Company or Institution
Institute of Rock Mechanics and Tunnelling, Graz University of Technology
Sustainable Development Goals (SDGs)
SDG 4: Quality Education
SDG 8: Decent Work and Economic Growth
SDG 9: Industry, Innovation and Infrastructure
SDG 11: Sustainable Cities and Communities
SDG 12: Responsible Consumption and Production
SDG 13: Climate Action
SDG 17: Partnerships to achieve the Goal
General description of the AI solution
Data analysis in civil engineering is critical and used to ensure high safety standards, optimize the time and cost of the construction process, leverage sustainable logistics principles, and accelerate the transition to Industry 4.0.
The DaVinci (Data Advance Via INtelligent Content Integration) is a toolkit for accurate data management in civil engineering and advanced processing of technical documentation. Most documents in civil engineering, especially created in the early- to mid-digitalization era, are stored in papers or files containing unstructured information like handwritten notes, engineering sketches, and images. The documents' formats, forms, and completeness vary from site to site. DaVinci is extracting, structuring, and harmonizing data from civil engineering projects' documentation via intelligent parsing and automatic ontology building. After extraction, the harmonized data is stored in a database and can be used to identify and further explore projects with similar conditions worldwide.
Such improvement in knowledge transfer and cross-site information flow enables the proactive management and selection of an effective strategy during the project planning, execution, and maintenance.
Github, open data repository, prototype or working demo
1. Sapronova, A., Unterlaß, P. J., & Marcher, T. (accepted) Towards the development of a harmonized inventory database for decision support: automatized information extraction. 15th International ISRM Congress 2023, Austrian Society for Geomechanics
2. Morgenroth, J., Unterlaß, P. J., Sapronova, A., Khan, U. T., Perras, M. A., Erharter, G. H., & Marcher, T. (2022). Practical recommendations for machine learning in underground rock engineering – On algorithm development, data balancing, and input variable selection. Geomechanics and Tunnelling, 15(5), 650–657. https://doi.org/10.1002/geot.202200047
3. Sapronova, A., Unterlaß, P. J., Dickmann, T., Hecht-Méndez, J., Marcher, T. On the use of synthesised geophysical data to improve rock mass predictions in tunneling. (2022). 4th International Conference on Information Technology in Geo-Engineering, sg. https://www.4iticg.org/
4. Sapronova, A. (Big) Data Lifecycle: best practices and tools for automation. (2021). Workshop Series: Risk Assessment of Waterways: WS 2: Typical procedure for risk analysis in tunneling and underground engineering, Kajang, sg.
5. Dickmann, T., Hecht‐Méndez, J., Krüger, D., Sapronova, A., Unterlaß, P. J., & Marcher, T. (2021). Towards the integration of smart techniques for tunnel seismic applications. Geomechanics and Tunnelling, 14(5), 609–615. https://doi.org/10.1002/geot.202100046