A Europe-wide research collaboration combining IoT sensors, machine-learning models and sustainable design to enhance energy performance, climate-adaptation and structural resilience of historic buildings — open-access data and hybrid courses included.
HEIstorical is a pioneering European research initiative that unites universities and research institutions to revolutionize the conservation of historic and heritage buildings. The project integrates artificial intelligence, IoT sensor networks, green technologies, and data-driven methodologies to improve energy efficiency, microclimate adaptation, and seismic resilience. Through higher-education collaboration, digital tools, and open-access data, HEIstorical empowers the next generation of experts in sustainable heritage management.
Innovative strategies for conserving Europe’s architectural heritage by combining traditional methods with AI-driven diagnostics and predictive maintenance.
Using machine learning and IoT-based monitoring to analyze environmental conditions and structural behavior for smarter decision-making in historic buildings.
Sustainable and eco-efficient retrofitting solutions that reduce carbon footprint, optimize energy use, and promote long-term environmental responsibility.
Advanced data modeling and AI-supported simulations to enhance earthquake resistance and minimize structural risks in vulnerable heritage sites.
Our mission is to transform the preservation of historic and heritage buildings by integrating AI, IoT sensor data, and sustainable technologies into higher education research and cross-border collaboration.
Create and validate machine learning models that analyze sensor data to predict structural damage and assess the safety of heritage buildings.
Design eco-efficient retrofitting and energy-saving solutions that maintain cultural authenticity while improving the environmental performance of historic sites.
Develop data-driven seismic risk models and reinforcement guidelines to improve earthquake resistance and ensure long-term building preservation.
Implement hybrid learning modules and international workshops connecting students, academics, and engineers in the field of heritage conservation and digital technologies.
Develop an open-access platform integrating IoT monitoring data, historical documentation, and AI-based analytics for future research and innovation.
Strengthen European networks to advance sustainable heritage preservation through interdisciplinary cooperation and shared digital resources.
The partners consortium will develop and implement a unique model for damage assessment in historical buildings, which incorporates AI through Machine Learning (ML). Data analysis using predictive methods will lead to recommendations for building damage prediction and more importantly, for structural strengthening in order to prevent potential damage and mitigate the risks for buildings with historical value. Students and academic staff will collect on-site data using digital tools, including specially developed application for entering parameters needed for data analysis. All the parameters will be included in an international (freely accessible) database. The database will provide a basis for future research in this field as well as in the field of earthquake protection, both in the member countries of the consortium and possibly beyond. In addition to professors, students will also be involved in the project activities, so that a large number of future engineers can acquire new knowledge and skills and establish contacts with colleagues at home and abroad.
Croatia Research Partner
Serbia Innovation Partner
Turkey Technology Partner
Romania Engineering Partner
Romania Project Coordinator
Croatia Research Partner
Serbia Innovation Partner
Turkey Technology Partner
Romania Engineering Partner
Romania Project Coordinator
Stay updated with the latest developments and upcoming activities
Event
Within the Industrial Engineering and Environmental Protection Conference – IIZS 2025
Research
Groundbreaking findings on seismic resilience published in leading conservation journal.
Data collection
A field class was held for first-year students of the University Master’s program in Civil Engineering – Structural Modeling track.
November 13, 2025
December 5, 2025
January 22, 2025
