18 papers in the archive.
Systematic study of design choices for DL weather models finds fixed-grid architectures beat grid-invariant ones, proposes a hybrid, and shows multi-step fine-tuning is essential.
Software, scaling & compressionNVIDIAUniversity of Cambridge (Aardvark)
Aurora is a large Earth-system foundation model trained on over a million hours of data that beats operational systems for air quality, waves, cyclone tracks and high-resolution weather.
Foundation modelsThe Alan Turing InstituteMicrosoft Research (AI for Science)Silurian AIUniversity of Cambridge (Aardvark)
End-to-end model ingests raw observations to produce global and station forecasts, beating operational NWP on several variables using 8% of input data.
Data assimilationThe Alan Turing InstituteECMWFGoogle DeepMindMicrosoft Research (AI for Science)University of Cambridge (Aardvark)
Sim2Real pre-trains a ConvCNP on reanalysis and fine-tunes on German weather stations, outperforming reanalysis-only or station-only training for surface air temperature interpolation.
Observations & remote sensingMicrosoft Research (AI for Science)University of Cambridge (Aardvark)
Review of deep learning solar forecasting from sky cameras, satellites and weather stations that tracks cloud displacement, outlining gaps relative to NWP.
Applications & impactsUniversity of Cambridge (Aardvark)Stanford University
A probabilistic CNN-BiLSTM with multi-head attention forecasts day-ahead wind speed for energy use; the abstract was unavailable, so the claim is limited.
Local & station forecastingUniversity of Cambridge (Aardvark)
Gaussian mixture modelling classifies UKESM1 CMIP6 ozone profiles into six coherent global regimes, with future projections showing ozone hole recovery and lower tropospheric ozone.
Climate analysis & attributionUniversity of Cambridge (Aardvark)
Combines sky images and satellite observations in one ML framework for deterministic and probabilistic intra-hour solar irradiance nowcasts up to 60 minutes ahead.
Transfer learning from unused high-resolution data improves machine-learnt emulators of chaotic systems, giving better stability, generalisation and forecast skill for climate-model emulation.
Machine learning attributes aerosol climate forcing largely to increased cloud cover. Abstract unavailable; judged from the title only.
Climate analysis & attributionNASAMet OfficeETH ZurichUniversity of Cambridge (Aardvark)
A probabilistic physically informed recurrent network learns stochastic parameterizations in the Lorenz 96 atmosphere model, outperforming autoregressive and GAN baselines on temporal patterns.
Hybrid physics-ML & parameterizationThe Alan Turing InstituteUniversity of Cambridge (Aardvark)University of Oxford
Convolutional conditional neural processes provide off-grid multisite temperature and precipitation downscaling over Europe, beating existing methods and improving extreme precipitation representation.
Downscaling & super-resolutionThe Alan Turing InstituteUniversity of Cambridge (Aardvark)
Uses a Bayesian neural network to fuse chemistry-climate model output with sparse satellite and sonde data, producing a continuous vertically resolved stratospheric ozone record with uncertainty.
Observations & remote sensingUniversity of Cambridge (Aardvark)The Alan Turing Institute
Ridge, Lasso, random forest and extra trees emulate UKESM1 tropical stratospheric ozone projections under SSPs, matching the model when trained on future simulations.
Climate emulationMet OfficeUniversity of Cambridge (Aardvark)
Statistical emulator GCMET reconstructs global climate over the last 800,000 years at high spatial detail, revealing stable habitat refugia.
Ordinal neural network refines a persistence baseline to predict airport low visibility, outperforming persistence and autoregressive models at longer horizons on station data.
Local & station forecastingUniversity of Cambridge (Aardvark)
Statistical emulators trained on 30 GCM runs map eruption parameters to volcanic aerosol forcing, producing response surfaces for thousands of eruptions.
Linear ML regression predicts 3D ozone from temperature alone, improving stratospheric ozone variability over fixed climatology for preindustrial and 4xCO2 climate sensitivity runs.
Hybrid physics-ML & parameterizationUniversity of Cambridge (Aardvark)Karlsruhe Institute of Technology (KIT)
