Agrofood and Environment Sustainability

The student must have basic computer skills at the user level.

The curricular unit seeks to develop doctoral students’ in-depth knowledge of the different approaches and technologies and how they can be integrated for agricultural management. In addition to knowledge and proficiency from the user’s perspective, PhD students will also have the chance to deepen their technical knowledge through technological challenges, aligned with their thesis topic and aimed at acquiring skills that will be used and optimized in their thesis work. This Problem Based Learning approach allows them to deepen their knowledge and, above all, their technical skills, which are unusual in the field of agriculture. The proposed methodologies include the exposition of concepts and theoretical content, followed by “hands on”, “on the job” opportunities individually targeted to the needs in terms of the doctoral thesis of each of the PhD students. Thus, the approach seeks to make doctoral students proficient in remote sensing, image processing and the use of GIS as a tool to support decision-making. PhD students will also acquire skills in IoT, automation, robotic systems and data processing using artificial intelligence and machine learning methodologies. Theoretical lectures cover each subject. Theoretical-practical classes combine theoretical concepts with the resolution of theoretical/practical exercises and the presentation of equipment used in operations. In the practical component, PhD students will develop their own project, in line with the theme of their doctorate, i.e. they will develop skills that will later be used in their thesis work.

The curricular unit provides fundamental knowledge of precision agriculture and automation in agriculture, and the use of information systems in agricultural management. PhD students should: Be proficient in the use of Geographic Information Systems (GIS) software and the use of GIS software for editing, integrate data and produce information; Acquires know how to process and edit images, record, process data and graphically data representation; Know the structure, functions and connections of different types of sensors and actuators, and IoT devices and technologies; Differentiate between various automation systems and identify the components used, as well as understanding the ideas behind automation technology and recognizing the different types of robotic systems; Explore the tools and systems that use artificial intelligence (AI), as well as learning about the development of machine learning techniques, with real data.

MOD 1: Introduction to Digital Agriculture.What is Digital Agriculture / Agriculture 4.0? Importance and benefits of Digital Agriculture. History and evolution of Digital Agriculture. Precision Agriculture.

MOD 2: Geographic Information Technology in Agriculture. Satellite Positioning Technology applied to Agriculture (GNSS). Geographic Information Systems (GIS) in Agriculture. Application of Remotely Piloted Aircraft Systems in agriculture. Types of drones: fixed-wing and multi-rotor. Applications: mapping, spraying, monitoring. Sensors. Legal considerations and regulations for drone use. Digital image processing for monitoring agricultural crops. Remote sensing concepts, fundamentals, and platforms (Orbital, Aircraft, Drone). Remotely Piloted Aircraft Systems in agriculture. Remote sensing and use of orbital images. Concepts and fundamentals of remote sensing. Remote sensing systems – sensors and platforms. Digital image processing – restoration and enhancement techniques. Visual interpretation techniques – photointerpretation. Land Cover and Land Use (LCLU). Digital image processing – classification techniques. Digital image processing – time series and change analysis.

MOD 3: New Technologies for Agriculture. Internet of Things (IoT) and sensor networks. Application of the IoT concept in agriculture. Examples of practical systems developed. Sensors to be used: temperature, humidity, atmospheric pressure, light intensity, pH, conductivity, among others. Low Power Wide Area Networks (LPWAN). Requirements, characteristics, and applications of LPWAN systems. LORA and LORAWAN technology: characteristics and applications. ZigBee technology – IEEE 802.15.4: characteristics and applications. Topics on Sigfox and NB-IoT technology. Information and communication technologies (ICT). Application of ICT technologies in agriculture. Digitalization of agricultural processes. LoRaWAN network: architecture, message types, device classes, and security. Activation of end devices. Registration of devices used in agriculture: sensors and actuators. Radio transceivers of LORAWAN and ZigBee technologies.

MOD 4: Automatic Control Systems. Artificial Intelligence, Machine Learning, and Big Data. Storage, analysis, and interpretation of large volumes of data from various sources (Big Data). Implementation of IoT solutions: platforms, protocols, and cloud services. The Things Network (TTN) and The Things Stack (TTS). Development of dashboards for data analysis. Application of Artificial Intelligence (AI) to agriculture. Machine learning (ML) techniques. Bayesian network, Decision tree, Artificial Neural Networks (ANN), Clustering, and Genetic Algorithms. Topics on blockchain technology applied to the production chain. Automatic control systems. Introduction and Fundamentals. Definition and Basic Concepts. What are automatic control systems? Difference between manual, semi-automatic, and automatic control. Examples applied to agriculture. Essential Components. Sensors (functions and types). Actuators. Controllers (PI, PD, PID, and others). Human-machine interfaces (HMI). Control Architectures. Open-loop vs. closed-loop systems. Practical examples in greenhouses and irrigation. Applications in Agriculture. Environmental Control in Greenhouses. Monitoring and adjusting temperature, humidity, and CO₂. Model-based control systems (forecasting and simulation). Intelligent and Precision Irrigation. Automatic systems based on humidity and climate sensors. Use of climatic data and forecasts. Autonomous Navigation Systems in Agricultural Machines. Control of autonomous vehicles (tractors, drones). RTK-GPS and computer vision systems. Post-harvest Processing Control. Storage control (temperature and controlled atmosphere). Automated processing of agricultural products.

MOD 5: Agricultural Robotics. Fundamentals and Introduction to Agricultural Robotics. Introduction. Definition of robotics and its application in different sectors. Context and importance of robotics in modern agriculture. The impact of robotics on productivity and sustainability. Basic Components of an Agricultural Robot. Sensors: computer vision, proximity sensors, environmental sensors. Actuators: robotic arms, wheels, drones. Control systems: intelligence and decision algorithms. Power sources: batteries, among others. Types of Agricultural Robots. Field robots: for harvesting, planting, monitoring. Agricultural drones: mapping, spraying, data collection. Robots for livestock: supervision and feeding of herds. Robots for greenhouses: pruning, pollination, and harvesting. Applications and Emerging Technologies. Applications in Precision Agriculture. Soil mapping and analysis. Crop monitoring by drones. Optimization of irrigation and fertilizer use. Robots for Harvesting and Pruning. Computer vision technologies to identify ripe fruits. Agricultural Drones. Types of drones: fixed-wing and multi-rotor. Functions: spraying, crop monitoring, climatic data collection. Automation in Livestock. Robots for automated milking. Monitoring animal health through sensors. Emerging Technologies. Machine learning in robotic decision-making. Use of neural networks to identify pests and diseases. Integration of IoT for real-time communication.

MOD 6: Challenges and Future of Digital Agriculture. Evolution of Agriculture. Agriculture 5.0. Advanced artificial intelligence. Collaborative robotics (cobots). Building Information Modeling. Biotechnology and Precision Genetics.

The assessment will be made by evaluating the work and an exam on concepts and theoretical aspects of the approaches, with a weight of  40%. The remaining 60% will be awarded for the proficiency demonstrated in the development of a project in a "Problem Based Learning"  environment, relevant to the doctoral work.

NAO