Barsanti, Sara GonizziElefante, ErikaNappi, ErnestoCampana, StefanoFerdani, DanieleGraf, HolgerGuidi, GabrieleHegarty, ZackaryPescarin, SofiaRemondino, Fabio2025-09-052025-09-052025978-3-03868-277-6https://doi.org/10.2312/dh.20253178https://diglib.eg.org/handle/10.2312/dh20253178The paper aims at presenting a study on the integration of thermographic data with 3D models for the predictive analysis of possible degradation of wooden furniture due to changing in temperature and humidity. The project is done in collaboration with the Royal Palace of Caserta, a UNESCO site that preserve a huge, majestic collection of ancient furniture. Combining thermographic images and 3D models to proceed with thermic analysis through Finite Element Analysis (FEA) software, the aim is to identify the influence of climate changes on ancient wood to predict their behavior or possible failure in the future. The paper presents the initial results obtained with a new methodological approach and has a fundamental importance in the conservation of ancient wooden objects. AI algorithms have been used to clean the 3D point cloud (denoising), create voxel, hence volumetric models for FEA and for the integration of all the data for the predictive analysis. The innovative part of the project lays in (i) creation of voxel from cleaned denoised 3D point cloud; (ii) accuracy analysis of the models obtained compared with the original point cloud and the 3D mesh; (iii) direct use of these volumetric data in the FEA software for thermic analysis, using thermographic data as boundary conditions.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Machine Learning → Machine Learning algorithms; Computing methodologies → Machine Learning → Learning paradigms; General and reference → Cross-computing tools and techniques Computing methodologies → Machine Learning → Measurements; Applied computing → Physical sciences and engineeringComputing methodologies → Machine Learning → Machine Learning algorithmsComputing methodologies → Machine Learning → Learning paradigmsGeneral and reference → Crosscomputing tools and techniques Computing methodologies → Machine Learning → MeasurementsApplied computing → Physical sciences and engineering10.2312/dh.2025317810 pages