The Distributed AI in Agriculture group focuses on development of distributed Artificial Intelligence (AI) techniques for Agriculture. Distributed AI facilitates agriculture by integrating data from diverse sources, such as sensors, actuators, and satellites, enabling real-time modeling and simulation of crop conditions and agricultural operations. This integration allows for the prediction of future conditions and avoid potential issues. For example, AI can help in identifying the optimal planting time, predicting crop diseases before they occur, optimizing water usage, and improving yield predictions. This results in more sustainable farming practices, reduced environmental impact, and improved food security. They can also predict how crops will respond to different environmental conditions or management strategies without having to conduct experiment in the real world. This reduces risks, saves time, and ensures optimal resource use, leading to increased efficiency and productivity in agricultural practices. Our initial step is to develop digital twin for agriculture, because it bridges the gap between the physical and digital worlds. By creating a virtual replica of farming operations, digital twins enable precise monitoring, simulation, and prediction of conditions, which can enhance decision-making in real-world. This integration of data modeling and simulation can address limitations of current decision-making across different agricultural areas.
Group Leader: Associate Professor Xiang Su
Information about research focusing on Laser scanning in management of renewable natural resources will be added here soon.