Agriculture & Food Systems

Farming is data-rich but has historically been technology-poor compared to other industries. AI is changing that, with applications spanning precision agriculture, crop disease detection, yield prediction, livestock monitoring, and supply chain optimisation. Computer vision systems mounted on drones or tractors can identify weeds, diseases, and nutrient deficiencies at the individual plant level, enabling targeted treatment rather than blanket spraying. Machine learning models that combine satellite imagery, weather data, and soil information can predict crop yields and help farmers make better planting and irrigation decisions. In livestock farming, AI-powered sensors monitor animal health and behaviour, detecting illness early and improving welfare outcomes. At the food system level, AI helps optimise supply chains to reduce waste - a significant issue when roughly a third of food produced globally is lost or wasted. The challenges are practical: many farms, particularly in developing regions, lack the connectivity, hardware, and technical skills to adopt these tools. Solutions that work on a well-funded research farm do not automatically translate to a smallholding in sub-Saharan Africa. The most impactful applications will be those designed for real-world farming conditions, not just ideal ones.