Towards the goal of carbon neutrality by 2050, Precision Fertiliser Management (PFM) has become high priority to maintain globally sustainable agriculture. Typically, PFM will depend on the widespread use of Internet of Things technologies (eg. UAV, mobile sensors) to collect and store a deluge of heterogenous farming data for intelligent decision-making, including suggestion of fertilizer use, prediction of crop yield, supervision of farming activities, etc. This project aims at investigating an emerging machine learning paradigm, namely lifelong learning, to analysis and mining multimodal farming data so as to make wise fertiliser management over long-time scales.
About the project
In order to reduce carbon emissions and improve crops productivity, many countries have developed IoT enabled smart farming technologies that enables monitoring, collecting and storing massive farming data over long-time scales. These long-term farming data brings more opportunities on leveraging emerging machine learning methods to examine the effects of multiple factors on crop growth and provide optimal fertilization usages for sustainable agricultural management.
This project intends to investigate how lifelong learning is used to analysis long-term farming data for providing precision fertiliser management. The main technical issue in this project includes feature selection of output-relevant variables, regression modelling of specific task upon a given dataset, lifelong learning of multiple consecutive tasks and learning new task by knowledge transfer. The main research objective in this project include: 1) to study to formulate long-term fertiliser management as a sequential multi-task learning problem and construct multiple farming datasets for individual tasks; 2) to develop reliable and robust predictive model for each task and find the relationships of various factors regarding fertilization usage; 3) to explore lifelong learning methods for modelling relationships of multiple tasks and predict future optimal fertilization usage by knowledge transfer from previously learned task.
Dr. Po Yang is a Senior Lecturer in the Department of Computer Science at The University of Sheffield (TUoS). His research interests are in mobile computing, machine learning and pervasive healthcare. Dr Yang has a broad interest in pervasive intelligence and its use in several applied domains. Since 2010, as first or corresponding author, Dr. Yang has published 32 high impact peer-reviewed IEEE Trans/Journal papers. (Google Citations > 3200, h-index 32, RG score = 34.56). Dr Yang has been a Principal Investigator of three Innovate UK collaborative projects (ID: I07462 and 10002902), one BBSRC project, and one EPSRC Industrial CASE PhD project (EP/T517835/1).
About the Department and Research Group
The Organisations, Information and Knowledge Group (OAK), is a highly successful research group in the department which undertakes research on semantic technologies with a particular focus on their application to large-scale data (from a variety of sources) and knowledge management. It has strong links into one of the University’s four flagship Research Institutes (via the Healthy Lifespan University Research Institute) and has accumulated over £8.5m in funding over the last decade (of which around 20% has been directly from industry). These are of particular relevance to Dr Yang’s research interests around mobile computing, pervasive intelligence and machine learning in healthcare applications.
We are seeking an enthusiastic individual to join the OAK research group at Sheffield University, with the following attributes:
- A first class undergraduate (Bsc) and/or postgraduate masters’ qualification (MSc) in a science and technology field: Computer Science, Engineering, Mathematics, with specialisation in mobile computing, pervasive healthcare, machine learning and AI
- Familiarity with machine learning and probabilistic models
- Relevant software knowledge and experience, for example Python and tensor frameworks (PyTorch or TensorFlow), Jave, C++, etc
- Excellent analytical and numerical skills
- A driven, professional and independent work attitude
- Ability to liaise with academic supervisors from a range of disciplines
- Excellent written and verbal communication skills
How to apply
To apply for a PhD studentship, applications must be made directly to the University of Sheffield using the Postgraduate Online Application Form. Make sure Po Yang as your proposed supervisor(s).
Information on what documents are required and a link to the application form can be found here - https://www.sheffield.ac.uk/postgraduate/phd/apply/applying
The form has comprehensive instructions for you to follow, and pop-up help is available.
Your research proposal should:
- Be no longer than 4 A4 pages, include references
- Outline your reasons for applying for this studentship
- Explain how you would approach the research, including details of your skills and experience in the topic area