- Predictive Models
- Generative Models
- Foundation Models
- Multi-modal Weather Models
- Distillation for Climate & Weather
- Agentic Models for Climate & Weather
- Applications
Taxonomy:
Representative review:
- (FourCastNet 3) FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale
arXiv 2025
[Paper] [Code]
-
(FourCastNet) FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
arXiv 2022
[Paper] [Code] -
(FuXi) FuXi: a cascade machine learning forecasting system for 15-day global weather forecast
npj Climate and Atmospheric Science 2023
[Paper] [Code] -
(FengWu) FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead
arXiv 2023
[Paper] [Code] -
(FengWu-4DVar) FengWu-4DVar: Coupling the Data-driven Weather Forecasting Model with 4D Variational Assimilation
arXiv 2023
[Paper] [Code] -
(XiChen) XiChen: An observation-scalable fully AI-driven global weather forecasting system with 4D variational knowledge
arXiv 2025
[Paper] [Code] -
(SwinVRNN) SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation
JAMES 2023
[Paper] [Code] -
(SwinRDM) SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting
AAAI 2023
[Paper] -
(Pangu-Weather) Accurate medium-range global weather forecasting with 3D neural networks
Nature 2023
[Paper] [Code] -
(Stormer) Scaling transformer neural networks for skillful and reliable medium-range weather forecasting
arXiv 2024
[Paper] [Code] -
(HEAL-ViT) HEAL-ViT: Vision Transformers on a spherical mesh for medium-range weather forecasting
arXiv 2024
[Paper] -
(TianXing) linear complexity transformer model with explicit attention decay for global weather forecasting
Advances in Atmospheric Sciences
[Paper] [Code]
-
(GraphCast) Graphcast: Learning skillful medium-range global weather forecasting
Science 2023
[Paper] [Code] -
(OneForecast) OneForecast: A Universal Framework for Global and Regional Weather Forecasting
ICML 2025
[Paper] [Code] -
(GnnWeather) Forecasting Global Weather with Graph Neural Networks
arXiv 2022
[Paper] [Code] -
(AIFS) AIFS -- ECMWF's data-driven forecasting system
arXiv 2024
[Paper] [Code] -
(GraphDOP) GraphDOP: Towards skilful data-driven medium-range weather forecasts learnt and initialised directly from observations
arXiv 2024
[Paper] [Code]
-
(Conformer) Searth Transformer: A Transformer Architecture Incorporating Earth's Geospheric Physical Priors for Global Mid-Range Weather Forecasting
arXiv 2026
[Paper] [Code] -
(ClimODE) ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs
arXiv 2024
[Paper] [Code] -
(WeatherODE) Mitigating Time Discretization Challenges with WeatherODE: A Sandwich Physics-Driven Neural ODE for Weather Forecasting
arXiv 2024
[Paper] [Code] -
(NeuralGCM) Neural general circulation models for weather and climate
Nature 2024
[Paper] [Code] -
(Conformer) STC-ViT: Spatio Temporal Continuous Vision Transformer for Weather Forecasting
arXiv 2024
[Paper] [Code]
-
(SwinUnet) Spatiotemporal vision transformer for short time weather forecasting
IEEE BigData 2022
[Paper] [Code] -
(Earthformer) Earthformer: Exploring Space-Time Transformers for Earth System Forecasting
NeurIPS 2022
[Paper] [Code] -
(Rainformer) Rainformer: Features Extraction Balanced Network for Radar-Based Precipitation Nowcasting
IEEE Geoscience and Remote Sensing Letters 2022
[Paper] [Code] -
(PFformer) PFformer: A Time-Series Forecasting Model for Short-Term Precipitation Forecasting
IEEE Access 2024
[Paper] -
(OMG-HD) OMG-HD: A high-resolution ai weather model for end-to-end forecasts from observations
arXiv 2024
[Paper] -
(U-STN) Towards physics-inspired data-driven weather forecasting: integrating data assimilation with a deep spatial-transformer-based u-net in a case study with era5
Geoscientific Model Development 2024
[Paper] [Code]
-
(HiSTGNN) HiSTGNN: Hierarchical spatio-temporal graph neural network for weather forecasting
