24 papers in the archive · tier-1 watchlist.
FuXi Weather is an ML system that assimilates multi-satellite observations and produces 10-day global forecasts, outperforming ECMWF HRES in observation-sparse regions like central Africa.
Data assimilationChina Meteorological Administration (CMA)Fudan University (FuXi)Nanjing University of Information Science & Technology (NUIST)Tsinghua University (NowcastNet)University of California, Los Angeles (UCLA)
FuXi-ENS, a VAE-based ensemble trained with CRPS and KL loss at 0.25°, beats ECMWF ENS in CRPS on 98.1% of 360 variable and lead time combinations.
Probabilistic & ensemble forecastingChina Meteorological Administration (CMA)Fudan University (FuXi)Nanjing University of Information Science & Technology (NUIST)
FuXi-DA is a deep learning data assimilation framework that assimilates FY-4B AGRI satellite radiances, reducing analysis errors and improving forecasts.
Data assimilationChina Meteorological Administration (CMA)Fudan University (FuXi)Nanjing University of Information Science & Technology (NUIST)
Adas is an AI data assimilation model that, combined with FengWu, forms an end-to-end AI forecast system with skill comparable to IFS.
Data assimilationFudan University (FuXi)Nanjing University of Information Science & Technology (NUIST)Shanghai Artificial Intelligence Laboratory
Machine learning S2S model outperforms ECMWF's S2S system for precipitation and OLR up to 42 days, extending MJO prediction skill from 30 to 36 days.
Sub-seasonal to seasonalChina Meteorological Administration (CMA)Fudan University (FuXi)
A denoising diffusion model restores fine-scale detail in FuXi 5-day forecasts, improving extreme precipitation and wind over HRES, but not TC intensity.
SwinIR and Uformer transformers downscale and bias-correct ECMWF HRES 2 m temperature and 10 m wind to 0.01°, outperforming UNet and RCAN baselines.
Downscaling & super-resolutionFudan University (FuXi)Alibaba (DAMO Academy)
Explainable CNN on 1200-year simulations attributes North China summer precipitation variability to PDO and AMO sea surface temperature patterns, with 96-98% accuracy.
Climate analysis & attributionFudan University (FuXi)Institute of Atmospheric Physics, Chinese Academy of Sciences
FuXi is a cascaded ML system giving 15-day global forecasts at 0.25 degrees, the first ML model to match the ECMWF ensemble mean at 15 days.
Neural network sub-grid cloud fraction scheme trained on CloudSat data reaches r > 0.9 and reduces high- and low-level cloud biases in GCM simulations.
Hybrid physics-ML & parameterizationFudan University (FuXi)Nanjing University of Information Science & Technology (NUIST)
Mutual-information reweighting and time-superimposing training improve radar precipitation nowcasts for convective scenarios across several state-of-the-art models.
Deep learning reconstructs monthly surface air temperature over the Tibetan Plateau for 1901–2020, filling gaps in the historical station record.
A 3D DBSCAN clustering workflow detects the 2022 Yangtze heatwave and drought from ERA5 and tests how clustering parameters change event tracking.
Extremes & hazardsFudan University (FuXi)China Meteorological Administration (CMA)
SwinVRNN learns VAE-based distribution perturbations within a Swin transformer recurrent model, giving better ensemble accuracy and spread than other perturbation methods on WeatherBench.
Probabilistic & ensemble forecastingAlibaba (DAMO Academy)Fudan University (FuXi)
A deep neural network corrects bias in daily satellite precipitation estimates over tropical regions, using ground observations as the reference.
A 3D CNN from one meteorology frame predicts daily CONUS precipitation, beating operational weather models up to 5-day leads and improving them when combined.
LightNet+ fuses radar, station and NWP data in a deep network for lightning forecasting, beating three established schemes and improving as data sources are added.
Extremes & hazardsFudan University (FuXi)China Meteorological Administration (CMA)
An end-to-end spatiotemporal scale-selection model improves ECMWF precipitation bias correction, especially for heavy rain, beating 11 published methods on two benchmarks.
An ordinal distribution autoencoder corrects ECMWF and SMS-WARMS precipitation forecast bias and outperforms classical ML and deep baselines.
MeteCNN classifies 11 weather phenomena in a new 6,877-image dataset, reaching about 92% test accuracy.
Observations & remote sensingFudan University (FuXi)Nanjing University of Information Science & Technology (NUIST)
ConvLSTM with star-shape bridge and rain-oriented loss improves radar precipitation nowcasting over convolutional LSTM baselines and extrapolation.
Hybrid CNN with classification and BP network estimates tropical cyclone intensity from satellite images with RMSE of 8.91 kt.
Extremes & hazardsFudan University (FuXi)Nanjing University of Information Science & Technology (NUIST)
Expert-free denoising autoencoder with ordinal regression corrects ECMWF precipitation forecasts, outperforming classical ML and deep baselines on threat scores.
EEMD-decomposed ConvLSTM forecasts the NAO index and outperforms six benchmarks and NOAA GFS and MRF ensemble-mean forecasts in the reported tests.
