Validated Near-Infrared Spectroscopy and Chemometric Modelling for Rapid Quantification of Essential Oil Yield and...

The sandalwood industry remains constrained by destructive, time-intensive assays for essential oil (EO) yield, composition, moisture content, and wood fraction, which limit real-time decision-making. We report a unified near-infrared spectroscopy-artificial intelligence (NIRS-AI) platform for non-destructive analytics across the Santalum album L. value chain. Reflectance and transmittance spectra from solid matrices (disks, logs, chips, and powders), oils, ethanol extracts, and CID-derived emulsions were acquired using benchtop (400-2500 nm) and portable (900-1700 nm) spectrometers and calibrated against hydrodistillation, gas chromatography, extraction, and moisture assays. Advanced chemometric modelling using AI-based machine learning techniques, including regularised regression, ensemble learning, boosting algorithms, and neural networks, was used to capture nonlinear spectral-property relationships and benchmark application-specific predictive performance. Independent external validation yielded R ² values of 0.97 for EO yield, 0.96 and 0.94 for α- and β-santalol, 0.99 for the heartwood-sapwood ratio, 0.86 for oil moisture, 0.98 for ethanol extract yield, and 0.94 for portable emulsion-yield prediction. NIRS also outperformed visible spectra for classifying heartwood, sapwood, inner and outer bark, and transition wood. ΔR ² analysis showed that ensemble models were comparatively robust to preprocessing variation, whereas linear models were more sensitive to changes in the variance structure.