In response to the challenges posed by climate change, including extreme weather events, such as heavy rainfall and droughts, the agricultural sector is increasingly seeking solutions for the efficient use of resources, particularly water. Pivotal aspects of smart agriculture include the establishment of weather-independent systems and the implementation of precise monitoring and control of plant growth and environmental conditions. Hydroponic cultivation techniques have emerged as transformative solutions with the potential to reduce water consumption for cultivation and offer a sheltered environment for crops, protecting them from the unpredictable impacts of climate change. However, a significant challenge lies in the frequent need for human intervention to ensure the efficiency and effectiveness of these systems. This paper introduces a novel system with a modular architecture, offering the ability to incorporate new functionalities without necessitating a complete system redesign. The autonomous hydroponic greenhouse, designed and implemented in this study, maintains stable environmental parameters to create an ideal environment for cultivating tomato plants. Actuators, receiving commands from a cloud application situated at the network’s edge, automatically regulate environmental conditions. Decision-making within this application is facilitated by a PID control algorithm, ensuring precision in control commands transmitted through the MQTT protocol and the NGSI-LD message format. The system transitioned from a single virtual machine in the public cloud to edge computing, specifically on a Raspberry Pi 3, to address latency concerns. In this study, we analyzed various delay aspects and network latency to better understand their significance in delays. This transition resulted in a significant reduction in communication latency and a reduction in total service delay, enhancing the system’s real-time responsiveness. The utilization of LoRa communication technology connects IoT devices to a gateway, typically located at the main farm building, addressing the challenge of limited Internet connectivity in remote greenhouse locations. Monitoring data are made accessible to end-users through a smartphone app, offering real-time insights into the greenhouse environment. Furthermore, end-users have the capability to modify system parameters manually and remotely when necessary. This approach not only provides a robust solution to climate-induced challenges but also enhances the efficiency and intelligence of agricultural practices. The transition to digitization poses a significant challenge for farmers. Our proposed system not only represents a step forward toward sustainable and precise agriculture but also serves as a practical demonstrator, providing farmers with a key tool during this crucial digital transition. The demonstrator enables farmers to optimize crop growth and resource management, concretely showcasing the benefits of smart and precise agriculture.
Wildlife monitoring in remote field environments presents significant challenges owing to energy constraints, limited network connectivity, and the need for real-time processing. This study proposes a scalable framework that integrates artificial intelligence (AI) and edge computing for autonomous wildlife detection, class-based object counting in frames, distance measurement, and geolocation estimation of key European wildlife species. The system leverages deep learning-based object detection models, specifically YOLOv8m and YOLOv10m trained by the European Animal Detection Dataset, deployed on power-efficient embedded platforms such as the NVIDIA Jetson Orin Nano and Raspberry Pi 5. The experimental evaluation assesses detection accuracy, computational efficiency, and energy consumption across different hardware configurations, ensuring an optimal trade-off between performance and resource utilization. Our findings demonstrate that the proposed approach enables real-time inference while maintaining high mean average precision (mAP) and minimizing power consumption, ensuring feasibility in resource-limited field conditions. A comprehensive cost-performance analysis highlights the Jetson Orin Nano as the optimal choice for balancing accuracy and efficiency, achieving 40.1 Frame Per Second (FPS) at just 8W in 25W power mode using a TensorRT-optimized YOLO model. Meanwhile, the Raspberry Pi 5 serves as a cost-effective alternative for lightweight models. Beyond technical performance, this work underscores the transformative role of edge AI in supporting ecologists and agronomists with actionable insights for biodiversity conservation, human wildlife conflict mitigation, and sustainable ecosystem management.
This study presents a networked cyber-physical architecture that integrates a Reinforcement Learning-based Digital Twin (DT) to enable zero-delay interaction between physical and digital components in smart agriculture. The proposed system allows real-time remote control of a robotic arm inside a hydroponic greenhouse, using a sensor-equipped Wearable Glove (SWG) for hand motion capture. The DT operates in three coordinated modes: Real2Digital, Digital2Real, and Digital2Digital, supporting bidirectional synchronization and predictive simulation. A core innovation lies in the use of a Reinforcement Learning model to anticipate hand motions, thereby compensating for network latency and enhancing the responsiveness of the virtual–physical interaction. The architecture was experimentally validated through a detailed communication delay analysis, covering sensing, data processing, network transmission, and 3D rendering. While results confirm the system’s effectiveness under typical conditions, performance may vary under unstable network scenarios. This work represents a promising step toward real-time adaptive DTs in complex smart greenhouse environments.
Traditional segmentation methods are slow and rely on manual annotations, which are labor-intensive. To address these limitations, we propose YOLO-SAM AgriScan, a unified framework that combines the fast object detection capabilities of YOLOv11 with the zero-shot segmentation power of the Segment Anything Model 2 (SAM2). Our approach adopts a hybrid paradigm for on-plant ripe strawberry segmentation, wherein YOLOv11 is fine-tuned using a few-shot learning strategy with minimal annotated samples, and SAM2 performs mask generation without additional supervision. This architecture eliminates the bottleneck of pixel-wise manual annotation and enables the scalable and efficient segmentation of strawberries in both controlled and natural farm environments. Experimental evaluations on two datasets, a custom-collected dataset and a publicly available benchmark, demonstrate strong detection and segmentation performance in both full-data and data-constrained scenarios. The proposed framework achieved a mean Dice score of 0.95 and an IoU of 0.93 on our collected dataset and maintained competitive performance on public data (Dice: 0.95, IoU: 0.92), demonstrating its robustness, generalizability, and practical relevance in real-world agricultural settings. Our results highlight the potential of combining few-shot detection and zero-shot segmentation to accelerate the development of annotation-light, intelligent phenotyping systems.
Maintaining optimal microclimatic conditions within greenhouses represents a significant challenge in modern agricultural contexts, where prediction systems play a crucial role in regulating temperature and humidity, thereby enabling timely interventions to prevent plant diseases or adverse growth conditions. In this work, we propose a novel approach which integrates a cascaded Feed-Forward Neural Network (FFNN) with the Granular Computing paradigm to achieve accurate microclimate forecasting and reduced computational complexity. The experimental results demonstrate that the accuracy of our approach is the same as that of the FFNN-based approach but the complexity is reduced, making this solution particularly well suited for deployment on edge devices with limited computational capabilities. Our innovative approach has been validated using a real-world dataset collected from four greenhouses and integrated into a distributed network architecture. This setup supports the execution of predictive models both on sensors deployed within the greenhouse and at the network edge, where more computationally intensive models can be utilized to enhance decision-making accuracy.