Multi-class semantic segmentation of digital surface models for solar energy applications

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

63 Downloads (Pure)

Abstract

Deep learning-based segmentation of urban digital surface models (DSMs) endures challenges from limited features, class imbalance, and sparse data, which limits the application of DSMs in urban solar energy assessment. In this study we propose a dynamic graph CNN (DGCNN) based segmentation model and address abovementioned problems by adding artificial features, using adaptive-weighted loss function, and introducing a modified spatial transformation module. Our model achieved outstanding performance in predicting the test dataset with an average accuracy of 0.95 and F1 scores of 0.94 after 300 epochs of training. The presented approach inspired several potential applications for solar energy simulation.
Original languageEnglish
Title of host publicationProceedings of the 2nd 4TU/14UAS Research Day on Digitalization of the Built Environment
ChapterData-Driven Buildings and Urban Transformation
Pages42-46
Number of pages5
ISBN (Electronic)978-90-386-5717-2
Publication statusPublished - 27 Mar 2023
Event2nd Research Day on Digitalization of the Built Environment - Eindhoven University of Technology, Eindhoven, Netherlands
Duration: 27 Mar 202327 Mar 2023
https://www.4tu.nl/bouw/Events/DigitalizationEvents/2nd%204TU-14UAS%20Research%20Day%20on%20Digitalization%20of%20the%20Built%20Environment/

Conference

Conference2nd Research Day on Digitalization of the Built Environment
Abbreviated title2nd 4TU/14UAS DBE
Country/TerritoryNetherlands
CityEindhoven
Period27/03/2327/03/23
Internet address

Keywords

  • Solar energy
  • Digital surface model
  • Machine learning

Fingerprint

Dive into the research topics of 'Multi-class semantic segmentation of digital surface models for solar energy applications'. Together they form a unique fingerprint.

Cite this