8 papers in the archive · tier-1 watchlist.
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
Modular neural network encodes uncertain seasonal climate forecasts for supply-chain demand forecasting, reducing error by 13% to 17% versus existing methods.
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)
GAN with sub-pixel convolution performs 8x super-resolution of ERA5 temperature fields, improving RMSE 37% over bicubic interpolation.
Downscaling & super-resolutionIBM ResearchNanjing University of Information Science & Technology (NUIST)
Random forest quantile regression and Bayesian LSTM surrogates emulate a malaria transmission model driven by seasonal temperature and rainfall ensembles, cutting computation while capturing forecast uncertainty.
Temporal Fusion Transformer forecasts weekly extreme precipitation quantiles up to six months ahead, beating calibrated SEAS5 at six-month lead and modestly beating climatology.
CNN and RNN models forecast 2 m temperature out to 52 weeks at six locations, beating climatology up to 30 weeks for correlation, but only at select 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)
