This article is written by Dr Marcelo Lampkowski, Expert in Sustainable Infrastructure, Data Governance and Green Digital Transformation at ICLEI Europe.

  • The problem: Europe’s building stock is currently accounting for ~ 40% of the EU’s total energy consumption and an estimated 36% of total Green House Gas (GHG) emissions, requiring decisive public and private action that is based on more precise, reliable data of the distinct characteristics of Europe’s buildings and the building stock as a whole.
  • Why it matters: The size of the task and the absence of precise, workable data makes an effective decarbonisation of the EU building stock a giant roadblock on the way to European climate neutrality by 2050, and more importantly, a more sustainable, energy-secure future.
  • The solution: The MATRYCS Toolbox combines technologies such as big data, machine learning/deep learning and artificial intelligence to drive profitable renovation actions within the building and construction sector and support citizens and local communities to become the masters of their own energy transition.

Accounting for nearly 40% of the EU’s total energy consumption, the decarbonisation of the EU building stock is a giant task – modestly speaking – on the way to achieving climate neutrality by 2050. Addressing this giant roadblock and doing so fast, will require effective policy and renovation measures, as well as public and private investments based on an accurate analysis of the characteristics of individual buildings, as well as the European building stock as a whole. A challenge, if not an outright uphill journey, that necessitates not only large-scale collection and availability of quality data — it requires systematic processing, thorough analysis and insightful interpretation of this vast data as well.

From decarbonisation targets to concrete renovation action with AI

Enter the building stock transition stage: European partners of the EU-funded MATRYCS project concluded the final testing phase of the MATRYCS toolbox. A tool combining technologies such as big data, machine learning/deep learning and artificial intelligence.

💬 Let the author know what you think by leaving a comment below

To what end? To drive precisely the profitable renovation actions within the building sector previously mentioned that are urgently required until 2050. The MATRYCS model is currently demonstrated and validated in 11 real-life large-scale pilots strategically selected to cover different regions and levels, such as regional, national and pan-European.

MATRYCS is helping users to help themselves by allowing them to coherently assess their data centrally within one tool.

Once finalised, MATRYCS users will gain access to a range of data analytics services, focusing on different building lifecycle opportunities and stakeholder perspectives, including digital building twins, improved buildings’ operation, building infrastructure design and EU/national policy assessment for energy efficiency investments. Additionally, these services will be applicable for different building scales, hence from buildings as individual entities (building scale), groups of buildings (district scale), groups of districts (city scale), groups of cities (regional scale) and national and European level.

Large-scale projects to support energy communities and the implementation of local energy and climate plans

What does that mean in practice? Or, to put it differently: what are these large-scale pilot projects doing and why? The city network ICLEI Europe, a MATRYCS partner, tested the MATRYCS Toolbox for policy impact assessments. More concretely, ICLEI coordinated the testing of MATRYCS in support of the implementation, performance evaluation and development of Sustainable Energy and Climate Action Plans (SECAPs). SECAPS are usually designed by local governments as a means to take stock of its current energy situation and GHG emissions, and to define quantifiable actions to reduce its emissions, identify energy efficiency measures and set concrete energy and climate targets.

Another goal is taking action to alleviate energy poverty and increase local energy security. By drawing on a vast amount of existing SECAPS submitted by local governments to initiatives such as the European Covenant of Mayors, MATRYCS is running forecasting, and impact evaluations to empower planners at various levels to not only design more effective building-related measures but to simulate their potential effects via digital test runs based on real-life data.

In addition, MATRYCS was tested by members of the Portuguese renewable energy cooperative, COOPERNICO, to fine-tune the tool's capacity to empower citizens to take an active role in the energy transition by setting up energy communities. Energy communities in the form of organised collective and citizen-driven energy actions are an important means to not only pave the way for a faster clean energy transition led and supported by citizens and private investments, but to increase energy security and democracy by allowing citizens to take actions towards increasing their energy efficiency, lowering their electricity bills and creating local job opportunities.

For citizens to become active players in the transition by taking part in energy communities, they are required to have the know-how and skillset to set up and manage a community of participants, as well as self-consumption monitoring and energy-sharing models. No small fee, even for the most highly motivated individuals, is often seen joining such initiatives. MATRYCS can facilitate both these tasks by providing – amongst others – precise energy predictions, production forecasting, Building Automation and Control (BAC), and technology catalogues for a comprehensive view of community building’s HVAC, lighting and other operating systems.

In other words, MATRYCS is helping users to help themselves by allowing them to coherently assess their data centrally within one tool, thereby actively improving their knowledge and understanding of their energy production dynamics, their self-production management efficiency and building energy performance. Thereby, maximising efficiency while also providing actionable insights into building management and sustainable technology, strengthening the energy community model and security in the transition as a whole.

Establishing a durable data flow for analysing Europe's building stock accurately.

Whereas the social impact of big data and artificial intelligence are currently high on public agendas, these are just two examples of how AI in tools such as MATRYCS can become a driving force towards social and environmental sustainability, if harnessed appropriately. If AI-based tools such as ChatGPT have taught us anything, it’s that their results are only as good as the data they are based on. A reality MATRYCS partners are working on with their EU sister project, BuiltHub – Dynamic EU building stock knowledge hub – and the MATRYCS led Big Data Alliance (BDA).

Whereas the BuiltHub project receives EU-funding to develop a roadmap and inclusive method for sustained dataflows to the EU Building Stock Observatory (BSO), the BDA provides a collaborative space for building stock stakeholders to work together on combining meaningful data sets and applying data analytics to allow tools such as MATRYCS to accurately analyse the characteristics of the EU building stock.

Are we all set for the future then?

The task to decarbonise each of our buildings is massive, and data alone will not be retrofitting in decarbonising any of them. Yet, the availability of qualitative data and, subsequently, more accurate data analytics provide the basis for taking decisive collective actions, by enabling more sustainable and smarter investments and targeted policy frameworks to support them. There is no one-size-fits-all solution for our building stock, but with innovation and fact-based modelling, some solutions might fit a lot better in the future, setting us on a socially acceptable path towards a climate-neutral building stock and, more importantly, a sustainable future.

Done reading? Make sure to share your own tips by leaving a comment below ⬇️

(Image credit: Unsplash)