The scope of this research was to provide rice growers with optimal N-rate recommendations through precision agriculture applications. To achieve this goal, a prediction rice yield model was constructed, based on soil data, remote sensing data (optical and radar), climatic data, and farming practices. The dataset was collected from a rice crop surface of 89.2 ha cultivated continuously for a 5-year period and was analyzed with machine learning (ML) systems. A variational autoencoder (VAE) for reconstructing the input data of the prediction model was applied, resulting in MAE of 0.6 tn/ha, with an average yield for the study fields and period measured at 9.6 tn/ha. VAE learns the original input data representation and transforms them in a latent feature space, so that the anomalies and the discrepancies of the data are reduced. The reconstructed data by VAE provided a more sophisticated and detailed ML model, improving our knowledge about the various correlations between soil, N management parameters, and yield. Both optical and radar imagery and the climatic data were found to be of high importance for the model, as indicated by the application of XAI (explainable artificial intelligence) techniques. The new model was applied in the 2022 rice cultivation in the study fields, resulting in an average yield increase of 4.32% compared to the 5 previous years of experimentation.
This research is an outcome of the R&D activities of Ecodevelopment S.A. (steadily supported by the Hellenic Agricultural Organization—Demeter) towards offering precision farming services to rice growers. Within this framework, a new methodology for topdressing nitrogen prediction was developed based on machine learning. Nitrogen is a key element in rice culture and its rational management can increase productivity, reduce costs, and prevent environmental impacts. A multi-source, multi-temporal, and multi-scale dataset was collected, including optical and radar imagery, soil data, and yield maps by monitoring a 110 ha pilot rice farm in Thessaloniki Plain, Greece, for four consecutive years. RapidEye imagery underwent image segmentation to delineate management zones (ancillary, visual interpretation of unmanned aerial system scenes was employed, too); Sentinel-1 (SAR) imagery was modelled with Computer Vision to detect inundated fields and (through this) indicate the exact growth stage of the crop; and Sentinel-2 image data were used to map leaf nitrogen concentration (LNC) exactly before topdressing applications. Several machine learning algorithms were configured to predict yield for various nitrogen levels, with the XGBoost model resulting in the highest accuracy. Finally, yield curves were used to select the nitrogen dose maximizing yield, which was thus recommended to the grower. Inundation mapping proved to be critical in the prediction process. Currently, Ecodevelopment S.A. is expanding the application of the new method in different study areas, with a view to further empower its generality and operationality.
In 2022, Greece was the second most seriously affected European country in terms of the West Nile virus (WNV), after Italy. Specifically, Central Macedonia was the region with the most reported human cases (81.5%). In the present study, 30,816 female Culex pipiens sensu lato mosquitoes were collected from May to September 2022 in the seven regional units of Central Macedonia; they were then grouped into 690 pools and tested for WNV, while next-generation sequencing was applied to the samples, which showed a cycle threshold of Ct < 30 in a real-time RT-PCR test. WNV was detected in 5.9% of pools, with significant differences in the detection rate among regional units and months. It is of interest that in the Thessaloniki regional unit, where most of the human cases were observed, the virus circulation started earlier, peaked earlier, and lasted longer than in the other regional units. All sequences clustered into the Central European subclade of WNV lineage 2, and the virus strain differed from the initial Greek strain of 2010 by 0.52% and 0.27% at the nucleotide and amino acid levels, respectively. Signature substitutions were present, such as S73P and T157A in the prM and E structural proteins, respectively. The screening of mosquitoes provides useful information for virus circulation in a region with a potential for early warning, while the availability of whole-genome sequences is essential for further studies, including virus evolution.
The objective of this study was to develop a methodology for mapping olive plantations on a sub-tree scale. For this purpose, multispectral imagery of an almost 60-ha plantation in Greece was acquired with an Unmanned Aerial Vehicle. Objects smaller than the tree crown were produced with image segmentation. Three image features were indicated as optimum for discriminating olive trees from other objects in the plantation, in a rule-based classification algorithm. After limited manual corrections, the final output was validated by an overall accuracy of 93%. The overall processing chain can be considered as suitable for operational olive tree monitoring for potential stresses.
We investigated the prevalence and genetic diversity of Wolbachia pipientis strains in Aedes albopictus populations in Greece. Using a combination of PCR and Sanger sequencing techniques, we genotyped Wolbachia strains in 105 mosquitoes collected across eight different administrative regions in 2021. We found a high prevalence of Wolbachia in both male (90%) and female (97%) mosquitoes. Among the infected samples, 84% had double infections with both wAlbA and wAlbB strains, while 16% had infections with only wAlbB. Our comparison of the Multi-Locus Sequence Typing (MLST) profile, employing gatB–coxA–hcpA–ftsZ–fbpA genotyping, revealed a single MLST profile for each wAlbA and wAlbB strain in Greek populations. The same MLST profiles were also reported in populations from China, Russia, and Argentina, suggesting low levels of global diversity in wAlbA and wAlbB strains. Furthermore, our results indicated a significant association between temperature and the prevalence of single infections (p = 6.498 × 10−7), with higher temperatures correlating with an increased likelihood of single infections. Although male bias showed a tendency towards single infections, the effect was marginally non-significant (p = 0.053). These results were confirmed using a bootstrap-with-replacement analysis approach. Overall, our findings offer novel insights into the distribution and species diversity of Wolbachia strains in Greek Ae. albopictus populations, emphasizing the importance of understanding the short-term plastic and adaptive responses of these organisms to environmental stressors and rapid climate change.
Greece is one of the countries in Europe most affected by West Nile virus (WNV), and since 2010, when the virus caused a large outbreak with 197 human neuroinvasive cases, outbreaks occur almost every year. Mosquito surveillance is an indirect sign of virus circulation; therefore, the purpose of the study was the molecular detection of WNV in 45,988 C. pipiens s.l. mosquitoes collected during 2024 in four Regions of Greece and the genetic characterization of the virus strains. WNV was detected in 41 of 1316 (3.12%) Culex spp. mosquito pools. Next-generation sequencing was applied to the WNV-positive samples that had a high viral load. All WNV sequences belong to Cluster B of the sub-lineage Europe WNV-2A presenting a temporal clustering. The WNV infection rates varied highly across the Regions, regional units and months, being higher in Thessaly and Central Macedonia Regions, especially in July and September. All mosquito pools were also tested for Usutu virus (USUV), and one pool was found positive, with sequence clustering into the EU-2 lineage. A subset of mosquitoes (737 pools) was tested for additional viruses, and bunya-like viruses were detected in 6 pools with sequences clustering into four distinct subclades. The prompt detection of pathogenic viruses is helpful for the design of control measures, while the detection of insect-specific viruses provides insights into viral diversity and evolution.