Aristotle University Of Thessaloniki (AUTH)
Olive trees stress detection using remote sensing, spectroscopy and machine learning
Abstract
dc:descriptionOlive is an essential crop for Greece constituting a major economic and agricultural factor. Diseases, pests, and environmental conditions are all factors that can deteriorate the health status of olive crops by causing plant stress. Researchers can utilize remote sensing to assist their actions in detecting both the stress itself and its sources, and act accordingly. This thesis presents an approach for detecting stress in two scales, olive fields and olive trees, by employing Sentinel-2 and UAV based remote sensing. The acquired multispectral and hyperspectral data collected were analysed utilising Machine Learning algorithms to produce classification models. For the first part, Sentinel-2 data were used to create vegetation indices for commercial olive fields in Halkidiki, Northern Greece. Twelve machine learning algorithms were tested to determine which type would be the most efficient to detect plant stress in olive trees. In parallel, a test was conducted using 26 stress incidence thresholds to determine how setting different thresholds for stress incidence affects model performance, and which threshold constitutes the best choice for more accurate classification. The results show that among all tested classification algorithms, the quadratic discriminant analysis provided the highest AUROC performance of 0.99. The stress incidence threshold used in the current case to generate the best-performing model was 6%, but the results suggest that setting customized thresholds relevant to specific cases would provide optimal results. The best-performing model was used in a one-vs-rest multiclass classification task to determine the source of the stress between four possible classes: “healthy”, “soil/wood pathogens”, “foliar pathogens”, and “unidentified source”. The multiclass model was more accurate in detection of the “healthy” class (0.99); the “soil/wood pathogens” and “unidentified source” classes were less accurate (0.76); and “foliar pathogens” had the lowest score (0.72). For the second part, two machine learning algorithms, Random Forest (RF) and XGBoost (XGB) were evaluated, in conjunction with the feature selection methods Recursive Feature Elimination (RFE) and Mutual Information (MI), for detecting stress in olive trees using hyperspectral data. The research focused on identifying early stress onset caused by biotic and abiotic factors through the analysis of hyperspectral images. Both the RF and XGB algorithms demonstrated high efficacy in stress detection, achieving AUROC scores of 0.977 and 0.955, respectively. The experiment also highlighted the effectiveness of RFE and MI in optimizing the classification process, with RF and XGB requiring a reduced number of hyperspectral features for an optimal performance of 1.00 on both occasions. Key wavelengths indicative of stress were identified in the visible to near-infrared spectrum, suggesting their strong correlation with olive tree stress. Findings contribute to precision agriculture by demonstrating the viability of using machine learning for stress detection in olive trees, as well as the impact of selecting stress incidence thresholds and underscore the importance of feature selection in improving classifier performance. Insights from this research can be used by experts as a service to enhance their decision-making and support the application of efficient strategies in the field of precision crop protection.
Degree
thesis:*- Grantor dc:publisher
- Aristotle University Of Thessaloniki (AUTH)
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Navrozidis, Ioannis
- Ναβροζίδης, Ιωάννης
Subjects
dc:subject × 27- Ανίχνευση φυτικής καταπόνησης
- Τηλεπισκόπηση
- Sentinel-2
- Υπερφασματικά δεδομένα
- Μηχανική μάθηση
- Επιλογή μεταβλητών
- Βελτιστοποίηση υπερπαραμέτρων
- Φασματοσκοπία
- Plant stress detection
- Remote sensing
- Hyperspectral data
- Machine learning
- Feature selection
- Hyperparameter optimization
- Spectroscopy
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Φυσικές Επιστήμες
- Τεχνητή νοημοσύνη
- Γεωπονία, Δασολογία και Αλιεία
- Γεωπονικές Επιστήμες και Κτηνιατρική
- Γεωπονία, διεπιστημονική προσέγγιση
- Computer and Information Sciences
- Natural Sciences
- Artificial Intelligence
- Agriculture, Forestry and Fisheries
- Agricultural and Veterinary Sciences
- Agriculture, interdisciplinary
Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/62281