Information Sciences 2023
[Paper] [Code] -
(w-GNN) Coupling Physical Factors for Precipitation Forecast in China With Graph Neural Network
AGU 2024
[Paper] -
(WeatherGNN) WeatherGNN: Exploiting Meteo- and Spatial-Dependencies for Local Numerical Weather Prediction Bias-Correction
IJCAI 2024
[Paper] -
(MPNNs) Multi-modal graph neural networks for localized off-grid weather forecasting
arXiv 2024
[Paper] [Code]
-
(Samudra) Samudra: An AI Global Ocean Emulator for Climate
Geophysical Reseach Letters 2025
[Paper] [Code] -
(MetNet) MetNet: A Neural Weather Model for Precipitation Forecasting
arXiv 2020
[Paper] [Code] -
(MetNet-3) Deep Learning for Day Forecasts from Sparse Observations
arXiv 2023
[Paper] -
(PredRNN) PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023
[Paper] [Code] -
(MM-RNN) MM-RNN: A Multimodal RNN for Precipitation Nowcasting
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2023
[Paper] -
(ConvLSTM) Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
NeurIPS 2015
[Paper] [Code]
-
(MetMamba) MetMamba: Regional Weather Forecasting with Spatial-Temporal Mamba Model
arXiv 2024[Paper] -
(MambaDS) MambaDS: Near-Surface Meteorological Field Downscaling With Topography Constrained Selective State-Space Modeling
IEEE Transactions on Geoscience and Remote Sensing 2024
[Paper]
-
(NowcastNet) Skilful nowcasting of extreme precipitation with NowcastNet
Nature 2023
[Paper] [Code] -
(PhysDL) Deep learning for physical processes: incorporating prior scientific knowledge
IOPScience 2019
[Paper] -
(PhyDNet) Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video Prediction
CVPR 2020
[Paper] [Code] -
(DeepPhysiNet) DeepPhysiNet: Bridging Deep Learning and Atmospheric Physics for Accurate and Continuous Weather Modeling
arXiv 2024
[Paper] [Code]
-
(OmniCast) OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
NeurIPS 2025
[Paper] [Code] -
(GenCast) GenCast: Diffusion-based ensemble forecasting for medium-range weather
Nature 2024
[Paper] [Code] -
(CoDiCast) CoDiCast: Conditional Diffusion Model for Weather Prediction with Uncertainty Quantification
IJCAI 2025
[Paper] [Code] -
(SEEDs) SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models
Science Advances 2024
[Paper] [Code] -
(ContinuousEnsCast) Continuous Ensemble Weather Forecasting with Diffusion models
ICLR 2025
[Paper] [Code]
-
(LDMRain) Latent diffusion models for generative precipitation nowcast-ing with accurate uncertainty quantification
arXiv 2023
[Paper] [Code] -
(PreDiff) PreDiff: Precipitation Nowcasting with Latent Diffusion Models
NeurIPS 2023
[Paper] [Code] -
(CasCast) CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling
ICML 2024
[Paper] [Code] -
(SRNDiff) SRNDiff: Short-term Rainfall Nowcasting with Condition Diffusion Model
arXiv 2024
[Paper] [Code] -
(DiffCast) DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting
CVPR 2024
[Paper] [Code] -
(GEDRain) Precipitation nowcasting with generative diffusion models
arXiv 2023
[Paper] [Code]
-
(GANRain) Skillful precipitation nowcasting using deep generative models of radar
Nature 2021
[Paper] [Code] -
(MultiScaleGAN) Experimental Study on Generative Adversarial Network for Precipitation Nowcasting
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2022
[Paper] [Code] -
(STGM) Physical-Dynamic-Driven AI-Synthetic Precipitation Nowcasting Using Task-Segmented Generative Model
AGU 2023
[Paper] [Code] -
(PCT-CycleGAN) PCT-CycleGAN: Paired Complementary Temporal Cycle-Consistent Adversarial Networks for Radar-Based Precipitation Nowcasting
ACM 2023
[Paper]
-
(ClimaX) ClimaX: A foundation model for weather and climate
ICML 2023
[Paper] [Code] -
(W-MAE) W-MAE: Pre-trained weather model with masked autoencoder for multi-variable weather forecasting
arXiv 2023
[Paper] [Code] -
(Aurora) Aurora: A foundation model of the atmosphere.
arXiv 2024
[Paper] [Code] -
(Prithvi WxC) Prithvi WxC: Foundation Model for Weather and Climate
arXiv 2024
[Paper] [Code] -
(AtmosArena) AtmosArena: Benchmarking Foundation Models for Atmospheric Sciences
NeurIPS 2024 Workshop FM4Science
[Paper] [Code]
-
(ClimateBench-M) ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Method
CIKM 2025
[Paper] [Code] -
(TyphoFormer) TyphoFormer: Language-Augmented Transformer for Accurate Typhoon Track Forecasting
arXiv 2025
[Paper] [Code] -
(Omni-Weather) Omni-Weather: Unified Multimodal Foundation Model for Weather Generation and Understanding
arXiv 2025
[Paper] [Code]
- (DLESyM) Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Models
arXiv 2025
[Paper] [Code]
- Neural general circulation models for modeling precipitation. [Paper]
- Deep Learning and the Weather Forecasting Problem: Precipitation Nowcasting. [Paper]
- PRISMA: A systematic quantitative review on the performance of some of the recent short-term rainfall forecasting techniques. [Paper]
- Deep Learning Techniques in Extreme Weather Events: A Review [Paper]
- Analysis, characterization, prediction, and attribution of extreme atmospheric events with machine learning and deep learning techniques: a review [Paper]
- Deep learning for precipitation nowcasting: A survey from the perspective of time series forecasting. [Paper]
- Precipitation Nowcasting with Satellite Imagery. [Paper]
- RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting. [Paper]
- Convective Precipitation Nowcasting Using U-Net Model. [Paper]
- NowCasting-Nets: Representation Learning to Mitigate Latency Gap of Satellite Precipitation Products Using Convolutional and Recurrent Neural Networks. [Paper]
- Domain Generalization Strategy to Train Classifiers Robust to Spatial-Temporal Shift. [Paper]
- Region-Conditioned Orthogonal 3D U-Net for Weather4Cast Competition. [Paper]
- Skilful nowcasting of extreme precipitation with NowcastNet. [Paper]
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. [Paper]
- PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs. [Paper]
- Nowformer: A Locally Enhanced Temporal Learner for Precipitation Nowcasting. [Paper]
- Earthformer: Exploring Space-Time Transformers for Earth System Forecasting. [Paper]
- Rainformer: Features Extraction Balanced Network for Radar-Based Precipitation Nowcasting. [Paper]
- The MS-RadarFormer: A Transformer-Based Multi-Scale Deep Learning Model for Radar Echo Extrapolation. [Paper]
- A Foundation Model for the Earth System. [Paper]
- WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning. [Paper]
- AENN: A GENERATIVE ADVERSARIAL NEURAL NETWORK FOR WEATHER RADAR ECHO EXTRAPOLATION. [Paper]
- MPL-GAN: Toward Realistic Meteorological Predictive Learning Using Conditional GAN. [Paper]
- Skillful Radar-Based Heavy Rainfall Nowcasting Using Task-Segmented Generative Adversarial Network. [Paper]
- A Self-Attention Causal LSTM Model for Precipitation Nowcasting. [Paper]
- PCT-CycleGAN: Paired Complementary Temporal Cycle-Consistent Adversarial Networks for Radar-Based Precipitation Nowcasting. [Paper]
- Precipitation Nowcasting Using Physics Informed Discriminator Generative Models. [Paper]
- GPTCast: a weather language model for precipitation nowcasting. [Paper]
- PreDiff: Precipitation Nowcasting with Latent Diffusion Models [Paper]
- Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification. [Paper]
- DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting. [Paper]
- CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling. [Paper]
- U-Air: when urban air quality inference meets big data. [Paper]
- Forecasting of Air Quality Using an Optimized Recurrent Neural Network. [Paper]
- Deep Distributed Fusion Network for Air Quality Prediction. [Paper]
- Time Series Forecasting (TSF) Using Various Deep Learning Models. [Paper]
- Group-Aware Graph Neural Network for Nationwide City Air Quality Forecasting. [Paper]
- PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting. [Paper]
- AirFormer: Predicting Nationwide Air Quality in China with Transformers. [Paper]
- MGSFformer: A Multi-Granularity Spatiotemporal Fusion Transformer for air quality prediction. [Paper]
- Air Quality Prediction Using the Fractional Gradient-Based Recurrent Neural Network. [Paper]
- Air quality prediction using CNN+LSTM-based hybrid deep learning architecture. [Paper]
- OptFormer: Optical Flow-Guided Attention and Phase Space Reconstruction for SST Forecasting. [Paper]
