Deliverables
D 1.1 Annual report
This deliverable presents the progress of the ARTs project during its first year of implementation. Activities focused on drone-based monitoring of rice fields, the creation of a weed image database, and field data collection to support the development of digital tools for weed detection and mapping. The results contribute to the advancement of precision agriculture approaches for improved and more sustainable weed management in rice cultivation.
D 1.2 Final report
This deliverable presents the final results of the ARTs project on weed monitoring and herbicide resistance in rice systems. The work evaluated herbicide responses of major rice weeds and developed machine learning and UAV-based approaches for weed identification and field monitoring. The outcomes support improved decision-making and sustainable weed management strategies in rice cultivation.
D 1.3 Project longenvity plan
The ARTs project establishes a framework to ensure that its digital tools and data infrastructure for weed monitoring and herbicide resistance management remain operational beyond the project lifetime. Key outputs include the ARTs digital platform and mobile application, AI-based weed detection algorithms, a geospatial resistance database, and predictive monitoring models developed for rice systems in Northern Greece. The longevity plan defines governance, funding pathways, and stakeholder engagement mechanisms to support the continued use and integration of these tools into agricultural advisory and monitoring systems
D 2.1 Baseline report of weed resistance in rice
Barnyardgrass (Echinochloa crus-galli) is one of the most competitive weeds in water-seeded rice systems and its control relies heavily on post-emergence herbicides. This study evaluated the herbicide sensitivity of five Echinochloa crus-galli biotypes collected from major rice-growing regions of Greece to three commonly used herbicides: cyhalofop-butyl, penoxsulam, and profoxydim under controlled greenhouse conditions. The results revealed significant variability in herbicide response among the examined biotypes, highlighting the importance of resistance monitoring and integrated weed management strategies in Greek rice production systems.
D 2.2 Herbicide resistance documentation from local seed samples
Herbicide resistance represents an increasing challenge for rice cultivation in Northern Greece. Within the ARTs project, populations of three major rice weeds—Echinochloa spp., weedy rice (Oryza sativa), and Cyperus difformis—were collected from rice fields in the Chalastra region and evaluated under greenhouse conditions for their response to commonly used herbicides. The results revealed substantial variability in herbicide sensitivity among populations, highlighting the importance of systematic monitoring and evidence-based approaches to support sustainable weed management in rice production systems.
D 2.3 Two final reports ready for publication in international journals with high impact factor on herbicide resistance documentation
The ARTs project developed two scientific studies addressing herbicide resistance and weed management challenges in Greek rice production systems. The first study combines greenhouse dose–response experiments with farmer questionnaires in the Chalastra region to evaluate herbicide responses of major rice weeds (Echinochloa spp., weedy rice, and Cyperus difformis) and to document farmer perceptions of weed pressure and herbicide efficacy. The second study provides a comprehensive literature-based assessment of herbicide-resistant weeds in Greek rice agroecosystems, synthesizing current knowledge on resistance mechanisms, agronomic drivers, and integrated weed management strategies
D 3.1 Digital weed databases for the 3 weed species
Within the ARTs project, a digital image database was developed to support automated weed detection and monitoring in rice cultivation. The database includes annotated images of the main rice weeds (Echinochloa spp. and Cyperus difformis) together with rice plants, collected under controlled greenhouse conditions across early growth stages and processed using machine learning classification methods. In addition, a farmer-generated database of georeferenced field images was created through the ARTs mobile application, enabling the documentation of weed infestation levels in commercial rice fields and supporting the development of decision-support tools for herbicide resistance monitoring.
D 3.2 A weed identification system using algorithms and Artificial Neural Networks (ANNs) fully operational and openly available to endusers
This deliverable presents the development and validation of a weed identification system based on machine learning algorithms and Artificial Neural Networks. The system combines a classical machine learning approach using Support Vector Machines with Random Forest classification on colour-derived features and a deep learning object detection model based on the YOLOv8 architecture. The models were trained and evaluated using a high-resolution RGB image dataset collected under controlled greenhouse conditions at the Benaki Phytopathological Institute, including the main weed species found in Greek rice systems (Echinochloa spp., Cyperus difformis, and weedy red rice), together with cultivated rice.
