Jack Foster is from Staffordshire. Jack wanted to join the CDT due to its combining of Artificial Intelligence and Robotics, as well as the focus on agricultural applications. Jack has already enjoyed various AgriFoRwArdS conferences and seminars, as well as training materials. Jack is particularly interested in autonomous high-value crop harvesting and the computer vision and multi-agent problems this task presents. Jack has never been to Lincoln before, but is very excited to discover what the University and the city have to offer. Jack will be proceeding on to the University of Cambridge for his PhD research. He is looking forward to studying at a University with such excellent resources and beginning his research with the opportunity to explore new problems within agri-food robotics. Jack listens to a lot of music in his spare time, enjoys going to gigs and playing the guitar. He also likes to spend time in the countryside, when time permits, and dabbles in wildlife photography.
Lifelong Learning for Sensor-based Precipitation Regression
This project seeks to improve the crop yield of a small farm by optimising the soil-moisture content via precipitation regression. A CNN or RNN, will use wind speed/direction, humidity, temperature, and air pressure to predict future precipitation. Once the network is trained, lifelong learning will be applied to improve the network’s performance when localised within the small farm, using data collected in real-time from a range of sensors and an Arduino. The future precipitation will be combined with the current moisture levels to create predictions on whether the crop requires watering today.