Mediterranean Agronomic Institute of Chania

Featured Application U-Net outperforms classical classifiers for mapping crop-nitrogen-water co-limitation on Unmanned Aerial Vehicle (UAV) multispectral imagery to guide fertilization and irrigation. Using a U-Net pre-trained with field data from known nitrogen and irrigation treatments, the model precisely delineates spatial patterns of crop nitrogen and water status, providing >70% accuracy for their interaction. This directly supports the grower's decision to fertilize and irrigate by identifying deficient or imbalanced areas and enabling site-specific management under subtle spatial variation. This study compared unsupervised and supervised machine learning, and deep learning (U-Net) classifiers on Unmanned Aerial Vehicle (UAV) multispectral imagery to identify nitrogen status in potato crops under nitrogen (N) fertilization treatments, irrigation (I), and their interaction (N & times; I). The U-Net model outperformed all other methods, achieving accuracies for crop nitrogen status of 65-99% in N, 84-100% in I, and 41-82% in N & times; I treatments, with variation due to different input data. Supervised machine learning also performed well, with Support Vector Machine achieving 53-87, 66-86, and 32-66% respectively, and Random Forest 61-96, 70-81, and 33-65%. Unsupervised K-means yielded the lowest accuracies (47-58, 9-65, and 8-34%), demonstrating necessity of substantial supervision to delineate crop nitrogen and water status. These findings were confirmed by repeated analyses of UAV imagery acquired later in the growing season with consistent results. Comparable classification performance was observed for crop water status and leaf area index at both time points. Despite being demonstrated in a single-field, single-crop framework, the results provide proof of concept for applying deep learning classifiers to detect subtle nitrogen and water stress under field conditions in precision agriculture. Future research could test diverse agroecosystems and growing seasons, alternative deep learning algorithms, and sensor data fusion to improve classification accuracies.

The cultivation of olive trees is concentrated in regions with a Mediterranean climate commonly characterized by drought and relatively high soil salinity. Scarce water supply, along with the accumulation of Sodium (Na+) ions in plant tissues, triggers various changes in plant mineral element concentrations. Three months of experimental treatments, consisting of deficient irrigation and saline water application on potted trees of three Greek Olea europaea L. cultivars (‘Lefkolia Serron’, ‘Amfissis’ and ‘Mastoidis’), led to statistically significant changes in Calcium (Ca), Copper (Cu), Iron (Fe), Manganese (Mn), Zinc (Zn), and Nitrogen (N) leaf concentrations. The correlation of hyperspectral leaf reflectance with Potassium (K) and Magnesium (Mg) appeared to be significant, which indicates a potential application for early and non-destructive detection of plant nutritional status. Additionally, customized Vegetation Indices, created as normalized ratios between wavelengths with the highest and lowest correlation with each element concentration, resulted in higher correlations than conventional, widely used indices (NDVI, WI, and PRI), a finding that emphasizes the importance of using individualized rather than generalized indices.

In this study, we designed a stacking ensemble machine learning method for accurate estimation of grass-clover biomass quality from high-resolution hyperspectral field data. Basic learners were support vector machine (SVM), K-Nearest Neighbor (KNN), random forest (RF), decision tree (DT), partial least square regress (PLS), shallow artificial- (ANN) and deep multi-layer perceptron (MLPs) neural networks. Three meta learners in the second layer were RF (stackingRF), eXtreme Gradient Boosting (stackingXGB), and CatBoost (stackingCat). We used 6 different datasets for the estimation, including the raw spectral reflectance, its 1st and 2nd derivatives, and their Standard Normal Variate (SNV). Quality indices were crude ash, crude protein, crude fat, crude fiber, neutral detergent fiber (NDF), acid detergent fiber (ADF), water-soluble carbohydrates (WSC), sugar, and fructans. The results showed that spectral feature selection by the PLS was useful in preprocessing. All machine learning methods predicted well quality from the raw reflectance, with PLS performing best (R2 = 0.64-0.87) for all indices except crude ash. The stacked ensemble learning benefited the predictions, especially with stackingRF and stackingCat as meta learners (R2 increased by 2-8 % compared with the average of the four best machine learning algorithms in the first layer). SNV generally performed better than the original reflectance across most datasets. In particular, SNV applied to the 2nd derivative, combined with either PLS or StackingRF, yielded the best predictions for carbohydrates (sugar, fructans, WSC) and fiber (crude fiber, NDF, ADF), achieving the highest R2 values (0.74-0.87) and the lowest nRMSE (5-15 %) among all pre-processing options. The red-edge region (700-780 nm) is the most important for all quality indices, except for ADF. This is among the first studies to systematically evaluate stacking ensemble learning, using the outputs of multiple machine-learning algorithms as inputs, for predicting biomass quality and supporting field management in complex grass-clover mixtures. PLS-based feature selection combined with stacking ensemble learning on second-derivative SNV spectra appears particularly promising and warrants testing at larger spatial and temporal scales.

Plant-derived glycoproteins and arabinogalactan proteins (AGPs) are increasingly recognized for their multifunctional bioactivity and relevance to food, health, and biotechnology. Present across botanically diverse species and environmental contexts, AGPs exhibit a wide range of physiological effects, including immunomodulatory, anti-inflammatory, antioxidant, antihyperglycemic, antiproliferative, and antiallergenic activities. This review offers a comprehensive overview of the therapeutic and nutritional potential of AGPs, emphasizing their structural diversity and emerging role as bioactive components in functional foods. Special focus is placed on their mechanisms of action and potential applications in nutraceuticals and biotechnological innovations. By summarizing current findings, the review highlights future research directions for exploiting AGPs as valuable yet underexplored, plant-derived ingredients in health-oriented food development.

In arid and semi-arid regions, the limited availability of surface water resources makes groundwater a critical source for domestic, agricultural, and industrial use. However, in Djibouti, unplanned and excessive exploitation of groundwater has led to aquifer depletion and seawater intrusion. Therefore, accurate and reliable prediction of groundwater potential represents an urgent need for sustainable water management. In this study, a comprehensive dataset comprising 14 hydrogeological, topographic, climatic, and remote sensing-based variables was developed to model groundwater potential. To predict groundwater potential, the Stochastic Gradient Boosting (SGB) algorithm was applied, while hyperparameter optimization was carried out using three different metaheuristic approaches, namely Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Gravitational Search Algorithm (GSA). Model performance was evaluated using accuracy, precision, recall, F1-score, and ROC/AUC metrics. Results demonstrated that the GSA-SGB model exhibited the most balanced performance on the test set, with 78.6