We develop statistical modelling techniques to correct forecast biases in numerical weather and climate models.

We develop statistical tools to evaluate the skill and reliability of weather and climate forecasts

We develop statistical methodology for calibrating computer simulation models, using statistical emulators that can be evaluated quickly in place of the expensive computer model.

We develop flexible statistical tools to approximate the output of complex systems, to efficiently explore the possible behaviors of the model and propagate uncertainties from model inputs to the final predictions.

We combine large amounts of data from different sources (satellites, station measurements, indirect predictors) to estimate air pollution at high spatial and temporal resolutions.

We combine large amounts of data from different sources (satellites, station measurements, indirect predictors) to estimate air pollution at high spatial and temporal resolutions

We develop disease risk prediction models, incorporating environmental factors and climate information, to assist in public health decision making.