Using machine learning to enrich building databases : Methods for tailored energy retrofits
(2020) In Energies 13(10).- Abstract
Building databases are important assets when estimating and planning for national energy savings fromenergy retrofitting. However, databases often lack information on building characteristics needed to determine the feasibility of specific energy conservation measures. In this paper, machine learning methods are used to enrich the Swedish database of Energy Performance Certificates with building characteristics relevant for a chosen set of energy retrofitting packages. The study is limited to the Swedish multifamily building stock constructed between 1945 and 1975, as these buildings are facing refurbishment needs that advantageously can be combined with energy retrofitting. In total, 514 ocular observations were conducted in Google... (More)
Building databases are important assets when estimating and planning for national energy savings fromenergy retrofitting. However, databases often lack information on building characteristics needed to determine the feasibility of specific energy conservation measures. In this paper, machine learning methods are used to enrich the Swedish database of Energy Performance Certificates with building characteristics relevant for a chosen set of energy retrofitting packages. The study is limited to the Swedish multifamily building stock constructed between 1945 and 1975, as these buildings are facing refurbishment needs that advantageously can be combined with energy retrofitting. In total, 514 ocular observations were conducted in Google Street View of two building characteristics that were needed to determine the feasibility of the chosen energy retrofitting packages: (i) building type and (ii) suitability for additional façade insulation. Results showed that these building characteristics could be predicted with an accuracy of 88.9% and 72.5% respectively. It could be concluded that machine learning methods show promising potential to enrich building databases with building characteristics relevant for energy retrofitting, which in turn can improve estimations of national energy savings potential.
(Less)
- author
- Von Platten, Jenny LU ; Sandels, Claes ; Jörgensson, Kajsa ; Karlsson, Viktor ; Mangold, Mikael and Mjörnell, Kristina LU
- organization
- publishing date
- 2020-05-19
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Artificial intelligence, Building database enrichment, Building-specific information, Energy performance certificate, Energy retrofitting, Energy transition, Google street view, Long-term renovation strategy, Machine learning, Support vector machine
- in
- Energies
- volume
- 13
- issue
- 10
- article number
- 2574
- publisher
- MDPI AG
- external identifiers
-
- scopus:85085842074
- ISSN
- 1996-1073
- DOI
- 10.3390/en13102574
- language
- English
- LU publication?
- yes
- id
- 85e52a41-c055-4238-a643-06e0b268ee57
- date added to LUP
- 2020-11-12 09:18:57
- date last changed
- 2022-04-26 21:44:04
@article{85e52a41-c055-4238-a643-06e0b268ee57, abstract = {{<p>Building databases are important assets when estimating and planning for national energy savings fromenergy retrofitting. However, databases often lack information on building characteristics needed to determine the feasibility of specific energy conservation measures. In this paper, machine learning methods are used to enrich the Swedish database of Energy Performance Certificates with building characteristics relevant for a chosen set of energy retrofitting packages. The study is limited to the Swedish multifamily building stock constructed between 1945 and 1975, as these buildings are facing refurbishment needs that advantageously can be combined with energy retrofitting. In total, 514 ocular observations were conducted in Google Street View of two building characteristics that were needed to determine the feasibility of the chosen energy retrofitting packages: (i) building type and (ii) suitability for additional façade insulation. Results showed that these building characteristics could be predicted with an accuracy of 88.9% and 72.5% respectively. It could be concluded that machine learning methods show promising potential to enrich building databases with building characteristics relevant for energy retrofitting, which in turn can improve estimations of national energy savings potential.</p>}}, author = {{Von Platten, Jenny and Sandels, Claes and Jörgensson, Kajsa and Karlsson, Viktor and Mangold, Mikael and Mjörnell, Kristina}}, issn = {{1996-1073}}, keywords = {{Artificial intelligence; Building database enrichment; Building-specific information; Energy performance certificate; Energy retrofitting; Energy transition; Google street view; Long-term renovation strategy; Machine learning; Support vector machine}}, language = {{eng}}, month = {{05}}, number = {{10}}, publisher = {{MDPI AG}}, series = {{Energies}}, title = {{Using machine learning to enrich building databases : Methods for tailored energy retrofits}}, url = {{http://dx.doi.org/10.3390/en13102574}}, doi = {{10.3390/en13102574}}, volume = {{13}}, year = {{2020}}, }