Interesting readings and reports
From 3D Data to Sustainable Governance: A Scalable, High-Fidelity Digital Twin for Urban Energy Management (07/2026)
This chapter presents a low-cost, law-compliant methodology for constructing high-fidelity 3D digital twins (DTs) to facilitate data-driven decision-making in urban environments. The economic and technical barriers caused by the “Building Information Modeling – Geographic Information Systems (BIM-GIS)” silo are addressed by utilizing open and available data from sources such as Google Earth Pro, Streetview, and authoritative open data from National Cadastral Portals. This allows for the integration of 3D data into high-fidelity DT by using game engines, such as UE5, and high-performance, real-time visualization within a global geospatial context.
This article focuses on the role of digital twins and generative AI to explore how these technologies can support the development of PEDs in line with circular economic principles. Based on a case study of an EU Horizon R&D project, this article develops a framework for implementing generative AI-assisted digital twins for PEDs and provides decision support for their integration into 9R circular economic strategies.
CEN TC465 Climate-Neutral Smart Cities and Communities
(12/2025)
The CEN/TC 465 Ad hoc Group on Climate-Neutral and Smart Cities and Communities was created to accelerate sustainability and digitalisation in Europe’s cities. Supporting the EU’s 2050 climate-neutrality goal, the group brought together experts from policy, industry, research, local governments, and initiatives such as ExPEDite partner OASC to translate EU ambitions into concrete standardisation pathways.
Over ten months, the group explored how emerging urban innovations—such as local digital twins, urban data spaces, and digitally enabled solutions—can be supported and scaled through European and international standards. Eight city case studies from across Europe highlighted how local transformation efforts can inform future standardisation, underlining the key role of cities and communities as drivers of innovation.
Catolica Lisbon School of Business & Economics published in this small article their vision on the special living lab approach of ExPEDite.
In this paper, the authors introduce a reinforcement learning framework that uses partially defined rewards along with human feedback to generate energy-efficiency recommendations aimed at reducing energy costs. Their approach generalizes human preferences effectively, decreasing the reliance on detailed labelling from users while also enhancing the robustness of the learned reward model. The proposed method demonstrates improved performance over prior models by striking a balance between user input burden and recommendation quality in energy optimization tasks.
The authors introduce isomorphic structured pruning, a technique in the Non-Intrusive Load Monitoring (NILM) field, which groups functionally equivalent substructures in neural networks to improve pruning consistency and performance for resource-restricted edge deployments. Experiments using a seq2seq CNN architecture on a Mediterranean-based dataset achieved dramatic reductions in model size—up to 97% smaller—and 42× fewer multiply-accumulate operations, while sustaining up to 99% accuracy and 81.4% F1-score. When deployed on two different industrial edge devices, the pruned models delivered over 95% faster inference, alongside more than 85% lower CPU usage and energy consumption, demonstrating isomorphic pruning’s practical value for efficient, high-performance edge computing.
Laurea supports the ExPEDite project by advancing ethical, stakeholder-driven Living Lab work to help cities develop digital-twin–enabled Positive Energy Districts on the path to climate neutrality.
This literature review explores the critical role of building stock modelling in understanding and predicting energy consumption, carbon emissions, and overall building performance across various scales, from individual structures to entire cities. The review highlights the significance of building stock modelling in addressing climate change and investigates the existing methodological frameworks for building stock modelling and their role in facilitating the design of Positive Energy Districts (PEDs), particularly in the context of the ExPEDite project, which aims to develop a digital twin for real-time energy management at the district level.
This report presents an exhaustive literature review within the domain of urban planning, with a particular emphasis on the integration of digital twin technology. The review is a critical component of Work Package 2 of the Expedite project, aiming to consolidate existing knowledge and insights pertinent to the field. Digital twins, as virtual counterparts of physical entities, have emerged as a pivotal innovation in urban planning, offering the potential to revolutionize the way cities are designed, monitored, and managed. By simulating urban environments in a digital space, planners can test scenarios, optimize decision-making, and enhance the sustainability and liveability of urban areas.
In this paper, a method of the energy management system (EMS) in multiple microgrids considering the constraints of power flow based on the three-objective optimization model is presented. The studied model specifications, the variable speed pumps in the water network as well and the storage tanks are optimally planned as flexible resources to reduce operating costs and pollution.