Yue Han, Zhihua Zhang, M. James C. Crabbe
· Big Earth Data
·
A hybrid RBF network downscales sparse station data into high-resolution precipitation, temperature and humidity maps for Bangladesh, outperforming MLR and kriging.
Emily Vosper, Peter A. G. Watson, Lucy Harris et al.
· Journal of Geophysical Research Atmospheres
·
A Wasserstein GAN downscales tropical cyclone rainfall from about 100 km to 10 km, reproducing spatial structure and spectra with mean bias within 5% and extrapolating to extreme storms.
Timothy B. Higgins, Aneesh C. Subramanian, Andre Graubner et al.
· Journal of Advances in Modeling Earth Systems
·
A deep learning atmospheric river tracker is applied to a high-resolution large-ensemble climate dataset and checked for consistency against established algorithms over the US West Coast.
Zied Ben Bouallègue, Fenwick Cooper, Matthew Chantry et al.
· Monthly Weather Review
·
Linear regression, random forests and neural networks correct ECMWF IFS 2 m temperature and 10 m wind errors, improving RMSE by 10–15% with uncertainty estimates.
James Carzon, Bruno Ricardi de Abreu, Leighton A. Regayre et al.
· Environmental Data Science
·
Surrogate-based statistical framework constrains UKESM1 aerosol parameters against MODIS observations on a cloud platform, using 3-hourly outputs for tighter constraints.
Maëlys Solal, Andrew Jesson, Yarin Gal et al.
· arXiv
·
Causal machine learning on satellite observations estimates aerosol-cloud interaction with uncertainty bounds, finding only one of three climate models reproduces the cooling trend.
Random forest and boosting models estimate pre-industrial cloudiness, suggesting aerosols increased global cloud fraction by 1.27% with about -0.42 W/m2 cooling.
Antoine P. Delaunay, Hannah M. Christensen
· Geophysical Research Letters
·
A CNN gives skilful probabilistic MJO forecasts whose uncertainty tracks instantaneous predictability, using predicted standard deviation and Monte Carlo dropout.
Lucy Harris, Andrew T. T. McRae, Matthew Chantry et al.
· Journal of Advances in Modeling Earth Systems
·
GAN and VAE-GAN downscale low-resolution forecasts to radar-scale precipitation maps with CRPS matching state-of-the-art pointwise post-processing, including heavy rain.
Raghul Parthipan, Hannah M. Christensen, J. Scott Hosking et al.
· Geoscientific model development
·
A probabilistic physically informed recurrent network learns stochastic parameterizations in the Lorenz 96 atmosphere model, outperforming autoregressive and GAN baselines on temporal patterns.
CorrectorGAN jointly bias-corrects and super-resolves global ensemble precipitation forecasts over the US against radar, approaching an operational regional model in seconds.
Duncan Watson-Parris, Andrew Williams, Lucia Deaconu et al.
· Geosci. Model Dev. 14 (2021) 7659-7672
·
ESEm, an open-source Gaussian-process emulation and calibration toolkit, reduces parametric uncertainty in a GCM and explores CMIP6 scenario uncertainty.
Andrew Gettelman, David John Gagne, Chih‐Chieh Chen et al.
· Journal of Advances in Modeling Earth Systems
·
Neural-network emulators replace bin-microphysics warm-rain processes in a GCM, reproducing its climate behaviour at the control run's computational cost.
Matthew Chantry, Sam Hatfield, Peter Duben et al.
· Journal of Advances in Modeling Earth Systems
·
Neural emulators of the non-orographic gravity wave drag scheme run stably to seasonal timescales, improve medium-range forecasts and run ten times faster on GPUs than the CPU scheme.
Christian Schroeder de Witt, Catherine Tong, Valentina Zantedeschi et al.
· arXiv
·
RainBench is a multimodal global benchmark combining simulated satellite data, ERA5 and IMERG precipitation, with the PyRain library and medium-range baselines.
Jan Ackmann, Peter D. Düben, Tim N. Palmer et al.
· arXiv
·
Machine-learned preconditioners for the semi-implicit linear solver in a shallow-water model are competitive with conventional preconditioners and generalize beyond the training range.
Dr. Richard Hughes
· American Journal of Data Science and Analysis
·
Review of big data and machine learning for climate change modeling using satellite, sensor and climate model data, covering challenges and outlook without new methods.
Duncan Watson-Parris
· Phil. Trans. R. Soc. A. 379 (2021) 20200098
·
Position review arguing climate emulation with machine learning differs from weather forecasting, since climate is a boundary-condition problem with steady-state emulation opportunities.
Chris Huntingford, Elizabeth S. Jeffers, Michael B. Bonsall et al.
· Environmental Research Letters
·
Perspective arguing that machine learning should mine existing climate data and simulations for teleconnections and warnings, not only improve Earth system models.
Valentina Zantedeschi, Fabrizio Falasca, Alyson Douglas et al.
· Tackling Climate Change with Machine Learning Workshop, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada
·
Cumulo is a global dataset pairing one year of 1km MODIS imagery with CloudSat cloud labels, with a flow-based baseline for cloud classification.
David John Gagne, Hannah M. Christensen, Aneesh C. Subramanian et al.
· Journal of Advances in Modeling Earth Systems
·
Trains a GAN as a stochastic sub-grid parameterization for the Lorenz '96 model; some configurations beat a bespoke scheme at weather and climate timescales.
Peter A. G. Watson
· Journal of Advances in Modeling Earth Systems
·
ML learns timestep-by-timestep error corrections to a physical model; tested on Lorenz-96, it gives stable runs, better initialised skill and improved long-term statistics.
