{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T08:27:52Z","timestamp":1767860872948,"version":"3.49.0"},"reference-count":55,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2021,5,15]],"date-time":"2021-05-15T00:00:00Z","timestamp":1621036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Portuguese Foundation for Science and Technology (FCT)","award":["PD\/BD\/128272\/2017"],"award-info":[{"award-number":["PD\/BD\/128272\/2017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Remote sensing technology, such as hyperspectral imaging, in combination with machine learning algorithms, has emerged as a viable tool for rapid and nondestructive assessment of wine grape ripeness. However, the differences in terroir, together with the climatic variations and the variability exhibited by different grape varieties, have a considerable impact on the grape ripening stages within a vintage and between vintages and, consequently, on the robustness of the predictive models. To address this challenge, we present a novel one-dimensional convolutional neural network architecture-based model for the prediction of sugar content and pH, using reflectance hyperspectral data from different vintages. We aimed to evaluate the model\u2019s generalization capacity for different varieties and for a different vintage not employed in the training process, using independent test sets. A transfer learning mechanism, based on the proposed convolutional neural network, was also used to evaluate improvements in the model\u2019s generalization. Overall, the results for generalization ability showed a very good performance with RMSEP values of 1.118 \u00b0Brix and 1.085 \u00b0Brix for sugar content and 0.199 and 0.183 for pH, for test sets using different varieties and a different vintage, respectively, improving and updating the current state of the art.<\/jats:p>","DOI":"10.3390\/s21103459","type":"journal-article","created":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T02:31:34Z","timestamp":1621218694000},"page":"3459","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Application of Hyperspectral Imaging and Deep Learning for Robust Prediction of Sugar and pH Levels in Wine Grape Berries"],"prefix":"10.3390","volume":"21","author":[{"given":"V\u00e9ronique","family":"Gomes","sequence":"first","affiliation":[{"name":"CITAB\u2014Centre for the Research and Technology of Agro-Environmental and Biological Sciences, Inov4Agro\u2014Institute for Innovation, Capacity Building and Sustainability of Agri-Food Production, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"}]},{"given":"Ana","family":"Mendes-Ferreira","sequence":"additional","affiliation":[{"name":"CITAB\u2014Centre for the Research and Technology of Agro-Environmental and Biological Sciences, Inov4Agro\u2014Institute for Innovation, Capacity Building and Sustainability of Agri-Food Production, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"},{"name":"WM&amp;B\u2014Laboratory of Wine Microbiology &amp; Biotechnology, Department of Biology and Environment, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"},{"name":"BioISI\u2014Biosystems &amp; Integrative Sciences Institute, Faculty of Sciences, University of Lisbon, Campo Grande, 1749-016 Lisbon, Portugal"}]},{"given":"Pedro","family":"Melo-Pinto","sequence":"additional","affiliation":[{"name":"CITAB\u2014Centre for the Research and Technology of Agro-Environmental and Biological Sciences, Inov4Agro\u2014Institute for Innovation, Capacity Building and Sustainability of Agri-Food Production, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"},{"name":"Departamento de Engenharias, Escola de Ci\u00eancias e Tecnologia, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1255\/jnirs.566","article-title":"Maturity, variety and origin determination in white grapes (Vitis vinifera L.) using near infrared reflectance technology","volume":"13","author":"Arana","year":"2005","journal-title":"J. Near Infrared Spectrosc."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"S15","DOI":"10.1016\/j.compag.2009.05.011","article-title":"Soluble solids content and pH prediction and varieties discrimination of grapes based on visible\u2013near infrared spectroscopy","volume":"71","author":"Cao","year":"2010","journal-title":"Comput. Electron. Agric."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.foodchem.2016.09.024","article-title":"Characterization of neural network generalization in the determination of pH and anthocyanin content of wine grape in new vintages and varieties","volume":"218","author":"Gomes","year":"2017","journal-title":"Food Chem."