Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines
Assessing vines’ vigour is essential for vineyard management and automatization of viticulture machines, including shaking adjustments of berry harvesters during grape harvest or leaf pruning applications. To address these problems, based on a standardized growth class assessment, labeled ground tru...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/431 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587536005857280 |
|---|---|
| author | Ronald P. Dillner Maria A. Wimmer Matthias Porten Thomas Udelhoven Rebecca Retzlaff |
| author_facet | Ronald P. Dillner Maria A. Wimmer Matthias Porten Thomas Udelhoven Rebecca Retzlaff |
| author_sort | Ronald P. Dillner |
| collection | DOAJ |
| description | Assessing vines’ vigour is essential for vineyard management and automatization of viticulture machines, including shaking adjustments of berry harvesters during grape harvest or leaf pruning applications. To address these problems, based on a standardized growth class assessment, labeled ground truth data of precisely located grapevines were predicted with specifically selected Machine Learning (ML) classifiers (Random Forest Classifier (RFC), Support Vector Machines (SVM)), utilizing multispectral UAV (Unmanned Aerial Vehicle) sensor data. The input features for ML model training comprise spectral, structural, and texture feature types generated from multispectral orthomosaics (spectral features), Digital Terrain and Surface Models (DTM/DSM- structural features), and Gray-Level Co-occurrence Matrix (GLCM) calculations (texture features). The specific features were selected based on extensive literature research, including especially the fields of precision agri- and viticulture. To integrate only vine canopy-exclusive features into ML classifications, different feature types were extracted and spatially aggregated (zonal statistics), based on a combined pixel- and object-based image-segmentation-technique-created vine row mask around each single grapevine position. The extracted canopy features were progressively grouped into seven input feature groups for model training. Model overall performance metrics were optimized with grid search-based hyperparameter tuning and repeated-k-fold-cross-validation. Finally, ML-based growth class prediction results were extensively discussed and evaluated for overall (accuracy, f1-weighted) and growth class specific- classification metrics (accuracy, user- and producer accuracy). |
| format | Article |
| id | doaj-art-ed318eefd7494df6b6b7ceecba0f973d |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-ed318eefd7494df6b6b7ceecba0f973d2025-01-24T13:48:54ZengMDPI AGSensors1424-82202025-01-0125243110.3390/s25020431Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of GrapevinesRonald P. Dillner0Maria A. Wimmer1Matthias Porten2Thomas Udelhoven3Rebecca Retzlaff4Department of Viticulture and Oenology, DLR (Dienstleistungszentrum Ländlicher Raum) Mosel/Steillagenzentrum, Gartenstraße 18, 54470 Bernkastel-Kues, GermanyDepartment of Computer Science, University of Koblenz, Universitätsstraße 1, 56070 Koblenz, GermanyDepartment of Viticulture and Oenology, DLR (Dienstleistungszentrum Ländlicher Raum) Mosel/Steillagenzentrum, Gartenstraße 18, 54470 Bernkastel-Kues, GermanyDepartment of Environmental Remote Sensing and Geoinformatics, Trier University, Universitätsring 15, 54296 Trier, GermanyDepartment of Environmental Remote Sensing and Geoinformatics, Trier University, Universitätsring 15, 54296 Trier, GermanyAssessing vines’ vigour is essential for vineyard management and automatization of viticulture machines, including shaking adjustments of berry harvesters during grape harvest or leaf pruning applications. To address these problems, based on a standardized growth class assessment, labeled ground truth data of precisely located grapevines were predicted with specifically selected Machine Learning (ML) classifiers (Random Forest Classifier (RFC), Support Vector Machines (SVM)), utilizing multispectral UAV (Unmanned Aerial Vehicle) sensor data. The input features for ML model training comprise spectral, structural, and texture feature types generated from multispectral orthomosaics (spectral features), Digital Terrain and Surface Models (DTM/DSM- structural features), and Gray-Level Co-occurrence Matrix (GLCM) calculations (texture features). The specific features were selected based on extensive literature research, including especially the fields of precision agri- and viticulture. To integrate only vine canopy-exclusive features into ML classifications, different feature types were extracted and spatially aggregated (zonal statistics), based on a combined pixel- and object-based image-segmentation-technique-created vine row mask around each single grapevine position. The extracted canopy features were progressively grouped into seven input feature groups for model training. Model overall performance metrics were optimized with grid search-based hyperparameter tuning and repeated-k-fold-cross-validation. Finally, ML-based growth class prediction results were extensively discussed and evaluated for overall (accuracy, f1-weighted) and growth class specific- classification metrics (accuracy, user- and producer accuracy).https://www.mdpi.com/1424-8220/25/2/431precision viticulturevine vigourremote sensingUAV (Unmanned Aerial Vehicle)photogrammetrymultispectral imagery |
| spellingShingle | Ronald P. Dillner Maria A. Wimmer Matthias Porten Thomas Udelhoven Rebecca Retzlaff Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines Sensors precision viticulture vine vigour remote sensing UAV (Unmanned Aerial Vehicle) photogrammetry multispectral imagery |
| title | Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines |
| title_full | Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines |
| title_fullStr | Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines |
| title_full_unstemmed | Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines |
| title_short | Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines |
| title_sort | combining a standardized growth class assessment uav sensor data gis processing and machine learning classification to derive a correlation with the vigour and canopy volume of grapevines |
| topic | precision viticulture vine vigour remote sensing UAV (Unmanned Aerial Vehicle) photogrammetry multispectral imagery |
| url | https://www.mdpi.com/1424-8220/25/2/431 |
| work_keys_str_mv | AT ronaldpdillner combiningastandardizedgrowthclassassessmentuavsensordatagisprocessingandmachinelearningclassificationtoderiveacorrelationwiththevigourandcanopyvolumeofgrapevines AT mariaawimmer combiningastandardizedgrowthclassassessmentuavsensordatagisprocessingandmachinelearningclassificationtoderiveacorrelationwiththevigourandcanopyvolumeofgrapevines AT matthiasporten combiningastandardizedgrowthclassassessmentuavsensordatagisprocessingandmachinelearningclassificationtoderiveacorrelationwiththevigourandcanopyvolumeofgrapevines AT thomasudelhoven combiningastandardizedgrowthclassassessmentuavsensordatagisprocessingandmachinelearningclassificationtoderiveacorrelationwiththevigourandcanopyvolumeofgrapevines AT rebeccaretzlaff combiningastandardizedgrowthclassassessmentuavsensordatagisprocessingandmachinelearningclassificationtoderiveacorrelationwiththevigourandcanopyvolumeofgrapevines |