D 3.3 One final report ready for publication in international journals with high impact factor on weed identification and classification
This study evaluates two computer-vision approaches for early-stage weed identification in rice cultivation using a controlled greenhouse image dataset. High-resolution RGB images were collected from cultivated rice (Oryza sativa) and three major weed species (Echinochloa spp., Cyperus difformis, and weedy red rice) at early growth stages (BBCH 10–14), and manually annotated at the individual plant level. Classification performance was compared between a classical machine learning approach based on Support Vector Machines and Random Forest classification using HSV-derived colour features, and a deep learning object detection model based on the YOLOv8 architecture, highlighting differences in classification accuracy and misclassification patterns among morphologically similar species.
D 4.1 A report on using UAVs for weed sensing and mapping
This deliverable evaluates the use of UAV-based multispectral imagery for weed sensing and spatial variability assessment in rice fields. Multispectral data were collected during two consecutive growing seasons from experimental rice fields located in Chalastra, Thessaloniki, using a UAV equipped with a MicaSense RedEdge-MX multispectral camera. Vegetation indices derived from the imagery, specifically NDVI and NDRE, were analyzed in combination with RTK-GPS ground truth observations classified according to weed presence levels. The analysis showed that the performance of the vegetation indices in detecting weed-related variability was strongly influenced by crop phenology and canopy development, highlighting the importance of appropriate timing of image acquisition and the use of supporting field observations for reliable interpretation of UAV-derived weed maps.
D 5.1 A monitoring system for herbicide resistance
Within the ARTs project, a monitoring and early-warning framework for herbicide resistance in Greek rice systems was developed by integrating field observations, farmer-reported management practices, remote sensing indicators, and laboratory resistance confirmation data. The system combines georeferenced field sampling, standardized farmer questionnaires, UAV-based multispectral imagery, and resistance bioassays to detect and monitor resistant weed populations. Collected information is integrated into a centralized geospatial database where management practices, weed density, and resistance verification results are analyzed to generate resistance risk assessments and spatial monitoring outputs for rice production areas.
D 5.2 Report on mitigation strategies based on BMPs for herbicide resistance
Herbicide resistance has become a major challenge for the sustainability of rice production systems in Greece, where weed control has historically relied heavily on chemical herbicides. This report compiles and synthesizes available national and international evidence on herbicide-resistant weeds in Greek rice agroecosystems, focusing on species composition, resistance mechanisms, geographic distribution, and agronomic drivers of resistance evolution. Documented resistance cases primarily involve Echinochloa spp., Cyperus difformis, weedy rice (Oryza sativa f. spontanea), and more recently Leptochloa fusca ssp. fascicularis, with resistance reported mainly to ALS- and ACCase-inhibiting herbicides as well as other herbicide groups. Based on this assessment, the report presents Best Management Practices (BMPs) for herbicide resistance mitigation in Greek rice systems, integrating preventive, tactical, and long-term strategies across different stages of the rice production cycle.
D 6.1 A tool for prediction of resistance development
An image-based approach for assessing weed infestation severity in rice fields was developed using photographs submitted by farmers through the ARTs mobile application. During the 2025 growing season, more than 40 rice producers contributed field images, resulting in a curated dataset of 103 annotated samples classified into Low, Medium, and High infestation severity levels. Several YOLO-based image classification architectures (YOLOv8, YOLO11, and YOLO26) were trained and evaluated using multiple model scales and input image resolutions. The comparative analysis showed that a YOLOv8-based configuration achieved the most balanced performance, reaching a Top-1 classification accuracy of up to 77% while maintaining favourable inference speed and prediction stability. These results demonstrate the potential of farmer-generated imagery combined with artificial intelligence to support early assessment of weed infestation severity and contribute to future resistance monitoring tools within the ARTs system.
D 7.1 Dissemination and awarness raising
Dissemination and awareness activities of the ARTs project focused on increasing visibility of the project results and promoting knowledge exchange among farmers, agronomists, researchers, policy stakeholders, and the wider agricultural sector in Greece. Communication actions included the development of the project website, dissemination through professional networks such as LinkedIn, presentations at national and international scientific events, and direct engagement with stakeholders through workshops and field activities. A scientific workshop titled “Innovation & Technology in Rice Cultivation” held in Chalastra in March 2025 gathered farmers, researchers, and agricultural professionals to discuss digital weed mapping tools, UAV-based monitoring, and sustainable herbicide use. Additional dissemination activities included participation in scientific conferences, training workshops on weed identification, collaboration with international research partners, and media coverage highlighting the development of digital weed recognition tools. These actions contributed to strengthening stakeholder engagement, increasing awareness of herbicide resistance challenges, and promoting the adoption of digital tools for sustainable weed management in rice systems.
