Digital Agriculture, Food and Wine

Digital Agriculture (DA) deals with implementing and integrating digital data, sensors, and tools on agricultural, food, and wine applications from the paddock/vineyard to consumers. These technologies can range from big data, sensor technology, sensor networks & IoT, remote sensing, robotics, unmanned aerial vehicles (UAV).

Data processing is performed using new and emerging technologies, such as computer vision, machine learning, and artificial intelligence, among others.

The latest advances made by the DAFW group for crop monitoring/decision making, assessment of the quality of produces, sensory analysis for consumer perception and animal stress, and welfare assessment.

Examples of the DAFW outputs are:

• Deep and machine learning modelling based on remote sensing for Livestock identification and welfare assessment
• Assessment of aroma profiles in cocoa plantations based on aerial photogrammetry, canopy architecture and AI
• Assessment of big data related to environmental factors affecting dairy cow stress and milk productivity and quality
• Remote sensing and AI to assess crop water status
• Use of robotics and remote sensing to assess the intensity of beer sensory descriptors , consumers acceptability , proteins and other physicochemical parameters
• Use of biometrics from consumers to assess acceptability of beer , and insect-based snacks
• A portable electronic nose (e-nose) coupled with AI to assess aromas in beer, smoke taint in wines after bushfires and detecting pest and diseases in crops , and
• NIR and machine learning to assess physicochemical parameters and sensory descriptors of beer , and physicochemical parameters in chocolate , detection of pest and diseases in crops, assessment of berry cell death and plant water status, among others.

Due to complexities involving agriculture, food, and wine sciences, many people consider these practices part science, part art. However, we attribute these complexities to intricate interactions that need to be taken into consideration and understood. These are related to complex processes happening in the soil, the root system, the plant, and canopies interacting with the atmosphere throughout the season.

The recent implementation of unmanned aerial vehicles (UAVs) or drones and remote sensing opened up a variety of technologies that were developed for image analysis through computer vision, more robust modeling techniques through machine learning and artificial intelligence that can be applied to agriculture and food process.

Our group has made many advances in researching these potential techniques for practical applications in the industry and many more industries related to animal production and food science.

What is the difference between Precision Agriculture (PA) and Digital Agriculture (DA)?

Precision agriculture has been around for more than 30 years and relates to the technology implemented in agricultural applications such as satellites, GPS guided agricultural machinery, among others. The DAFW group creates intelligent and smart tools to interpret data and do practical and tangible applications using machine learning, robotics, and artificial intelligence. The DAFW group has been developing DA practical tools that can be readily applied to the industry.