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/j.compag.2017.06.009","article-title":"Comparison of different approaches for the prediction of sugar content in new vintages of whole Port wine grape berries using hyperspectral imaging","volume":"140","author":"Gomes","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"6109","DOI":"10.3390\/s110606109","article-title":"Optimization of NIR Spectral Data Management for Quality Control of Grape Bunches during On-Vine Ripening","volume":"11","year":"2011","journal-title":"Sensors"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"9804","DOI":"10.1021\/jf4021637","article-title":"Feasibility Study on the Use of Near-Infrared Hyperspectral Imaging for the Screening of Anthocyanins in Intact Grapes during Ripening","volume":"61","author":"Heredia","year":"2013","journal-title":"J. Agric. Food Chem."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1016\/j.foodchem.2013.12.030","article-title":"Determination of technological maturity of grapes and total phenolic compounds of grape skins in red and white cultivars during ripening by near infrared hyperspectral image: A preliminary approach","volume":"152","author":"Heredia","year":"2014","journal-title":"Food Chem."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Silva, R., Gomes, V., Mendes-Faia, A., and Melo-Pinto, P. (2018). Using support vector regression and hyperspectral imaging for the prediction of oenological parameters on different vintages and varieties ofwine grape berries. Remote Sens., 10.","DOI":"10.3390\/rs10020312"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1016\/j.foodchem.2014.09.119","article-title":"Predicting the anthocyanin content of wine grapes by NIR hyperspectral imaging","volume":"172","author":"Chen","year":"2015","journal-title":"Food Chem."},{"key":"ref_10","unstructured":"Cozzolino, D., Cynkar, W., Janik, L., Dambergs, R., Francis, L., and Gishen, M. (2004, January 24\u201329). Measurement of colour, total soluble solids and pH in whole red grapes using visible and near infrared spectroscopy. Proceedings of the 12th Australian Wine Industry Technical Conference, Melbourne, Australia."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.postharvbio.2018.12.010","article-title":"Development of predictive models for quality and maturation stage attributes of wine grapes using vis-nir reflectance spectroscopy","volume":"150","year":"2019","journal-title":"Postharvest Biol. Technol."},{"key":"ref_12","unstructured":"Fadock, M. (2011). Non-Destructive VIS-NIR Reflectance Spectrometry for Red Wine Grape Analysis, The University of Guelph."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"38","DOI":"10.5344\/ajev.2015.15035","article-title":"Visible-Near Infrared Reflectance Spectroscopy for Nondestructive Analysis of Red Wine Grapes","volume":"67","author":"Fadock","year":"2016","journal-title":"Am. J. Enol. Vitic."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1016\/j.jfoodeng.2011.02.018","article-title":"Determination of anthocyanin concentration in whole grape skins using hyperspectral imaging and adaptive boosting neural networks","volume":"105","author":"Fernandes","year":"2011","journal-title":"J. Food Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.compag.2015.05.013","article-title":"Brix, pH and anthocyanin content determination in whole Port wine grape berries by hyperspectral imaging and neural networks","volume":"115","author":"Fernandes","year":"2015","journal-title":"Comput. Electron. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1016\/j.lwt.2010.12.001","article-title":"Determination of phenolic compounds of grape skins during ripening by NIR spectroscopy","volume":"44","year":"2011","journal-title":"LWT Food Sci. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1016\/j.tifs.2007.06.001","article-title":"Hyperspectral imaging\u2014An emerging process analytical tool for food quality and safety control","volume":"18","author":"Gowen","year":"2007","journal-title":"Trends Food Sci. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1111\/j.1755-0238.2002.tb00209.x","article-title":"Optical remote sensing applications in viticulture\u2014A review","volume":"8","author":"Hall","year":"2002","journal-title":"Aust. J. Grape Wine Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.aca.2007.05.019","article-title":"The prediction of total anthocyanin concentration in red-grape homogenates using visible-near-infrared spectroscopy and artificial neural networks","volume":"594","author":"Janik","year":"2007","journal-title":"Anal. Chim. Acta"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.aca.2007.09.054","article-title":"Front face fluorescence spectroscopy and visible spectroscopy coupled with chemometrics have the potential to characterise ripening of Cabernet Franc