Publications
Conference Participation – XII Weeds Science Congress and symposium on herbicides and growth regulators
Date: 23-26 September 2024
Location: Belgrade, Serbia
Gerassimos G. Peteinatos
Computer vision and AI in weed detection: Current applications and future perspectives
Abstract
As the public’s concern for food security increases and stricter rules apply worldwide in order to restrict the use of herbicides in the agriculture-food chain, consumers are becoming less willing to accept chemical plant protection. A site-specific weed management technique involves applying a treatment to only the weed patches in order to achieve site-specific weed control. It is vital to identify plants and weeds when doing precision farming in order to spray herbicides on-site, robotically weed, and to control mechanical weeds with precision. There have been many different approaches to this problem over the last few years, but more work needs to be done to improve the speed, robustness, and accuracy of algorithms and recognition systems. Digital cameras and Artificial Neural Networks (ANNs) have rapidly developed in the past few years, providing new methods and tools also in agriculture and weed management. With computer vision and artificial intelligence (AI), weed detection methods have been significantly advanced. AI-powered cameras on tractors or drones can use image data to identify weeds and distinguish them from crops. Using deep learning algorithms trained on vast datasets of plant images, these systems are able to recognize different types of weed species at an early stage of their growth.
Autonomous robots, like Farming Revolution, Naïo Technologies, EcoRobotix, BlueRiver Technologies, etc, use cameras and AI algorithms to identify weeds and either mechanically remove them or apply targeted micro-doses of herbicide. These robots navigate fields independently, reducing labor and minimizing soil compaction. On the tractor implement side, there exist camera-guided hoeing systems that can distinguish between crops and weeds based on size, shape, and color. It is possible for these implements to adjust their tools in real time in order to get rid of weeds while leaving the crops untouched at the same time. Advanced systems combine detection with selective herbicide application, spraying only where weeds have been detected in order to provide spot spraying applications. Furthermore, interrow weed control as well as intrarow band spraying has also been developed and tested, reducing herbicide use as much as possible while maintaining effective weed control. There is continued development of both robotic and tractor-mounted detection systems, with ongoing research aimed at improving the accuracy of these systems across a variety of crop types and environments. There can be many technologies that will be implemented into agriculture in the coming years, including the development of better algorithms, higher recognition precision, faster and more robust implements, as well as fully autonomous systems or highly sophisticated systems.
Conference Participation – 22nd Scientific Conference of the Hellenic Weed Science Society
Date: 19–21 March 2025
Location: Arta, Greece
M. Tserioni, R. J. Van-Esdonk, D. Chachalis, K. Ferentinos, G. G. Petinatos
Utilizing Artificial Neural Networks (ANNs) for Accurate Weed Detection in Rice Cultivation
Abstract
Weeds pose a significant threat to rice cultivation, reducing yield and production quality. Specific species, such as red rice (Oryza sativa, ORYZ), barnyardgrass (Echinochloa spp., ECHCG), and smallflower umbrella sedge (Cyperus difformis, CYPDI), stand out for their competitive ability, making their accurate identification essential. In this study, 30 pots of each weed species were established, along with cultivated rice (Indica long sperm / CL111 variety), in the greenhouse of the Benaki Phytopathological Institute. High-resolution photographs were taken at various weed development stages, creating an extensive dataset. This dataset was used to develop digital weed recognition models through advanced image analysis and machine learning techniques. Two different machine learning (ML) models were used for weed differentiation and classification. In the Hue-Saturation-Value (HSV) color space, separation between cultivated rice and weeds was performed using Support Vector Machines (SVM). In the Red-Green-Blue (RGB) color space, an evaluation was made of the advanced convolutional neural network (CNN) YOLOv8, which is used both for object detection within the image and for classification. In both models, system performance measurement was based on established evaluation metrics: Precision, Recall, mean Average Precision at 50% (mAP50), and F1-score. These metrics were calculated both for each weed type individually and for all weeds collectively. The distinction between cultivated rice and red rice or barnyardgrass was satisfactory in both cases, with better results from YOLOv8; however, the same cannot be said for smallflower umbrella sedge. The use of these methods contributes significantly to improving the accuracy of weed detection systems, bridging the gap between laboratory conditions and field applications. The result is a more efficient and sustainable weed management approach in rice cultivation.
