Estimation of Sugar Content in Wine Grapes via In Situ VNIR–SWIR Point Spectroscopy Using Explainable Artificial Intelligence Techniques
Spectroscopy is a widely used technique that can contribute to food quality assessment in a simple and inexpensive way. Especially in grape production, the visible and near infrared (VNIR) and the short-wave infrared (SWIR) regions are of great interest, and they may be utilized for both fruit monit...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/3/1065 |
| _version_ | 1797623322341539840 |
|---|---|
| author | Eleni Kalopesa Konstantinos Karyotis Nikolaos Tziolas Nikolaos Tsakiridis Nikiforos Samarinas George Zalidis |
| author_facet | Eleni Kalopesa Konstantinos Karyotis Nikolaos Tziolas Nikolaos Tsakiridis Nikiforos Samarinas George Zalidis |
| author_sort | Eleni Kalopesa |
| collection | DOAJ |
| description | Spectroscopy is a widely used technique that can contribute to food quality assessment in a simple and inexpensive way. Especially in grape production, the visible and near infrared (VNIR) and the short-wave infrared (SWIR) regions are of great interest, and they may be utilized for both fruit monitoring and quality control at all stages of maturity. The aim of this work was the quantitative estimation of the wine grape ripeness, for four different grape varieties, by using a highly accurate contact probe spectrometer that covers the entire VNIR–SWIR spectrum (350–2500 nm). The four varieties under examination were Chardonnay, Malagouzia, Sauvignon-Blanc, and Syrah and all the samples were collected over the 2020 and 2021 harvest and pre-harvest phenological stages (corresponding to stages 81 through 89 of the BBCH scale) from the vineyard of Ktima Gerovassiliou located in Northern Greece. All measurements were performed in situ and a refractometer was used to measure the total soluble solids content (°Brix) of the grapes, providing the ground truth data. After the development of the grape spectra library, four different machine learning algorithms, namely Partial Least Squares regression (PLS), Random Forest regression, Support Vector Regression (SVR), and Convolutional Neural Networks (CNN), coupled with several pre-treatment methods were applied for the prediction of the °Brix content from the VNIR–SWIR hyperspectral data. The performance of the different models was evaluated using a cross-validation strategy with three metrics, namely the coefficient of the determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>), the root mean square error (RMSE), and the ratio of performance to interquartile distance (RPIQ). High accuracy was achieved for Malagouzia, Sauvignon-Blanc, and Syrah from the best models developed using the CNN learning algorithm (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>R</mi><mn>2</mn></msup><mo>></mo><mn>0.8</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>RPIQ</mi><mo>≥</mo><mn>4</mn></mrow></semantics></math></inline-formula>), while a good fit was attained for the Chardonnay variety from SVR (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>R</mi><mn>2</mn></msup><mo>=</mo><mn>0.63</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>RMSE</mi><mo>=</mo><mn>2.10</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>RPIQ</mi><mo>=</mo><mn>2.24</mn></mrow></semantics></math></inline-formula>), proving that by using a portable spectrometer the in situ estimation of the wine grape maturity could be provided. The proposed methodology could be a valuable tool for wine producers making real-time decisions on harvest time and with a non-destructive way. |
| first_indexed | 2024-03-11T09:27:08Z |
| format | Article |
| id | doaj.art-4e82c8ab3e474b9b80c289e7f317f00d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T09:27:08Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4e82c8ab3e474b9b80c289e7f317f00d2023-11-16T17:55:38ZengMDPI AGSensors1424-82202023-01-01233106510.3390/s23031065Estimation of Sugar Content in Wine Grapes via In Situ VNIR–SWIR Point Spectroscopy Using Explainable Artificial Intelligence TechniquesEleni Kalopesa0Konstantinos Karyotis1Nikolaos Tziolas2Nikolaos Tsakiridis3Nikiforos Samarinas4George Zalidis5Laboratory of Remote Sensing, Spectroscopy, and GIS, School of Agriculture, Aristotle University of Thessaloniki, 57001 Thermi, GreeceLaboratory of Remote Sensing, Spectroscopy, and GIS, School of Agriculture, Aristotle University of Thessaloniki, 57001 Thermi, GreeceLaboratory of Remote Sensing, Spectroscopy, and GIS, School of Agriculture, Aristotle University of Thessaloniki, 57001 Thermi, GreeceLaboratory of Remote Sensing, Spectroscopy, and GIS, School of Agriculture, Aristotle University of Thessaloniki, 57001 Thermi, GreeceLaboratory of Remote Sensing, Spectroscopy, and GIS, School of Agriculture, Aristotle University of Thessaloniki, 57001 Thermi, GreeceLaboratory of Remote Sensing, Spectroscopy, and GIS, School of Agriculture, Aristotle University of Thessaloniki, 57001 Thermi, GreeceSpectroscopy is a widely used technique that