grapes","volume":"621","author":"Dufour","year":"2008","journal-title":"Anal. Chim. Acta"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Gomes, V., Fernandes, A., Faia, A., and Melo-Pinto, P. (2014, January 9\u201312). Determination of sugar content in whole Port Wine grape berries combining hyperspectral imaging with neural networks methodologies. Proceedings of the Computational Intelligence for Engineering Solutions (CIES), 2014 IEEE Symposium, Orlando, FL, USA.","DOI":"10.1109\/CIES.2014.7011850"},{"key":"ref_22","unstructured":"Gomes, V., Fernandes, A., Faia, A., and Pinto, P.M. (2015, January 17\u201318). A Comparison of Neural Networks and Partial Least Squares for Estimation of Sugar Content in Wine Grape Berries Using Hyperspectral Imaging. Proceedings of the International Conference on Computer Science and Environmental Engineering (Csee 2015), Beijing, China."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.isprsjprs.2020.12.010","article-title":"Review on Convolutional Neural Networks (CNN) in vegetation remote sensing","volume":"173","author":"Kattenborn","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Guidici, D., and Clark, M.L. (2017). One-Dimensional Convolutional Neural Network Land-Cover Classification of Multi-Seasonal Hyperspectral Imagery in the San Francisco Bay Area, California. Remote Sens., 9.","DOI":"10.3390\/rs9060629"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Xie, B., Zhang, H.K., and Xue, J. (2019). Deep Convolutional Neural Network for Mapping Smallholder Agriculture Using High Spatial Resolution Satellite Image. Sensors, 19.","DOI":"10.3390\/s19102398"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liu, X., Han, F., Ghazali, K.H., Mohamed, I.I., and Zhao, Y. (2019). A review of convolutional neural networks in remote sensing image. Proceedings of the 8th International Conference on Software and Computer Applications, Association for Computing Machinery.","DOI":"10.1145\/3316615.3316712"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Albawi, S., Mohammed, T.A., and Al-Zawi, S. (2017, January 21\u201323). Understanding of a convolutional neural network. Proceedings of the 2017 International Conference on Engineering and Technology, ICET 2017, Antalya, Turkey.","DOI":"10.1109\/ICEngTechnol.2017.8308186"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.aca.2016.12.010","article-title":"Convolutional neural networks for vibrational spectroscopic data analysis","volume":"954","author":"Acquarelli","year":"2017","journal-title":"Anal. Chim. Acta"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4067","DOI":"10.1039\/C7AN01371J","article-title":"Deep convolutional neural networks for Raman spectrum recognition: A unified solution","volume":"142","author":"Liu","year":"2017","journal-title":"Analyst"},{"key":"ref_30","unstructured":"Zhang, X., Xu, J., Lin, T., and Ying, Y. (2018). Convolutional neural network based classification analysis for near infrared spectroscopic sensing. Proceedings of the 2018 ASABE Annual International Meeting, American Society of Agricultural and Biological Engineers."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Fernandes, A.M., Utkin, A.B., Eiras-Dias, J., Cunha, J., Silvestre, J., and Melo-Pinto, P. (2019). Grapevine variety identification using \u201cBig Data\u201d collected with miniaturized spectrometer combined with support vector machines and convolutional neural networks. Comput. Electron. Agric., 163.","DOI":"10.1016\/j.compag.2019.104855"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"103550","DOI":"10.1016\/j.infrared.2020.103550","article-title":"Application of near-infrared hyperspectral imaging for variety identification of coated maize kernels with deep learning","volume":"111","author":"Zhang","year":"2020","journal-title":"Infrared Phys. Technol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.chemolab.2018.07.008","article-title":"Modern practical convolutional neural networks for multivariate regression: Applications to NIR calibration","volume":"182","author":"Cui","year":"2018","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Padarian, J., Minasny, B., and McBratney, A.B. (2019). Using deep learning to predict soil properties from regional spectral data. Geoderma Reg., 16.","DOI":"10.1016\/j.geodrs.2018.e00198"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhao, X., Guo, X., and Guo, J. (2019). Deep Learning Application for Predicting Soil Organic Matter Content by VIS-NIR Spectroscopy. Comput. Intell. Neurosci., 2019.","DOI":"10.1155\/2019\/3563761"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e2977","DOI":"10.1002\/cem.2977","article-title":"One-dimensional convolutional neural networks for spectroscopic signal regression","volume":"32","author":"Malek","year":"2018","journal-title":"J. Chemom."