Conference Participation-20th European Weed Research Society Symposium
Date: 1-4 July 2025
Location: Lleida, Spain
Tserioni, Z. M., Psomiadis, E., Oikonomou, A., Kavadias, A., Avramidou, M., Petinatos, G. G., Kopaka, C., Petraki, A., Chachalis, D.
Advanced Approaches for Monitoring and Managing Weeds in Rice Cultivation.
Abstract
This study focuses on addressing the challenges posed by weeds in rice cultivation through the application of innovative methods that utilize ground-based and aerial multispectral sensors, as well as high-resolution satellite imagery. Particular emphasis is placed on estimating the density of three major weed species: Oryza sativa (ORYZ), Echinochloa spp. (ECHCG), and Cyperus difformis (CYPDI), which pose a significant threat to rice production due to their competitive ability. The research was conducted in the largest rice cultivation region in Greece (Chalastra, Thessaloniki) during the 2023–2024 growing season, in three experimental fields, each approximately 20 hectares in size. An advanced UAV (quadcopter drone) equipped with a MicaSense RedEdge-MX multispectral camera (5 bands: R, G, B, RedEdge, NIR) was used for data collection. UAV flights produced high-resolution orthophotomaps (3.5 cm/px), while weed density classification was performed in ArcMap, aiding in the spatial categorization of weed density in the fields. Specific vegetation indices, such as the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Red Edge Index (NDRE), were calculated, enabling correlation of weed density with the data derived from the orthophotomaps. Satellite images were obtained from Sentinel-2A (12 bands with resolutions ranging from 10 m to 60 m), in chronological correspondence with UAV flights at two time points: August 1–3 (BBCH 57–59) and September 11–13 (BBCH 77). In the pilot area, 48 samples were collected using a 0.5 × 0.5 m sampling frame (September 11–13) to estimate weed biomass as a percentage of total crop biomass: low (5.22%), medium (18.3%), and high (31.1%). These data provided significant input for correlating digital weed detection models with the vegetation indices derived from UAV and satellite imagery. This study highlights the importance of integrating digital tools, such as UAV-based multispectral imaging and satellite data, for precise weed mapping and management. The use of these technologies supports sustainable rice cultivation, promotes the rational and timely use of herbicides, and contributes to limiting weed resistance to herbicides.
Conference Participation – FOOD2030 Networks Conference 2025
Date: 2–4 December 2025
Location: Copenhagen, Denmark
Demosthenis Chachalis, Aggeliki Petraki, Nikolina Vidali, Dimitris Vlotsos, Athina Motsenigou, Gerasimos Peteinatos, Alma Balestrazzi
Participatory Pathways for Agroecological Transition in Mediterranean and European Food Systems
Abstract
Over the last five years, our research group in Benaki Phytopathological Institute (BPI) has been involved either as coordinator or a key partner in several Mediterranean projects (i.e. PRIMA-ZeroParasitic, PRIMA-Benefit-Med, and the Greek project ARTs-rice) aiming to advancing participatory frameworks for agroecological innovation in various cropping systems. These projects established multi-actor Living Labs and Communities of Practice bring together farmers, researchers, SMEs, and policymakers to co-design and test agroecological solutions in crop management, input reduction, and ecosystem restoration. Through iterative learning cycles, participatory field trials, and digital tools for knowledge exchange, the projects strengthened local innovation capacity and demonstrated the value of farmer-scientist collaboration for adaptive management under changing climatic and socio-economic conditions. Building upon this foundation, the newly launched Horizon Europe project PROSPER (2025–2029) expands this participatory legacy into a pan-European framework for resilient and biodiversity-friendly agroecosystems, by focusing on orphan legumes. PROSPER integrates the methodological and social innovations developed under previous initiatives into a cohesive platform for co-creation, behavioral adoption, and policy uptake. The project mobilizes Living Labs as engines of transition, linking agroecological science with digital decision support, circular practices, and market incentives. By reinforcing transnational collaboration and farmer engagement, PROSPER aims to accelerate the scaling of agroecological solutions, contributing directly to the European Green Deal, Farm to Fork, and Zero-Pesticide ambitions for sustainable food systems.