Data generated from trait analysis will be used to develop convolutional neural net architectures capable of analysing image sequences of roots or shoots to extract temporal traits associated with environmental stress. The initial focus of this task will be to develop convolutional neural net architectures capable of analysing image sequences of roots to extract temporal traits associated with heat/drought.
Plants grown under varying stress levels by members of the challenge team will be imaged over time and networks will be trained to distinguish the different conditions applied. The initial focus will be on 2D colour images of a single species (rice) undergoing a single stress (heat/drought), but we expect the techniques developed, and particularly the network architectures, to be extendable to 3D imager, other species, and other stressors.
This PhD will be based in the School of Computer Science. For further details, please contact Prof Tony Pridmore: [email protected]
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need. Why not add a message here