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.geoderma.2019.06.016","article-title":"Convolutional neural network for simultaneous prediction of several soil properties using visible\/near-infrared, mid-infrared, and their combined spectra","volume":"352","author":"Ng","year":"2019","journal-title":"Geoderma"},{"key":"ref_38","unstructured":"Bjerrum, E.J., Glahder, M., and Skov, T. (2017). Data augmentation of spectral data for convolutional neural network (CNN) based deep chemometrics. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Pang, L., Men, S., Yan, L., and Xiao, J. (2020). Rapid Vitality Estimation and Prediction of Corn Seeds Based on Spectra and Images Using Deep Learning and Hyperspectral Imaging Techniques. IEEE Access, 8.","DOI":"10.1109\/ACCESS.2020.3006495"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1016\/j.tplants.2018.07.004","article-title":"Deep Learning for Plant Stress Phenotyping: Trends and Future Perspectives","volume":"23","author":"Singh","year":"2018","journal-title":"Trends Plant Sci."},{"key":"ref_41","unstructured":"International Organisation of Vine and Wine (2006). Organisation International de la Vigne e du Vin Recueil des M\u00e9thodes Internationales D\u2019analyse des Vins et des Mouts, OIV."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Maldonado, A.I.L., Rodriguez-Fuentes, H., and Contreras, J.A.V. (2018). Hyperspectral Imaging in Agriculture, Food and Environment, IntechOpen.","DOI":"10.5772\/intechopen.70213"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1016\/j.trac.2009.07.007","article-title":"Review of the most common pre-processing techniques for near-infrared spectra","volume":"28","author":"Rinnan","year":"2009","journal-title":"TrAC Trends Anal. Chem."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1140\/epjti\/s40485-015-0018-6","article-title":"Review of multidimensional data processing approaches for Raman and infrared spectroscopy","volume":"2","author":"Gautam","year":"2015","journal-title":"EPJ Tech. Instrum."},{"key":"ref_45","unstructured":"Brown, S.D., Tauler, R., and Walczak, B. (2009). Preprocessing Methods. Comprehensive Chemometrics: Chemical and Biochemical Data Analysis, Elsevier."},{"key":"ref_46","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning. PMLR, Lille, France."},{"key":"ref_47","unstructured":"Glorot, X., and Bengio, Y. (2010, January 13\u201315). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, Sardinia, Italy."},{"key":"ref_48","unstructured":"Zeiler, M.D. (2012). ADADELTA: An Adaptive Learning Rate Method. arXiv."},{"key":"ref_49","first-page":"26","article-title":"Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimizationb","volume":"17","author":"Wu","year":"2019","journal-title":"J. Electron. Sci. Technol."},{"key":"ref_50","unstructured":"Snoek, J., Larochelle, H., and Adams, R.P. (2012, January 3\u20136). Practical Bayesian optimization of machine learning algorithms. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Victoria, A.H., and Maragatham, G. (2020). Automatic tuning of hyperparameters using Bayesian optimization. Evol. Syst.","DOI":"10.1007\/s12530-020-09345-2"},{"key":"ref_52","unstructured":"Murugan, P. (2017). Hyperparameters Optimization in Deep Convolutional Neural Network\/Bayesian Approach with Gaussian Process Prior. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"104249","DOI":"10.1016\/j.catena.2019.104249","article-title":"Application of convolutional neural networks featuring Bayesian optimization for landslide susceptibility assessment","volume":"186","author":"Sameen","year":"2020","journal-title":"CATENA"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"52588","DOI":"10.1109\/ACCESS.2020.2981072","article-title":"Basic Enhancement Strategies When Using Bayesian Optimization for Hyperparameter Tuning of Deep Neural Networks","volume":"8","author":"Cho","year":"2020","journal-title":"IEEE Access"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Shi, D., Ye, Y., Gillwald, M., and Hecht, M. (2020). Designing a lightweight 1D convolutional neural network with Bayesian optimization for wheel flat detection using carbody accelerations. Int. J. Rail Transp., 1\u201331.","DOI":"10.1080\/23248378.2020.1795942"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/10\/3459\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:02:07Z","timestamp":1760162527000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/10\/3459"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,15]]},"references-count":55,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["s21103459"],"URL":"https:\/\/doi.org\/10.3390\/s21103459","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,15]]}}}