Back to research

AI for research and innovation

Overview

By analysing complex datasets and uncovering previously unknown patterns, machine learning has the potential to accelerate scientific discovery across the sciences – from healthcare to climate science, fundamental physics to conservation, and more. Realising this potential requires action to equip researchers from across disciplines with the skills they need to use machine learning in their work, and to build a community of practice at the interface of data science and other disciplines.

How can AI enhance scientific discovery?

Activities in this theme advance research, training, and engagement at the interface of AI and the sciences.

Current areas of research interest include:

innovations in Gaussian Processes, dimensionality reduction techniques and their application to challenges in the life sciences;
the application of ideas from physics and applied mathematics to develop robust sampling methods;
the development of computational methods for interrogating the relationship between cellular morphology and genomics;
the application of data science approaches to better understand mental health conditions, including machine learning, network science and NLP;
theoretical machine learning to understand String Theory;
innovations in modelling and software engineering to support increased accuracy in climate predictions.

Projects

Human Cell Atlas

The Human Cell Atlas programme aims to chart the properties of human cells, building a reference map of the human body that can be used to understand human health and to treat disease.

Accelerate Science

Artificial intelligence (AI) has the potential to become an engine for scientific discovery across disciplines – from predicting the impact of climate change, to using genetic data to create new healthcare treatments, and from finding new astronomical phenomena to identifying new materials here on Earth.

Climate Ensembling

General Circulation Models (GCMs) of Earth's climate provide robust simulations of large-scale average climatic variables, such as end-of-century global average temperature, under various future greenhouse gas emissions scenarios. Translating these outputs to insights that can be used to manage the local-level impacts of climate change is challenging, and requires innovations in modelling, data management, and software engineering.