This project aims to develop a proof of concept, cost-effective, and easy-to-use mobile imaging application that uses artificial intelligence (AI) modelling to accurately diagnose early onset foliar disease symptoms in wheat and oilseed rape crops. We will develop new technology that provides unprecedented levels of disease diagnosis accuracy by using various crop-specific parameters to train the AI models and find new patterns. To do this, we make use of NIAB's research facilities and expertise to collect extensive datasets across a wide range of trials. This includes crops grown under controlled conditions and those inoculated with specific diseases. Farmers and growers will be able to use the tool to rapidly and accurately diagnose diseases, allowing them to take early intervention to stop the pathogen from spreading. This will result in higher crop yields and reduce the amount of fungicide needed. We will also develop a scoring system that allows the user to receive a rating for the disease identified. This will provide scientific users (breeders and researchers) with data that can be used to quantify assessments, enhancing their ability to identify the most disease resistant lines and varieties. Early and timely detection of foliar pathogens provides growers with greater time to intervene, reducing the risk of losses to yield and quality, and reducing the likelihood further sprays will be required to control the outbreak. More accurate detection and diagnosis could help to prevent growers from applying fungicides unnecessarily, helping to reduce chemical use, improving sustainability, and reducing risks of fungicide resistance development. The ability to score disease ratings would also improve breeders' ability to select the most disease resistant breeding lines, thus improving overall crop resilience.