Estimating building energy efficiency from street view imagery, aerial imagery, and land surface temperature data

TL;DR

This study demonstrates that combining street view, aerial imagery, and land surface temperature data with deep learning can effectively estimate building energy efficiency at large scale, reducing reliance on costly on-site audits.

Contribution

It introduces a novel approach using multiple remotely sensed data sources and deep learning to classify building energy efficiency, outperforming traditional baseline models.

Findings

Deep learning model achieved 64.64% F1 score.

Model outperformed baseline k-NN and SVM models by over 12 percentage points.

Combining multiple data sources improves prediction accuracy.

Abstract

Current methods to determine the energy efficiency of buildings require on-site visits of certified energy auditors which makes the process slow, costly, and geographically incomplete. To accelerate the identification of promising retrofit targets on a large scale, we propose to estimate building energy efficiency from widely available and remotely sensed data sources only, namely street view, aerial view, footprint, and satellite-borne land surface temperature (LST) data. After collecting data for almost 40,000 buildings in the United Kingdom, we combine these data sources by training multiple end-to-end deep learning models with the objective to classify buildings as energy efficient (EU rating A-D) or inefficient (EU rating E-G). After evaluating the trained models quantitatively as well as qualitatively, we extend our analysis by studying the predictive power of each data source in an ablation study. We find that the end-to-end deep learning model trained on all four data sources achieves a macro-averaged F1 score of 64.64% and outperforms the k-NN and SVM-based baseline models by 14.13 to 12.02 percentage points, respectively. Thus, this work shows the potential and complementary nature of remotely sensed data in predicting energy efficiency and opens up new opportunities for future work to integrate additional data sources.