Machine learning-assisted non-destructive plasticizer identification and quantification in historical PVC objects based on IR spectroscopy
importance 3/10
ai assisted
Cultural Heritage Materials Analysis heritage conservation stage: research
Problem
Identifying and quantifying plasticizers in historical PVC museum objects non-destructively was not previously done on a large, diverse collection.
Why it matters
Knowing plasticizer content helps preserve degraded PVC objects of heritage value in museum collections.
What the AI did
ML classification and regression models were built on a dataset of 100+ PVC objects analysed by chromatographic and spectroscopic techniques; six classification algorithms were compared.
Results
not stated in source
Impact
The abstract states a classification model identifies common plasticizers from spectroscopic data alone, but reports no accuracy figures.
Record
| Venue | Scientific Reports |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Tjaša Rijavec, David Ribar, Jernej Markelj, Matija Strlič, Irena Kralj Cigić |
| Citations | 35 (OpenAlex, at import time) |
| References | 43 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41598-022-08862-1 |
| Open access | gold |
| Keywords | machine learning, IR spectroscopy, PVC, plasticizers, non-destructive analysis, heritage |
Importance rating
3
incremental / niche
Heritage preservation of PVC museum objects; abstract quantifies only a 100+ object collection, a niche conservation benefit.