Evaluating the Effect of Thermal Treatment on Phenolic Compounds in Functional Flours Using Vis–NIR–SWIR Spectroscopy: A Machine Learning Approach
Functional flours, high in bioactive compounds, have garnered increasing attention, driven by consumer demand for alternative ingredients and the nutritional limitations of wheat flour. This study explores the thermal stability of phenolic compounds in various functional flours using visible, near a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Foods |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-8158/14/15/2663 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849770878582128640 |
|---|---|
| author | Achilleas Panagiotis Zalidis Nikolaos Tsakiridis George Zalidis Ioannis Mourtzinos Konstantinos Gkatzionis |
| author_facet | Achilleas Panagiotis Zalidis Nikolaos Tsakiridis George Zalidis Ioannis Mourtzinos Konstantinos Gkatzionis |
| author_sort | Achilleas Panagiotis Zalidis |
| collection | DOAJ |
| description | Functional flours, high in bioactive compounds, have garnered increasing attention, driven by consumer demand for alternative ingredients and the nutritional limitations of wheat flour. This study explores the thermal stability of phenolic compounds in various functional flours using visible, near and shortwave-infrared (Vis–NIR–SWIR) spectroscopy (350–2500 nm), integrated with machine learning (ML) algorithms. Random Forest models were employed to classify samples based on flour type, baking temperature, and phenolic concentration. The full spectral range yielded high classification accuracy (0.98, 0.98, and 0.99, respectively), and an explainability framework revealed the wavelengths most relevant for each class. To address concerns regarding color as a confounding factor, a targeted spectral refinement was implemented by sequentially excluding the visible region. Models trained on the 1000–2500 nm and 1400–2500 nm ranges showed minor reductions in accuracy, suggesting that classification is not solely driven by visible characteristics. Results indicated that legume and wheat flours retain higher total phenolic content (TPC) under mild thermal conditions, whereas grape seed flour (GSF) and olive stone flour (OSF) exhibited notable thermal stability of TPC even at elevated temperatures. These first findings suggest that the proposed non-destructive spectroscopic approach enables rapid classification and quality assessment of functional flours, supporting future applications in precision food formulation and quality control. |
| format | Article |
| id | doaj-art-df075d7d7b1743e1ba50d35e3379f89b |
| institution | DOAJ |
| issn | 2304-8158 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj-art-df075d7d7b1743e1ba50d35e3379f89b2025-08-20T03:02:49ZengMDPI AGFoods2304-81582025-07-011415266310.3390/foods14152663Evaluating the Effect of Thermal Treatment on Phenolic Compounds in Functional Flours Using Vis–NIR–SWIR Spectroscopy: A Machine Learning ApproachAchilleas Panagiotis Zalidis0Nikolaos Tsakiridis1George Zalidis2Ioannis Mourtzinos3Konstantinos Gkatzionis4Laboratory of Consumer and Sensory Perception of Food & Drinks, Department of Food Science and Nutrition, University of the Aegean, Metropolite Ioakeim 2, 81400 Myrina, GreeceLaboratory of Remote Sensing, Spectroscopy and Geographic Information Systems (GIS), School of Agriculture, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceLaboratory of Remote Sensing, Spectroscopy and Geographic Information Systems (GIS), School of Agriculture, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceLaboratory of Food Chemistry and Biochemistry, Department of Food Science and Technology, School of Agriculture, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceLaboratory of Consumer and Sensory Perception of Food & Drinks, Department of Food Science and Nutrition, University of the Aegean, Metropolite Ioakeim 2, 81400 Myrina, GreeceFunctional flours, high in bioactive compounds, have garnered increasing attention, driven by consumer demand for alternative ingredients and the nutritional limitations of wheat flour. This study explores the thermal stability of phenolic compounds in various functional flours using visible, near and shortwave-infrared (Vis–NIR–SWIR) spectroscopy (350–2500 nm), integrated with machine learning (ML) algorithms. Random Forest models were employed to classify samples based on flour type, baking temperature, and phenolic concentration. The full spectral range yielded high classification accuracy (0.98, 0.98, and 0.99, respectively), and an explainability framework revealed the wavelengths most relevant for each class. To address concerns regarding color as a confounding factor, a targeted spectral refinement was implemented by sequentially excluding the visible region. Models trained on the 1000–2500 nm and 1400–2500 nm ranges showed minor reductions in accuracy, suggesting that classification is not solely driven by visible characteristics. Results indicated that legume and wheat flours retain higher total phenolic content (TPC) under mild thermal conditions, whereas grape seed flour (GSF) and olive stone flour (OSF) exhibited notable thermal stability of TPC even at elevated temperatures. These first findings suggest that the proposed non-destructive spectroscopic approach enables rapid classification and quality assessment of functional flours, supporting future applications in precision food formulation and quality control.https://www.mdpi.com/2304-8158/14/15/2663near infrared spectroscopystability of phenolicsthermal treatmentfunctional floursolive-by-productspulse flours |
| spellingShingle | Achilleas Panagiotis Zalidis Nikolaos Tsakiridis George Zalidis Ioannis Mourtzinos Konstantinos Gkatzionis Evaluating the Effect of Thermal Treatment on Phenolic Compounds in Functional Flours Using Vis–NIR–SWIR Spectroscopy: A Machine Learning Approach Foods near infrared spectroscopy stability of phenolics thermal treatment functional flours olive-by-products pulse flours |
| title | Evaluating the Effect of Thermal Treatment on Phenolic Compounds in Functional Flours Using Vis–NIR–SWIR Spectroscopy: A Machine Learning Approach |
| title_full | Evaluating the Effect of Thermal Treatment on Phenolic Compounds in Functional Flours Using Vis–NIR–SWIR Spectroscopy: A Machine Learning Approach |
| title_fullStr | Evaluating the Effect of Thermal Treatment on Phenolic Compounds in Functional Flours Using Vis–NIR–SWIR Spectroscopy: A Machine Learning Approach |
| title_full_unstemmed | Evaluating the Effect of Thermal Treatment on Phenolic Compounds in Functional Flours Using Vis–NIR–SWIR Spectroscopy: A Machine Learning Approach |
| title_short | Evaluating the Effect of Thermal Treatment on Phenolic Compounds in Functional Flours Using Vis–NIR–SWIR Spectroscopy: A Machine Learning Approach |
| title_sort | evaluating the effect of thermal treatment on phenolic compounds in functional flours using vis nir swir spectroscopy a machine learning approach |
| topic | near infrared spectroscopy stability of phenolics thermal treatment functional flours olive-by-products pulse flours |
| url | https://www.mdpi.com/2304-8158/14/15/2663 |
| work_keys_str_mv | AT achilleaspanagiotiszalidis evaluatingtheeffectofthermaltreatmentonphenoliccompoundsinfunctionalfloursusingvisnirswirspectroscopyamachinelearningapproach AT nikolaostsakiridis evaluatingtheeffectofthermaltreatmentonphenoliccompoundsinfunctionalfloursusingvisnirswirspectroscopyamachinelearningapproach AT georgezalidis evaluatingtheeffectofthermaltreatmentonphenoliccompoundsinfunctionalfloursusingvisnirswirspectroscopyamachinelearningapproach AT ioannismourtzinos evaluatingtheeffectofthermaltreatmentonphenoliccompoundsinfunctionalfloursusingvisnirswirspectroscopyamachinelearningapproach AT konstantinosgkatzionis evaluatingtheeffectofthermaltreatmentonphenoliccompoundsinfunctionalfloursusingvisnirswirspectroscopyamachinelearningapproach |