Sustainable and smart agriculture is emerging based on digital agriculture, focused on utilizing modern information and communication technologies to increase the quantity and quality of agricultural products while reducing the needed human workload.

A fundamental challenge in practical agricultural systems is to understand the complex biological environment through a large amount of field sensors and build system-level intelligent applications based on Artificial Intelligence (AI). The Internet of Things (IoT) technology supports to deploy massive sensors that collect and transmit data, monitoring soil, water, light, humidity, temperature, etc. Then, based on the gathered data, it is feasible to build a digital twin system and use the smart AI model to deal with the practical agricultural problems, such as smart diagnostics, decisions, and actions. From the perspective of sustainable environment, smart agricultural models play a vital role in understanding and monitoring the growing status of plants and crops.

The aim of this Special Issue is to collect research focusing on advanced IoT, digital twin, and AI algorithms in smart agricultural systems, committed to providing solutions for precision agriculture, plant factories, smart greenhouses, etc. It aims to call for the state-of-the-art research in theories, algorithms, models, systems, and applications. The original research and review articles are both welcomed.

Potential topics include but are not limited to the following:

• Smart IoT sensors for smart agricultural systems
• Security and privacy for IoT in digital agriculture
• Architecture, protocols, and frameworks of IoT in agriculture
• Digital twin of smart agriculture supported by drones and sensors
• Plant health monitoring and precise control of weeds in digital twin
• Deep learning and reinforcement learning for data-driven AI systems
• Multi-source IoT-based data fusion for AI-based smart agricultural systems
• Cloud computing or edge computing for smart agricultural applications
• Few-shot learning and data quality assessment in smart agricultural applications
• Deep learning methods for the analysis of complex multi-source time-series data
• Model acceleration and edge computing based on AI methods and big data from IoT
• Specific applications, e.g., crop pests and disease recognition, yield prediction, irrigation strategies, agricultural on-line data acquisition, farm machinery, etc