
























Abstract:Near-infrared (NIR; a.k.a.\ NIRS) deep-learning studies in chemometrics increasingly report mutually inconsistent conclusions regarding convolutional neural network (CNN) design, including small versus large kernels, shallow versus deep architectures, raw spectra versus preprocessing, and single-domain training versus transfer learning. As a result, the same architecture can appear superior in one study and inferior in another, creating a practical impasse for chemometric practitioners. In this review, we argue that these contradictions are not evidence of irreconcilable methods but a structurally expected consequence of uncontrolled moderating variables. Specifically, we trace recurring disagreements to (i) the indirect nature of Vis--NIR measurement in water-dominated matrices, (ii) mismatch between effective receptive field (ERF) and the width of informative spectral structure, and (iii) validation design (including split strategy, hyperparameter tuning budget, and exposure to deployment-like shifts) acting as a hidden hyperparameter that can dominate model ranking. Building on evidence from published chemometrics and spectroscopy studies, we propose a conditional design framework that links architecture and preprocessing choices to spectral physics, dataset regime, and intended deployment scenario. Overall, the proposed perspective moves DL Chemometrics from template-driven architecture selection toward reproducible, physics-aware, and deployment-aligned model comparison.
| Comments: | 19 pages, 1 figure, review article |
| Subjects: | Machine Learning (cs.LG); Optics (physics.optics) |
| MSC classes: | J.2, I.2.m |
| Cite as: | arXiv:2605.02636 [cs.LG] |
| (or arXiv:2605.02636v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.02636 arXiv-issued DOI via DataCite (pending registration) |
From: Dário Passos [view email]
[v1]
Mon, 4 May 2026 14:21:02 UTC (42 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。