Purpose and goal: The aim of this project is to adapt and apply ML algorithms to extract features from publicly available databases to enrich urban digital twin models and provide optimized renovation measures for decision-support.
First, the project will develop a ML-based method to extract information needed to simulate the performance of buildings. Second, an optimization method based on Genetic Algorithms will be developed that includes energy simulation, Life Cycle Assessment and a Life Cycle Cost Analysis. Third, the developed methods will be implemented in a decision-support tool. Expected results and effects: Two main outcomes are expected from this project. First, a scalable and future-proof workflow for enriching digital twins of cities with geometric features and semantic data. Second, the decision support tool will provide stakeholders, including real estate managers and municipalities with the right information for renovation planning.
Alexander Hollberg (contact)
Assistant Professor at Chalmers, Architecture and Civil Engineering, Building Technology
Alex Arnoldo Gonzalez Caceres
Postdoc at Chalmers, Architecture and Civil Engineering, Building Technology
Stiftelsen Chalmers Industriteknik
Project ID: 2021-02759
Funding Chalmers participation during 2021–2024
Related Areas of Advance and Infrastructure