The decarbonization strategies for the built environment that policy-makers face today from the EU mandate risk being made with incomplete or insufficient information. The consequence of this could be ineffective choices, thus slowing down the ongoing ecological transition, or their high cost, whether borne by the state or citizens. The progressive and unstoppable digitization of the built environment offers information collection and previously unthinkable management opportunities. The construction sector, traditionally lagging behind other industrial sectors, is beginning to produce large quantities of data that can be exploited thanks to the most modern techniques derived from the information technology sector. Among the most promising data sources are energy performance certificates for buildings, which provide a snapshot of the characteristics of buildings, their fabric and plant components, and design forecasts of their energy performances. Analyzing the energy performance certificates through Artificial Intelligence techniques proves the effectiveness of using big data in the construction sector. In particular, in this study, unsupervised machine learning techniques led to an in-depth knowledge of a stock of buildings approaching two hundred thousand units distributed over an almost twenty-four thousand square kilometers area in northern Italy.

Gaining knowledge from big data: energy performance certificate as a source of information to decarbonize the built environment

Re Cecconi, Fulvio;Rampini, Luca
2022-01-01

Abstract

The decarbonization strategies for the built environment that policy-makers face today from the EU mandate risk being made with incomplete or insufficient information. The consequence of this could be ineffective choices, thus slowing down the ongoing ecological transition, or their high cost, whether borne by the state or citizens. The progressive and unstoppable digitization of the built environment offers information collection and previously unthinkable management opportunities. The construction sector, traditionally lagging behind other industrial sectors, is beginning to produce large quantities of data that can be exploited thanks to the most modern techniques derived from the information technology sector. Among the most promising data sources are energy performance certificates for buildings, which provide a snapshot of the characteristics of buildings, their fabric and plant components, and design forecasts of their energy performances. Analyzing the energy performance certificates through Artificial Intelligence techniques proves the effectiveness of using big data in the construction sector. In particular, in this study, unsupervised machine learning techniques led to an in-depth knowledge of a stock of buildings approaching two hundred thousand units distributed over an almost twenty-four thousand square kilometers area in northern Italy.
2022
Proceedings of 22nd International Multidisciplinary Scientific GeoConference SGEM 2022
9786197603521
Artificial Intelligence, Residential buildings, Energy performances, Decarbonisation, Open data
File in questo prodotto:
File Dimensione Formato  
EDA2Decarbonisation_review.pdf

accesso aperto

Descrizione: Pre-Print
: Pre-Print (o Pre-Refereeing)
Dimensione 2.04 MB
Formato Adobe PDF
2.04 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1237144
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact