49 papers in the archive · tier-1 watchlist.
GeoCryoAI, a CNN-RNN hybrid, models Alaskan permafrost active layer thickness and CO2/CH4 fluxes, with a 1.327 cm ALT RMSE over 1969–2022.
Climate analysis & attributionNASACalifornia Institute of Technology (Caltech)
An adversarially trained deep learning parameterization of subgrid vertical wind variability reproduces observed statistics and can run online in large-scale atmospheric models.
Review and perspective arguing that transformer-based weather and climate foundation models are mature enough to build, outlining criteria for downscaling, wildfire and hurricane tasks.
Foundation modelsIBM ResearchKarlsruhe Institute of Technology (KIT)NASA
Neural networks with explainable AI identify decadal variability in tropically driven subseasonal precipitation skill in CESM2 and confirm the relationships in ERA5 reanalysis.
Sub-seasonal to seasonalNASANSF NCAR / UCARColorado State University (incl. CIRA)
A deep neural network combining GOES cloud-top satellite data with reanalysis parameters estimates severe hail likelihood, reaching CSI 0.511 against radar MESH.
Interpretable non-linear ML bias correction removes 3D cloud artifacts from OCO-2 XCO2, cutting unphysical variability by 31% over land and 55% over ocean.
Observations & remote sensingNASACalifornia Institute of Technology (Caltech)
Curates an hourly-interpolated satellite image and wind-speed dataset for tropical cyclones, plus a community competition whose winners improved on the benchmark by about 50%.
Customized deep learning with weighted losses, multitask learning and covariates improves hourly precipitation bias correction and downscaling, better capturing extremes than quantile mapping.
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)
A physics-informed CloudMask loss improves deep networks that reconstruct 3D multilayer cloud masks from 2D satellite imagery over binary cross-entropy.
Deep neural network retrieves cloud fraction from CrIS infrared sounder observations; abstract unavailable, so scope is inferred from the title.
Random forest trained on GFS forecasts and radiometer data predicts zenith atmospheric noise temperature at NASA Deep Space Network sites, enabling up to 2.43 dB downlink gain.
Applications & impactsNASACalifornia Institute of Technology (Caltech)University of California, Los Angeles (UCLA)
Unsupervised ML on tree-ring PDSI drought atlases finds outlier drought patterns in 80% of 21st-century years, showing unusual hydroclimate states.
Climate analysis & attributionNASAColumbia University (LEAP, Lamont-Doherty)
Random forest surrogate for particle number concentration in GISS-ModelE2.1 reduces aerosol-cloud radiative forcing from -1.46 to -1.11 W m-2.
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)
Gradient-free Kalman inversion trains hybrid subgrid turbulence and convection parameterizations from large-eddy simulation data, with uncertainty estimates from unscented Kalman inversion.
Hybrid physics-ML & parameterizationNASACalifornia Institute of Technology (Caltech)
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
Neural networks emulate a non-orographic gravity wave drag scheme and generalize to reproduce the QBO and the climate response to increased CO2 when coupled online.
Hybrid physics-ML & parameterizationNASAStanford UniversityNew York University (M2LInES)
Trains a neural network on Viking and Mars Science Laboratory measurements to predict next-day Martian temperature and pressure within 0.5 to 1% accuracy.
Saliency-map explainable deep learning on global SST reveals ENSO-related information beyond indices and improves river flow prediction with uncertainty estimates.
A CNN fuses LEO and geostationary satellite data into 2 km, 10-minute land surface temperature, with 1.73 K mean absolute error against LEO targets.
A neural network using a microwave rain index and 24 h wind changes identifies tropical cyclone rapid intensification with near-perfect skill and reveals environmental drivers up to 1050 km away.
Extremes & hazardsNASACalifornia Institute of Technology (Caltech)
XGBoost with SHAP predicts and explains NASA GEOS lightning-occurrence errors, linking them to convection and land-surface characteristics.
Global planetary boundary layer height retrieved from ICESat-2 and CATS lidar using a threshold method and a CNN, validated against MERRA-2 with good spatial agreement.
ML trained on a large climate model ensemble yields seasonal precipitation forecasts over the western US competitive with NMME dynamical models.
Sub-seasonal to seasonalCalifornia Institute of Technology (Caltech)NASA
Neural-network retrieval VACOS uses MSG/SEVIRI thermal channels and ECMWF profiles to detect volcanic ash and retrieve cloud-top height and particle radius, day and night.
