Smart agents for complex environmental data

Location:

Computer Science, Streatham Campus, University of Exeter

The University of Exeter’s Department of Computer Science is inviting applications for two fully funded PhD studentships to commence on 23 September 2024 or as soon as possible thereafter. For eligible students each studentship will cover Home or International tuition fees plus an annual tax-free stipend of at least £19,237 for 4 years full-time, or pro rata for part-time study. The student would be based in Computer Science in the Faculty of Environment, Science and Economy at the Streatham Campus in Exeter.

These are 4 year PhD studentships funded by University of Exeter to support the UKRI AI Hub on “AI for Collective Intelligence (AI4CI)” (UKRI grant number EP/Y028392/1). Two fully funded studentships are available. The students will be aligned to the UKRI AI Centre for Doctoral Training in Environmental Intelligence (UKRI grant number EP/S022074/1) for purposes of training, enrichment and cohort activities.

Project Description:

Smart agents for complex environmental data

A huge volume of data on climate, biodiversity and other environmental challenges is now routinely generated by (e.g.) sensors, satellites, drones/UAVs, digital media, models, and simulations. Making effective use of this data depends on insight and interpretation by expert scientists, which creates information bottlenecks in decision-making; there are too few scientists to supply the huge demand for decision-ready knowledge around environmental sustainability. Meanwhile, artificial intelligence (AI) is rapidly increasing our scientific ability to extract patterns from observations and make predictions of environmental processes. Generative AI is providing new abilities for automated systems to interact with human users using natural language, audio and video channels.

This PhD project will develop “smart agent” tools that harness generative AI as an interface between human decision-makers and complex environmental data/models. Smart agents are envisaged as software tools that interact with humans in a conversational and natural style, interpret the information needs and context of individual users, and then utilise a range of environmental models and data sources to provide immediate answers to questions. Smart agents might be deployed across a range of platforms (e.g. web applications, social media bots) and interact in different styles (e.g. text/audio chatbots, video avatars). A core challenge is the establishment of robust and rigorous methods that build trust; scientific information must always be interpreted and presented with attention to accuracy, uncertainty and ambiguity. Responsible innovation and stakeholder engagement are vital to ensure these tools are developed ethically and deliver public environmental benefits.

Potential benefits of smart agents for the environment are diverse and substantial. Smart agents can interact with humans at scale, yet provide information tailored to individuals, supporting better environmental decision-making. They can provide easy access to scientific knowledge, to counter misinformation and improve the quality of public debate. They can translate across languages and democratise access to information around the world. In these and many other ways, this technology can help in the ongoing struggle to mitigate and reverse environmental damage in the 21st century.

This studentship offers some flexibility for the student to tailor their research project towards their own interests. The student will join a team of researchers working on relevant topics and will be supported to develop a strong research proposal in collaboration with their supervisors.

Two fully funded PhD studentships are available. Students will be based at University of Exeter (Streatham Campus) and work under supervision of Prof Hywel Williams. They will join the Centre for Doctoral Training in Environmental Intelligence, a 4-year programme offering training in AI, data science, environmental challenges, responsible innovation and data governance/ethics. They will also join the new UKRI AI Hub on “AI for Collective Intelligence”, a major investment to understand how complex systems of humans and artificial agents can effectively combine. At Exeter, the students will join a thriving research group with other students and postdoctoral researchers working on related problems.

This PhD project will suit students with a strong technical background in computer science, mathematics, physics or a similar discipline. It will also require scientific curiosity and willingness to engage in interdisciplinary study. Motivation to solve environmental problems is an important factor. Interested candidates are encouraged to contact Prof Hywel Williams on h.t.p.williams@exeter.ac.uk if they have any queries.

International applicants need to be aware that you will have to cover the cost of your student visa, healthcare surcharge and other costs of moving to the UK to do a PhD.

For further information and to apply please click here