37 papers in the archive.
Review of ML for climate physics and climate simulations, arguing physics knowledge and interpretability are essential in the small-data, non-stationary regime of long-term climate projection.
Hybrid physics-ML & parameterizationMassachusetts Institute of Technology (MIT)Stanford UniversityUniversity of Chicago
NeuralGCM couples a differentiable dynamical solver with ML components, matching ML and ECMWF ensemble skill for 1-15 day forecasts and stable multi-decade climate runs.
Hybrid physics-ML & parameterizationECMWFGoogle DeepMindGoogle ResearchMassachusetts Institute of Technology (MIT)
Nature Climate Change perspective on combining AI and computing for climate modelling and prediction; abstract absent, judged from title and venue.
Hybrid physics-ML & parameterizationCalifornia Institute of Technology (Caltech)Massachusetts Institute of Technology (MIT)NSF NCAR / UCARPrinceton University
Position paper on Earth Virtualization Engines that pair high-resolution physics-based climate models with machine learning and federated access to exabyte-scale climate data.
Software, scaling & compressionCSCS - Swiss National Supercomputing CentreETH ZurichMeteoSwissMassachusetts Institute of Technology (MIT)Max Planck Institute for MeteorologyNSF NCAR / UCARNVIDIAUniversity of Reading
Reviews physics-informed and data-driven visual anemometry, inferring local wind from the motion of trees and flags for renewable energy and urban applications.
Observations & remote sensingMassachusetts Institute of Technology (MIT)California Institute of Technology (Caltech)
Machine-learned correction operator, trained on nudged coarse E3SM runs against ERA5, makes free-running climate statistics and extreme-event frequencies resemble observations.
Climate emulationMassachusetts Institute of Technology (MIT)
A neural-network subgrid momentum parameterization trained on high-resolution aquaplanet output conserves momentum and gives stable coarse-model runs with reduced wind biases.
Hybrid physics-ML & parameterizationMassachusetts Institute of Technology (MIT)
Gradient-boosted models forecast short-term local wind for a Moroccan chemical plant, cutting errors 38-52% versus official forecasts and enabling pollution-aware production decisions.
Applications & impactsMassachusetts Institute of Technology (MIT)
Neural networks forecast Nigerian weather parameters from 19 years of NASA data to assess solar PV siting, reaching 96% training correlation.
Local & station forecastingMassachusetts Institute of Technology (MIT)University of Oklahoma (AI2ES)
A 3D deep neural network sharpens AIRS/AMSU temperature and humidity retrievals, better capturing planetary boundary layer top inversions and improving PBL height estimates.
Observations & remote sensingNASAMassachusetts Institute of Technology (MIT)
Linear and random forest models forecast central European summer heatwaves 1–6 weeks ahead, matching ECMWF hindcast ensemble mean beyond two weeks lead.
Sub-seasonal to seasonalETH ZurichMassachusetts Institute of Technology (MIT)
A physics-statistical GAN downscales 0.25° climate model rainfall to 0.01° fields, quantifying uncertainty and matching observed extreme rainfall distributions.
Downscaling & super-resolutionMassachusetts Institute of Technology (MIT)
A U-Net emulates the WSR-88D operational velocity dealiasing algorithm, giving accurate, fast radar dealiasing that ports to other radar systems.
Observations & remote sensingMassachusetts Institute of Technology (MIT)
Multi-resolution deep learning debiases GCM tail statistics against reanalysis and reconstructs finer scales, producing realistic Western European weather-extreme realizations for risk assessment.
Downscaling & super-resolutionMassachusetts Institute of Technology (MIT)
Machine-learning adaptive bias correction of ECMWF subseasonal forecasts raises contiguous-US temperature skill 60-90% and precipitation skill 40-69%.
Post-processing & calibrationMicrosoft Research (AI for Science)Massachusetts Institute of Technology (MIT)
An ensemble-based algorithm targets data acquisition to regions and times that most reduce parametric uncertainty in a GCM convection scheme, within calibrate-emulate-sample.
Explainability, uncertainty & physicsMassachusetts Institute of Technology (MIT)California Institute of Technology (Caltech)
Hybrid multiscale neural operator learns grid-independent closure parameterizations for coarse dynamics, demonstrated on the chaotic multiscale Lorenz96 model.
Hybrid physics-ML & parameterizationIBM ResearchMassachusetts Institute of Technology (MIT)
Neural networks trained on SMAP soil moisture project Southeast Asian peat drying under RCP8.5, finding decreases about half as strong as recent El Niño droughts.
Applications & impactsMassachusetts Institute of Technology (MIT)NASAStanford University
Compares shallow supervised learners for 10 m wind speed forecasting at 32 Italian anemometer sites, finding well-designed shallow models competitive with deep networks.
