S. Bouabid, D. Sejdinovic and D. Watson-Parris
Preprint. Under review.
Emulators, or reduced complexity climate models, are surrogate Earth system models that produce projections of key climate quantities with minimal computational resources. Using time-series modelling or more advanced machine learning techniques data-driven emulators have emerged […] Read more
S. Bouabid*, J. Fawkes*, and D. Sejdinovic
Published in International Conference on Machine Learning, 2023
A directed acyclic graph (DAG) provides valuable prior knowledge that is often discarded in regression tasks in machine learning. We show that the independences arising from the presence of collider structures in DAGs provide meaningful inductive biases, […] Read more
D. Watson-Parris, Y. Rao, D. Olivié, Ø. Seland, P. Nowack, G. Camp-Valls, P. Stier, S. Bouabid, M. Dewey, E. Fons, J. Gonzalez, P. Harder, K. Jeggle, J. Lenhardt, P. Manshausen, M. Novitasari, L. Ricard, C. Roesch
Published in Journal of Advances in Modeling Earth Systems, 2022
Many different emission pathways exist that are compatible with the Paris climate agreement, and many more are possible that miss that target. While some of the most complex Earth System Models have simulated a small selection of Shared Socioeconomic Pathways, […] Read more
S. Bouabid, D. Watson-Parris, S. Stefanovic, A. Nenes, and D. Sejdinovic
Preprint. Under review.
Aerosol-cloud interactions constitute the largest source of uncertainty in assessments of the anthropogenic climate change. This uncertainty arises in part from the difficulty in measuring the vertical distributions of aerosols, and only sporadic vertically resolved observations are available […] Read more
S. L. Chau*, S. Bouabid*, and D. Sejdinovic
Published in Advances in Neural Information Processing Systems, 2021
Refining low-resolution (LR) spatial fields with high-resolution (HR) information, often known as statistical downscaling, is challenging as the diversity of spatial datasets often prevents direct matching of observations […] Read more