Tabular foundation models for robust calibration of near-infrared chemical sensing data

Robin Reiter, Denis Cornet, Fabien Michel, Lauriane Rouan, Gregory Beurier

arXiv:2605.21544 · 2026-05-23 공개 · arXiv · PDF

classification tabular-foundation-models uncertainty-aware tabpfn regression chemical-sensing calibration-models nir-spectroscopy

Abstract

Near-infrared spectroscopy is increasingly used as a rapid, non-destructive chemical sensing technology for the analysis of food, pharmaceutical, biological, and environmental samples. However, the practical deployment of NIR sensors still depends on calibration models able to handle high-dimensional, collinear spectra, limited sample sizes, preprocessing dependence, spectral outliers, and extrapolation beyond the calibration domain. Here, we evaluate whether tabular foundation models can provide a new calibration strategy for NIR chemical sensing. We benchmark TabPFN on 66 NIR datasets covering 54 regression and 12 classification tasks, and compare direct inference on raw spectra with preprocessing-optimized inference against PLS/PLS-DA, Ridge, Catboost, and one-dimensional convolutional neural networks. The study uses a unified validation framework in which preprocessing and model selection are performed exclusively on calibration data before external test evaluation. In regression, preprocessing-optimized TabPFN achieves the best overall average rank and significantly outperforms PLS, CatBoost, TabPFN on raw spectra, and CNN-1D, while remaining statistically comparable to Ridge. In classification, TabPFN applied directly to raw spectra provides the best average rank, with performance close to the optimized variant. Robustness analyses show that TabPFN provides strong average predictive performance but that its advantage decreases on spectral outliers and extrapolated samples, where classical chemometric models remain competitive. These results suggest that tabular foundation models can complement established chemometric workflows for NIR chemical sensing, especially in small- to medium-sized calibration settings, while highlighting the need for spectroscopy-specific priors and uncertainty-aware deployment strategies.

한국어 요약

한 줄 요약

**[Tabular FM / NIR 화학 센싱]** TabPFN을 66 NIR 데이터셋(54 회귀·12 분류)으로 벤치마크 — 전처리 최적화 TabPFN이 회귀에서 PLS·CatBoost·CNN-1D 능가·Ridge와 동등, raw spectra 분류에서 최고 평균 rank 달성.

핵심 기여도

핵심 아이디어

Tabular foundation 모델이 NIR 같은 specialized 화학 센싱에서도 강력하지만 spectral outlier·extrapolation에서는 chemometric 방법의 spectroscopy-specific prior가 여전히 가치 있으므로, foundation model과 classical chemometrics는 complementary로 결합해야 한다.

기술적 접근법

주요 결과

의의 및 한계

**의의**: NIR 분광에 tabular foundation 모델의 실용성 처음 체계 검증, 통합 validation framework, foundation·chemometrics complementary 발견. **한계**: TabPFN의 outlier·extrapolation 약점 — production에서는 chemometric 모델 병행 필요, spectroscopy-specific prior 부재, uncertainty quantification 미커버.

실용적 활용