Local & station forecastingMassachusetts Institute of Technology (MIT)
Calibrating a convection parameterization with seasonally averaged statistics cuts calibration error up to tenfold and narrows posterior spread by two to five times in an idealized GCM.
Explainability, uncertainty & physicsCalifornia Institute of Technology (Caltech)Massachusetts Institute of Technology (MIT)
An ensemble-based experimental design algorithm, using calibrate-emulate-sample, chooses high-resolution simulation regions that most reduce uncertainty in GCM convection parameters, with 10^2 rather than 10^5 model runs.
Explainability, uncertainty & physicsMassachusetts Institute of Technology (MIT)California Institute of Technology (Caltech)
Neural-network subgrid parameterizations using non-local 3x3-column inputs improve offline skill, especially for momentum transport, with vertical velocity or divergence as key inputs.
Hybrid physics-ML & parameterizationMassachusetts Institute of Technology (MIT)
Climate-invariant ML embeds physical knowledge into parameterization emulators so they generalize across climate regimes, maintaining offline accuracy in three atmospheric models.
Explainability, uncertainty & physicsColumbia University (LEAP, Lamont-Doherty)Google ResearchMassachusetts Institute of Technology (MIT)NVIDIAUniversity of California, Los Angeles (UCLA)
Multiple machine learning models predict Atlantic Multidecadal Variability from North Atlantic SST, salinity and sea level pressure maps, beating persistence in CESM-LE.
Sub-seasonal to seasonalMassachusetts Institute of Technology (MIT)
Benchmarks ESRGAN, EDSR and PhIREGAN for super-resolving NWP wind and solar fields, and releases an ML-ready dataset for renewable forecasting.
Downscaling & super-resolutionMassachusetts Institute of Technology (MIT)California Institute of Technology (Caltech)University of California, Berkeley
A neural network on MODIS brightness temperatures detects Atacama Desert fog better than a cloud-height method (Heidke skill 0.56 vs 0.49), enabling a fog frequency climatology.
Observations & remote sensingMassachusetts Institute of Technology (MIT)
A data-driven stochastic framework reconstructs small-scale features in climate data sets; no abstract was provided, so impact is hard to assess.
Downscaling & super-resolutionMassachusetts Institute of Technology (MIT)
Compares CNNs with analogue methods for predicting US regional extreme precipitation from large-scale patterns, finding CNNs more skillful and integrated vapor transport the most predictive variable.
Extremes & hazardsMassachusetts Institute of Technology (MIT)
Recurrent neural networks generate localized synthetic weather data from airport and on-site measurements, improving test accuracy over standard weather files by over 100%.
Local & station forecastingMassachusetts Institute of Technology (MIT)
Hurricast combines encoder-decoder features with gradient-boosted trees for 24-hour tropical cyclone track and intensity, matching operational skill in seconds and improving NHC consensus.
Extremes & hazardsMassachusetts Institute of Technology (MIT)
Physically constrained neural network subgrid parameterization trained on high-resolution simulations stays stable in coupled runs and tolerates reduced numerical precision.
Hybrid physics-ML & parameterizationMassachusetts Institute of Technology (MIT)
Gaussian process parameter estimation for the Lorenz-96 climate benchmark outperforms deep learning and linear regression under small-data constraints, with uncertainty quantification.
Hybrid physics-ML & parameterizationMassachusetts Institute of Technology (MIT)
A random forest subgrid parameterization learned from 3D high-resolution output yields stable coarse-resolution climate simulations that reproduce precipitation extremes.
Hybrid physics-ML & parameterizationMassachusetts Institute of Technology (MIT)
Position paper surveying how machine learning can help climate change mitigation and adaptation across sectors such as energy and disaster management; not focused on weather or climate science.
Applications & impactsETH ZurichGoogle DeepMindGoogle ResearchLawrence Berkeley National Laboratory / NERSCMassachusetts Institute of Technology (MIT)New York University (M2LInES)Stanford UniversityUniversity of California, Berkeley
Opinion article arguing machine learning should be adopted for S2S forecasting, showing statistical methods beat dynamical models on a polar vortex case.
Sub-seasonal to seasonalMicrosoft Research (AI for Science)Massachusetts Institute of Technology (MIT)Potsdam Institute for Climate Impact Research (PIK)Stanford University
A random forest moist convection parameterization trained on high-resolution output runs stably in a GCM, capturing precipitation extremes and climate change when trained on warm-climate samples.
Hybrid physics-ML & parameterizationMassachusetts Institute of Technology (MIT)
Neural network parameterizations of typhoon-induced sea surface cooling reduce maximum wind intensity errors by 60–70% in four atmosphere-only typhoon forecast cases.
Hybrid physics-ML & parameterizationMassachusetts Institute of Technology (MIT)China Meteorological Administration (CMA)