can contribute to food quality assessment in a simple and inexpensive way. Especially in grape production, the visible and near infrared (VNIR) and the short-wave infrared (SWIR) regions are of great interest, and they may be utilized for both fruit monitoring and quality control at all stages of maturity. The aim of this work was the quantitative estimation of the wine grape ripeness, for four different grape varieties, by using a highly accurate contact probe spectrometer that covers the entire VNIR–SWIR spectrum (350–2500 nm). The four varieties under examination were Chardonnay, Malagouzia, Sauvignon-Blanc, and Syrah and all the samples were collected over the 2020 and 2021 harvest and pre-harvest phenological stages (corresponding to stages 81 through 89 of the BBCH scale) from the vineyard of Ktima Gerovassiliou located in Northern Greece. All measurements were performed in situ and a refractometer was used to measure the total soluble solids content (°Brix) of the grapes, providing the ground truth data. After the development of the grape spectra library, four different machine learning algorithms, namely Partial Least Squares regression (PLS), Random Forest regression, Support Vector Regression (SVR), and Convolutional Neural Networks (CNN), coupled with several pre-treatment methods were applied for the prediction of the °Brix content from the VNIR–SWIR hyperspectral data. The performance of the different models was evaluated using a cross-validation strategy with three metrics, namely the coefficient of the determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>), the root mean square error (RMSE), and the ratio of performance to interquartile distance (RPIQ). High accuracy was achieved for Malagouzia, Sauvignon-Blanc, and Syrah from the best models developed using the CNN learning algorithm (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>R</mi><mn>2</mn></msup><mo>></mo><mn>0.8</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>RPIQ</mi><mo>≥</mo><mn>4</mn></mrow></semantics></math></inline-formula>), while a good fit was attained for the Chardonnay variety from SVR (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>R</mi><mn>2</mn></msup><mo>=</mo><mn>0.63</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>RMSE</mi><mo>=</mo><mn>2.10</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>RPIQ</mi><mo>=</mo><mn>2.24</mn></mrow></semantics></math></inline-formula>), proving that by using a portable spectrometer the in situ estimation of the wine grape maturity could be provided. The proposed methodology could be a valuable tool for wine producers making real-time decisions on harvest time and with a non-destructive way.https://www.mdpi.com/1424-8220/23/3/1065TSSvis–NIRNIR spectroscopycultivarvineyarddeep learning |
| spellingShingle | Eleni Kalopesa Konstantinos Karyotis Nikolaos Tziolas Nikolaos Tsakiridis Nikiforos Samarinas George Zalidis Estimation of Sugar Content in Wine Grapes via In Situ VNIR–SWIR Point Spectroscopy Using Explainable Artificial Intelligence Techniques Sensors TSS vis–NIR NIR spectroscopy cultivar vineyard deep learning |
| title | Estimation of Sugar Content in Wine Grapes via In Situ VNIR–SWIR Point Spectroscopy Using Explainable Artificial Intelligence Techniques |
| title_full | Estimation of Sugar Content in Wine Grapes via In Situ VNIR–SWIR Point Spectroscopy Using Explainable Artificial Intelligence Techniques |
| title_fullStr | Estimation of Sugar Content in Wine Grapes via In Situ VNIR–SWIR Point Spectroscopy Using Explainable Artificial Intelligence Techniques |
| title_full_unstemmed | Estimation of Sugar Content in Wine Grapes via In Situ VNIR–SWIR Point Spectroscopy Using Explainable Artificial Intelligence Techniques |
| title_short | Estimation of Sugar Content in Wine Grapes via In Situ VNIR–SWIR Point Spectroscopy Using Explainable Artificial Intelligence Techniques |
| title_sort | estimation of sugar content in wine grapes via in situ vnir swir point spectroscopy using explainable artificial intelligence techniques |
| topic | TSS vis–NIR NIR spectroscopy cultivar vineyard deep learning |
| url | https://www.mdpi.com/1424-8220/23/3/1065 |
| work_keys_str_mv | AT elenikalopesa estimationofsugarcontentinwinegrapesviainsituvnirswirpointspectroscopyusingexplainableartificialintelligencetechniques AT konstantinoskaryotis estimationofsugarcontentinwinegrapesviainsituvnirswirpointspectroscopyusingexplainableartificialintelligencetechniques AT nikolaostziolas estimationofsugarcontentinwinegrapesviainsituvnirswirpointspectroscopyusingexplainableartificialintelligencetechniques AT nikolaostsakiridis estimationofsugarcontentinwinegrapesviainsituvnirswirpointspectroscopyusingexplainableartificialintelligencetechniques AT nikiforossamarinas estimationofsugarcontentinwinegrapesviainsituvnirswirpointspectroscopyusingexplainableartificialintelligencetechniques AT georgezalidis estimationofsugarcontentinwinegrapesviainsituvnirswirpointspectroscopyusingexplainableartificialintelligencetechniques |