On the possible benefits of deep learning for spectral preprocessing. (2nd October 2021)

• Record Type: Journal Article
• Authors: Helin, Runar; Indahl, Ulf Geir; Tomic, Oliver; Liland, Kristian Hovde
• Other Names: Duponchel Ludovic guestEditor.; Bro Rasmus guestEditor.
• Is Part Of: Journal of chemometrics. Volume 36:Number 2(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-10-02
• Subjects: artificial neural networks -- deep learning -- model validation -- preprocessing -- spectroscopy; Chemistry -- Mathematics -- Periodicals; Chemistry -- Statistical methods -- Periodicals; 542.85
• DOI: 10.1002/cem.3374
• Languages: English
• ISSNs: 0886-9383

Abstract

Abstract: Preprocessing is a mandatory step in most types of spectroscopy and spectrometry. The choice of preprocessing method depends on the data being analysed, and to get the preprocessing right, domain knowledge or trial and error is required. Given the recent success of deep learning‐based methods in numerous applications and their ability to automatically detect patterns in data, we aimed at exploring the possibilities of using such methods for preprocessing. Our study considered a flexible but systematic investigation of spectroscopic preprocessing methods (classical and deep learning‐based) combined with predictive modelling, including both traditional linear modelling and artificial neural network‐based modelling. The main ambition of the present work was to assess if the advantages of deep learning‐based methods in spectral preprocessing are sufficient to justify the additional efforts in model set‐up and training and the possible losses of interpretability and transparency. With the use of data from different vibrational spectroscopy techniques, we demonstrated that deep learning‐based preprocessing successfully increased the predictive performance of our models but that classical preprocessing still is a good alternative or even the best one in some cases. A significant increase in effort was required when using deep learning‐based preprocessing together with linear model prediction. Compared with classical preprocessing techniques, deep learning‐based preprocessing decreased the transparency and showed only modest improvements of the prediction performance of linear models. Our conclusion is that deep learning‐based preprocessing is best suited when integrated in neural network predictions. Abstract : This study compares classical and deep learning (DL)‐based spectral preprocessing. Experiments were performed to find combinations of preprocessing and predictive modelling that are sensible for "chemometric size" datasets. The study includes a discussion about a possible overkill of applying DL preprocessing in light of the simple relations given by Beer–Lambert's law. DL‐based preprocessing was shown to increase the predictive performance but came with a considerable extra cost in the increased effort of setting up and running the models.