Application of Artificial Intelligence to the study of Environmental Risks

Entry requirements

Applicants for this course should have achieved a UK 2:1 honours degree.

Applications are encouraged from exceptional candidates with backgrounds in:

• natural sciences (e.g. physics, chemistry, earth sciences, biology)
• engineering
• computer science
• mathematics

Strong computational and programming skills are highly desirable.

Months of entry

September

Course content

The UKRI Centre for Doctoral Training in the Application of Artificial Intelligence to the study of Environmental Risks (AI4ER) trains researchers (through several multidisciplinary cohorts) to be uniquely equipped to develop and apply leading-edge computational approaches to address critical global environmental challenges by exploiting vast, diverse and often currently untapped environmental data sets. Embedded in the outstanding research environments of the University of Cambridge and the British Antarctic Survey (BAS), the AI4ER CDT addresses problems that are relevant to building resilience to environmental hazards and managing environmental change. The primary application areas are:

• Weather, Climate and Air Quality
• Natural Hazards
• Natural Resources (food, water & resource security and biodiversity)

Students in the CDT cohorts engage in a one-year MRes degree in Physical Sciences (Environmental Data Science) which includes a taught component and a major research element, followed by a three-year PhD research project. Students will receive high-quality training in research, professional, technical and transferable skills through a focused core programme with an emphasis on the development of data science skills through hackathons and team challenges. Training is guided by personalised advice and the expertise of a network of partners in industry, government, the third sector and beyond.

Educational Aims

The overall objectives of the MRes course are to:

• Provide students with a broad understanding of the range of urgent environmental challenges facing global society and the practical experience of applying AI-based tools to address these challenges. The training programme will be individually tailored to take into account the educational background and interests of the students;
• Build a cohort of students and equip them with skills that prepare them optimally for PhD research. Students will undertake both individual masters-level research projects, as well as a guided team challenge, before embarking on their PhD research. The aim is to encourage both originality and intellectual independence in tackling complex problems and to foster team working and leadership skills suited to academic and industrial R&D environments and to policymaking.
• Develop entrepreneurial and project management skills and generate awareness of industrial, commercial and policy drivers through relevant cohort activities and close integration of CDT partners in the delivery of the educational programme.

Learning Outcomes

By the end of the programme, students will have:

• learnt additional skills in disciplines outside of their first degree;
• gained understanding and command of methods and techniques relevant for research at the interface between artificial intelligence and machine learning on the one hand and the study of environmental change and risk on the other;
• attended lectures in degree level topics bespoke to complement their own strengths and knowledge base upon entry, gaining a broad overview and specific knowledge of environmental data science, shared across the whole cohort;
• developed skills in research methods through the execution of a masters level independent research project;
• developed a full interdisciplinary PhD proposal they can defend in an oral examination and, if successful, embark on from their 2nd year at the CDT;
• gained an understanding of the Enterprise landscape relating to environmental data science;
• developed a good transferrable skills base, including science communication skills, as well as a sound grasp of safety and ethics in research;
• learnt to work effectively in teams as well as individually.