Species Identification of Animal Glue Adhesives on Polychrome Cultural Heritage: An Integrated Analytical Approach Combining Gel Sampling, ATR-FTIR Spectroscopy, and Machine Learning

Abstract

Accurate identification of protein adhesive sources in polychrome relics is critical for their conservation. Conventional infrared spectroscopy faces limitations in cross-species discrimination of such adhesives. To address this, we developed a high-resolution analytical system integrating attenuated total reflection Fourier-transform infrared spectroscopy (ATR-FTIR) with multidimensional chemometrics. Spectral fingerprints (4000-500 cm⁻¹) were acquired from the simulated mural samples containing collagen-based adhesives derived from bovine, fish, porcine, and rabbit sources. Detailed analysis was performed in the 1800-1600 cm-1 range, which encompasses the diagnostically critical Amide I band. After dimensionality reduction via Principal Component Analysis (PCA), classification models based on Support Vector Machines (SVM), Bayesian Neural Network (BNN), and Random Forest (RF) achieved cross-validated accuracies exceeding 91.8% for four-species classification in unaged samples, and > 82.5% after 168 hours of UV-accelerated aging. To address the contact limitations of conventional ATR probes on non-planar surfaces, a polyethylene glycol (PEG)-based hydrogel sampling strategy was introduced, enabling effective extraction of trace collagen signals from complex substrates. This method yielded above 86% accuracy in well-preserved samples. However, classification performance decreased significantly with extended aging, with severely degraded samples, such as those subjected to 336 hours of UV-accelerated aging, becoming indistinguishable. This work establishes a novel protocol that integrates minimally invasive sampling with machine learning for species-specific identification of protein adhesives in cultural heritage. The proposed framework proves particularly effective for well-preserved relics, offering significant potential for advancing provenance studies and tailored conservation strategies.