Water management is paramount in countries with water scarcity. This also affects agriculture, as a large amount of water is dedicated to that use. The possible consequences of global warming lead to the consideration of creating water adaptation measures to ensure the availability of water for food production and consumption. Thus, studies aimed at saving water usage in the irrigation process have increased over the years. Typical commercial sensors for agriculture irrigation systems are very expensive, making it impossible for smaller farmers to implement this type of system. However, manufacturers are currently offering low-cost sensors that can be connected to nodes to implement affordable systems for irrigation management and agriculture monitoring. Due to the recent advances in IoT and WSN technologies that can be applied in the development of these systems, we present a survey aimed at summarizing the current state of the art regarding smart irrigation systems. We determine the parameters that are monitored in irrigation systems regarding water quantity and quality, soil characteristics and weather conditions. We provide an overview of the most utilized nodes and wireless technologies. Lastly, we will discuss the challenges and the best practices for the implementation of sensor-based irrigation systems.

The use of precision agriculture is becoming more and more necessary to provide food for the world’s growing population, as well as to reduce environmental impact and enhance the usage of limited natural resources. One of the main drawbacks that hinder the use of precision agriculture is the cost of technological immersion in the sector. For farmers, it is necessary to provide low-cost and robust systems as well as reliability. Toward this end, this paper presents a wireless sensor network of low-cost sensor nodes for soil moisture that can help farmers optimize the irrigation processes in precision agriculture. Each wireless node is composed of four soil moisture sensors that are able to measure the moisture at different depths. Each sensor is composed of two coils wound onto a plastic pipe. The sensor operation is based on mutual induction between coils that allow monitoring the percentage of water content in the soil. Several prototypes with different features have been tested. The prototype that has offered better results has a winding ratio of 1:2 with 15 and 30 spires working at 93 kHz. We also have developed a specific communication protocol to improve the performance of the whole system. Finally, the wireless network was tested, in a real, cultivated plot of citrus trees, in terms of coverage and received signal strength indicator (RSSI) to check losses due to vegetation.

The monitoring of farming processes can optimize the use of resources and improve its sustainability and profitability. In fish farms, the water quality, tank environment, and fish behavior must be monitored. Wireless sensor networks (WSNs) are a promising option to perform this monitoring. Nevertheless, its high cost is slowing the expansion of its use. In this paper, we propose a set of sensors for monitoring the water quality and fish behavior in aquaculture tanks during the feeding process. The WSN is based on physical sensors, composed of simple electronic components. The system proposed can monitor water quality parameters, tank status, the feed falling and fish swimming depth and velocity. In addition, the system includes a smart algorithm to reduce the energy waste when sending the information from the node to the database. The system is composed of three nodes in each tank that send the information though the local area network to a database on the Internet and a smart algorithm that detects abnormal values and sends alarms when they happen. All the sensors are designed, calibrated, and deployed to ensure its suitability. The greatest efforts have been accomplished with the fish presence sensor. The total cost of the sensors and nodes for the proposed system is less than 90 €.

Deploying wireless sensor networks (WSN) in rural environments such as agricultural fields may present some challenges that affect the communication between the nodes due to the vegetation. These challenges must be addressed when implementing precision agriculture (PA) systems that monitor the fields and estimate irrigation requirements with the gathered data. In this paper, different WSN deployment configurations for a soil monitoring PA system are studied to identify the effects of the rural environment on the signal and to identify the key aspects to consider when designing a PA wireless network. The PA system is described, providing the architecture, the node design, and the algorithm that determines the irrigation requirements. The testbed includes different types of vegetation and on-ground, near-ground, and above-ground ESP32 Wi-Fi node placements. The results of the testbed show high variability in densely vegetated areas. These results are analyzed to determine the theoretical maximum coverage for acceptable signal quality for each of the studied configurations. The best coverage was obtained for the near-ground deployment. Lastly, the aspects of the rural environment and the deployment that affect the signal such as node height, crop type, foliage density, or the form of irrigation are discussed.

The number of forest fires that occurred in recent years in different parts of the world is causing increased concern in the population, as the consequences of these fires expand beyond the destruction of the ecosystem. However, with the proliferation of the Internet of Things (IoT) industry, solutions for early fire detection should be developed. The assessment of the fire risk of an area and the communication of this fact to the population could reduce the number of fires originated by accident or due to the carelessness of the users. This paper presents a low-cost network based on Long Range (LoRa) technology to autonomously evaluate the level of fire risk and the presence of a forest fire in rural areas. The system is comprised of several LoRa nodes with sensors to measure the temperature, relative humidity, wind speed and CO₂ of the environment. The data from the nodes is stored and processed in a The Things Network (TTN) server that sends the data to a website for the graphic visualization of the collected data. The system is tested in a real environment and, the results show that it is possible to cover a circular area of a radius of 4 km with a single gateway.

Precision Agriculture (PA) is gaining new momentum due to its ability to accurately adjust the resources to a crop’s needs while maintaining/enhancing quality levels. However, crop-damaging pests compromise yields, jeopardizing the benefits of PA. Computer vision-based pest detection techniques offer promising avenues to overcome potential losses for farmers. The recent object detection framework, YOLOv8 (You Only Look Once) applied to real-time insect monitoring is an open-source, cutting-edge PA approach based on Convolutional Neural Network (CNN) models that enables precise and quick decision making in agricultural crops. Under this umbrella, traditional pest studies using YOLO or other deep-learning solutions focused on only one or a few insects for specific crops provide an excessively narrow solution. In this paper, we propose a new form of using YOLO for pest detection with a generalist perspective by intensively testing a YOLOv8-based tool implementing a single insect category. The goal is to detect the presence of any type of insect in any type of crop in real time. A comprehensive performance evaluation is carried out using a well-known dataset. The results of the training, validation, and testing phases are then discussed, obtaining an mAP ₅₀ value of 0.967 for the m model and an mAP _50-95 value of 0.632 for the l model. Finally, we also identify the premises to elaborate a complete and useful dataset able to unleash the full potential of YOLOv8.