature from Volumetric Urban Morphology with Machine Learning

TL;DR

This paper introduces a fast voxelization method for large-scale urban data, uses Gaussian blurring and image similarity metrics to improve and evaluate machine learning predictions of urban air temperature based on volumetric morphology.

Contribution

A novel efficient voxelization technique for large urban datasets and an improved machine learning model for predicting air temperature from volumetric city data.

Findings

Voxelization method is computationally efficient for large cities.

Gaussian blurring enhances correlation between morphology and temperature.

Model accurately predicts spatial temperature distribution.

Abstract

In this study, we firstly introduce a method that converts CityGML data into voxels which works efficiently and fast in high resolution for large scale datasets such as cities but by sacrificing some building details to overcome the limitations of previous voxelization methodologies that have been computationally intensive and inefficient at transforming large-scale urban areas into voxel representations for high resolution. Those voxelized 3D city data from multiple cities and corresponding air temperature data are used to develop a machine learning model. Before the model training, Gaussian blurring is implemented on input data to consider spatial relationships, as a result the correlation rate between air temperature and volumetric building morphology is also increased after the Gaussian blurring. After the model training, the prediction results are not just evaluated with Mean Square Error (MSE) but some image similarity metrics such as Structural Similarity Index Measure (SSIM) and Learned Perceptual Image Patch Similarity (LPIPS) that are able to detect and consider spatial relations during the evaluation process. This trained model is capable of predicting the spatial distribution of air temperature by using building volume information of corresponding pixel as input. By doing so, this research aims to assist urban planners in incorporating environmental parameters into their planning strategies, thereby facilitating more sustainable and inhabitable urban environments.