Random forest combined with Gaussian mixture clustering characterizes bias and standard error of water vapour atmospheric motion vectors, addressing a known gap in uncertainty estimation.
Observations & remote sensingNASACalifornia Institute of Technology (Caltech)
Random forests combining GOES-16 satellite, lightning and radar fields improve severe storm warning prediction over radar alone, identifying cloud-top divergence as most informative.
NowcastingNASAColorado State University (incl. CIRA)University of Oklahoma (AI2ES)
A UNet segments airborne dust at night from GOES-16 infrared bands, aiming to support dust storm warnings for forecasters.
PDIR-Now provides hourly quasi-global infrared-based precipitation at 0.04° with 15-60 min latency, improving the critical success index to 0.53 from 0.47 over PERSIANN-CCS.
A DNN trained on principal components of CrIS hyperspectral spectra, with VIIRS cloud masks as truth, detects cloudy fields of view with 93% accuracy.
XGBoost corrects MAIAC satellite column water vapor errors, cutting RMSE by 26.9% for Terra and 16.5% for Aqua against AERONET sites.
Machine learning using satellite inner-core precipitation and outflow temperature beats the NHC operational rapid-intensification consensus, improving Peirce skill score by 12 to 138%.
Extremes & hazardsIBM ResearchNASACalifornia Institute of Technology (Caltech)
Compares six ML algorithms for county-level maize yield prediction and finds XGBoost best; the target is crop yield rather than the atmosphere.
Artificial neural networks classify 500 hPa circulation patterns, showing the 2019 Greenland melt season was about five standard deviations anomalous in atmospheric persistence.
Climate analysis & attributionNASAColumbia University (LEAP, Lamont-Doherty)
PreciPatch uses dictionary learning to downscale hourly GCM precipitation, outperforming bicubic, RainFARM and DeepSD on IMERG data.
Convcast, a convolutional LSTM trained on NASA IMERG satellite precipitation, nowcasts up to 150 minutes with 0.805 mm/h RMSE at 30 minutes, outperforming optical flow.
Fuzzy-logic ALPHA algorithm fuses satellite, NWP and radar data to detect high ice water content for aviation, with AUC 0.85 against in situ measurements.
Observations & remote sensingNASANSF NCAR / UCARBureau of Meteorology (Australia)
DeepCTC neural network classifies cloud types from GOES-16 ABI imagery using CloudSat labels and evaluates PERSIANN-CCS precipitation by cloud type against MRMS.
Web-based Image Labeler tool speeds labeling of Earth science images, such as hurricane imagery, to build shareable datasets for deep learning.
Deep learning emulates a satellite remote-sensing surrogate model, reproducing its outputs with acceptable accuracy and often faster runtime than the surrogate.
Information-flow analysis of FLUXNET eddy-covariance sites with a neural network maps global land-atmosphere coupling, revealing hotspots and aridity dependence.
Describes a deep-learning portal for estimating tropical cyclone intensity; no abstract is available, so the detail is limited.
A conditional GAN reconstructs CloudSat-style cloud vertical structure from MODIS inputs, capturing multilayer clouds and providing uncertainty estimates.
Observations & remote sensingCalifornia Institute of Technology (Caltech)NASA
Deep learning model estimates tropical cyclone intensity from satellite data at higher temporal frequency, deployed in a production monitoring system with a portal.
A deep neural network retrieves high-latitude rain and snow from GMI and MODIS data, largely outperforming GPROF on snowfall and reducing rain underestimation.
Observations & remote sensingNASACalifornia Institute of Technology (Caltech)Tsinghua University (NowcastNet)University of California, Los Angeles (UCLA)University of Oklahoma (AI2ES)
Deep CNNs estimate tropical cyclone intensity directly from infrared satellite imagery as an objective alternative to subjective Dvorak analysis.
A blueprint proposes Earth system models that learn parameterizations from observations and high-resolution simulations via data assimilation and machine learning, illustrated on a toy system.
Hybrid physics-ML & parameterizationCalifornia Institute of Technology (Caltech)NASA
DeepSD applies a multi-scale stacked super-resolution CNN to downscale daily precipitation from 1 degree to 1/8 degree over the continental US for climate projections.
