Large datasets from both observations and complex numerical models offer an unprecedented opportunity to explore our environment.
LIDA: environment aims to support researchers in developing and implementing data-driven techniques to better understand our environment.
What we do
– organise monthly workshops for researchers at Leeds on scientific machine learning, often with an environmental focus
– coordinate schemes such as travel bursaries and visiting programmes to promote engagement
– discuss and produce new training materials to make machine learning methods more accessible to real world research problems
The SciML community is fostering collaboration and knowledge-sharing between researchers carrying out research in studying for example iceberg dynamics, air-quality prediction, crop yield and resilience, aerosol interactions and climate-impacts of convective clouds, and ground-water flows. To make predictions and understand processes in these physical applications we are utilising both supervised, self-supervised and un-supervised learning, utilising techniques such as deep convolutional networks, generative neural networks, Gaussian processes, reservoir computing, SINDy, physics-informed neural networks (PINN) and random forests. We have active collaboration with people developing machine learning techniques in the Department of Computer Science at Leeds, nationally through the Alan Turing Institute and British Antarctic Survey and internationally through the Frontiers Development Lab and European Space Agency. With the establishment of the Environment Theme within LIDA we aim to foster further collaborations between colleagues within Leeds and to the wider research community.