Deep learning for near-infrared spectral data modelling: Hypes and benefits

被引：105

作者：

Mishra, Puneet ^{[1
]}

Passos, Dario ^{[2
,3
]}

Marini, Federico ^{[4
]}

Xu, Junli ^{[5
]}

Amigo, Jose M. ^{[6
,7
]}

Gowen, Aoife A. ^{[5
]}

Jansen, Jeroen J. ^{[8
]}

Biancolillo, Alessandra ^{[9
]}

Roger, Jean Michel ^{[10
,11
]}

Rutledge, Douglas N. ^{[11
,12
]}

Nordon, Alison

机构：

[1] Wageningen Food & Biobased Res, POB 17,Bornse Weilanden 9, NL-6700 AA Wageningen, Netherlands

[2] Univ Algarve, CEOT, Campus de Gambelas,FCT Ed2, P-8005189 Faro, Portugal

[3] Univ Algarve, Phys Dept, FCT Ed2,Campus Gambelas, P-8005189 Faro, Portugal

[4] Univ Roma La Sapienza, Dept Chem, Piazzale Aldo Moro 5, I-00185 Rome, Italy

[5] Univ Coll Dublin UCD, Sch Biosyst & Food Engn, Belfield, Dublin, Ireland

[6] Basque Fdn Sci, IKERBASQUE, Bilbao 48011, Spain

[7] Univ Basque Country UPV EHU, Dept Analyt Chem, POB 644, Bilbao 48080, Basque Country, Spain

[8] Radboud Univ Nijmegen, Inst Mol & Mat, POB 9010, NL-6500 GL Nijmegen, Netherlands

[9] Univ Aquila, Dept Phys & Chem Sci, Via Vetoio, I-67100 Coppito, Laquila, Italy

[10] Univ Montpellier, INRAE Montpellier Inst Agro, ITAP, Montpellier G1 1XL, France

[11] ChemHouse Res Grp, Ctr Proc Analyt & Control Technol, Montpellier G1 1XL, France

[12] Charles Sturt Univ, Natl Wine & Grape Ind Ctr, Wagga Wagga, Australia

来源：

TRAC-TRENDS IN ANALYTICAL CHEMISTRY | 2022年 / 157卷

基金：

爱尔兰科学基金会;

关键词：

Artificial intelligence; Neural networks; NIR; Near-infrared; Spectroscopy; Chemometrics; ARTIFICIAL NEURAL-NETWORKS; SOLVING CHEMICAL PROBLEMS; SOIL PROPERTIES; REGRESSION; PREDICTION;

D O I：

10.1016/j.trac.2022.116804

中图分类号：

O65 [分析化学];

学科分类号：

070302 ; 081704 ;

摘要：

Deep learning (DL) is emerging as a new tool to model spectral data acquired in analytical experiments. Although applications are flourishing, there is also much interest currently observed in the scientific community on the use of DL for spectral data modelling. This paper provides a critical and compre-hensive review of the major benefits, and potential pitfalls, of current DL tecnhiques used for spectral data modelling. Although this work focuses on DL for the modelling of near-infrared (NIR) spectral data in chemometric tasks, many of the findings can be expanded to cover other spectral techniques. Finally, empirical guidelines on the best practice for the use of DL for the modelling of spectral data are provided. (c) 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

引用

页数：8

共 55 条

[1] Spectral-Spatial Classification of Hyperspectral Images: Three Tricks and a New Learning Setting [J].

Acquarelli, Jacopo ;

Marchiori, Elena ;

Buydens, Lutgarde M. C. ;

Thanh Tran ;

van Laarhoven, Twan .

REMOTE SENSING, 2018, 10 (07)

[2] Convolutional neural networks for vibrational spectroscopic data analysis [J].

Acquarelli, Jacopo ;

van Laarhoven, Twan ;

Gerretzen, Jan ;

Tran, Thanh N. ;

Buydens, Lutgarde M. C. ;

Marchiori, Elena .

ANALYTICA CHIMICA ACTA, 2017, 954 :22-31

[3]

Anderson N., 2020, MANGO DMC SPECTRA AN, V2020

[4] Achieving robustness across season, location and cultivar for a NIRS model for intact mango fruit dry matter content. II. Local PLS and nonlinear models [J].

Anderson, N. T. ;

Walsh, K. B. ;

Flynn, J. R. ;

Walsh, J. P. .

POSTHARVEST BIOLOGY AND TECHNOLOGY, 2021, 171

[5] Achieving robustness across season, location and cultivar for a NIRS model for intact mango fruit dry matter content [J].

Anderson, N. T. ;

Walsh, K. B. ;

Subedi, P. P. ;

Hayes, C. H. .

POSTHARVEST BIOLOGY AND TECHNOLOGY, 2020, 168

[6] Comparison of augmentation and pre-processing for deep learning and chemometric classification of infrared spectra [J].

Blazhko, Uladzislau ;

Shapaval, Volha ;

Kovalev, Vassili ;

Kohler, Achim .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2021, 215

[7] End-to-end quantitative analysis modeling of near-infrared spectroscopy based on convolutional neural network [J].

Chen, Yuan-Yuan ;

Wang, Zhi-Bin .

JOURNAL OF CHEMOMETRICS, 2019, 33 (05)

[8] Modern practical convolutional neural networks for multivariate regression: Applications to NIR calibration [J].

Cui, Chenhao ;

Fearn, Tom .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2018, 182 :9-20

[9] Deep learning in analytical chemistry [J].

Debus, Bruno ;

Parastar, Hadi ;

Harrington, Peter ;

Kirsanov, Dmitry .

TRAC-TRENDS IN ANALYTICAL CHEMISTRY, 2021, 145

[10] A practical convolutional neural network model for discriminating Raman spectra of human and animal blood [J].

Dong, Jialin ;

Hong, Mingjian ;

Xu, Yi ;

Zheng, Xiangquan .

JOURNAL OF CHEMOMETRICS, 2019, 33 (11)

← 1 2 3 4 5 6 →