- ENSO analysis and prediction using deep learning: A review. [Paper]
- Analyzing El Niño–Southern Oscillation Predictability Using Long-Short-Term-Memory Models. [Paper]
- Spatiotemporal Model Based on Deep Learning for ENSO Forecasts. [Paper]
- Deep learning for multi-year ENSO forecasts. [Paper]
- Forecasting the Indian Ocean Dipole With Deep Learning Techniques. [Paper]
- Deep Residual Convolutional Neural Network Combining Dropout and Transfer Learning for ENSO Forecasting. [Paper]
- DLENSO: A Deep Learning ENSO Forecasting Model. [Paper]
- Graph Neural Networks for Improved El Niño Forecasting. [Paper]
- Transformer for EI Niño-Southern Oscillation Prediction. [Paper]
- A self-attention–based neural network for three-dimensional multivariate modeling and its skillful ENSO predictions. [Paper]
- Spatial-temporal transformer network for multi-year ENSO prediction. [Paper]
- Adaptive Graph Spatial-Temporal Attention Networks for long lead ENSO prediction. [Paper]
- ENSO dataset & comparison of deep learning models for ENSO forecasting. [Paper]
- Global Spatiotemporal Graph Attention Network for Sea Surface Temperature Prediction. [Paper]
- Physical Knowledge-Enhanced Deep Neural Network for Sea Surface Temperature Prediction. [Paper]
- Explainable deep learning for insights in El Niño and river flows. [Paper]
- Data-driven multi-step prediction and analysis of monthly rainfall using explainable deep learning. [Paper]
- An Interpretable Deep Learning Approach for Detecting Marine Heatwaves Patterns. [Paper]
- 3D-Geoformer: A self-attention–based neural network for three-dimensional multivariate modeling and its skillful ENSO predictions. [Paper]
- Evaluation of artificial intelligence models for flood and drought forecasting in arid and tropical regions. [Paper]
- Flood forecasting with machine learning models in an operational framework. [Paper]
- Particle swarm optimization based LSTM networks for water level forecasting: A case study on Bangladesh river network. [Paper]
- Prediction of Flow Based on a CNN-LSTM Combined Deep Learning Approach. [Paper]
- Designing Deep-Based Learning Flood Forecast Model With ConvLSTM Hybrid Algorithm. [Paper]
- Improving urban flood prediction using LSTM-DeepLabv3+ and Bayesian optimization with spatiotemporal feature fusion. [Paper]
- The Merit of River Network Topology for Neural Flood Forecasting. [Paper]
- FloodGNN-GRU: a spatio-temporal graph neural network for flood prediction. [Paper]
- Graph Transformer Network for Flood Forecasting with Heterogeneous Covariates. [Paper]
- FIDLAR: Forecast-Informed Deep Learning Architecture for Flood Mitigation. [Paper]
- Data-driven and knowledge-guided denoising diffusion model for flood forecasting. [Paper]
- DRUM: Diffusion-based runoff model for probabilistic flood forecasting. [Paper]
- Generalizing rapid flood predictions to unseen urban catchments with conditional generative adversarial networks. [Paper]
- Drought as a natural hazard: concepts and definitions. [Paper]
- Drought predic- tion based on spi and spei with varying timescales using lstm recurrent neural network. [Paper]
- Explain- able ai in drought forecasting. [Paper]
- Drought prediction based on feature-based transfer learning and time series imaging. [Paper]
- Application of a hybrid arima-lstm model based on the spei for drought forecasting. [Paper]
- Evaluation of artificial intelligence models for flood and drought forecasting. [Paper]
- Deep learning oriented satellite remote sensing for drought and prediction in agriculture. [Paper]
- Forecasting the propagation from meteorolog- ical to hydrological and agricultural drought in the huaihe river basin with machine learning methods. [Paper]
- Multivariate time series convo- lutional neural networks for long-term agricultural drought prediction under global warming. [Paper]
- A novel intelligent deep learning predictive model for meteorological drought forecasting. [Paper]
- Harnessing deep learning for meteorological drought forecasts in the northern cape, south africa. [Paper]
- Construction of an integrated drought monitoring model based on deep learning algorithms. [Paper]
- Drought prediction using artificial intelligence models based on climate data and soil moisture. [Paper]
- Advanced stacked integration method for forecasting long-term drought severity: Cnn with machine learning models. [Paper]
- Multiscale spatiotemporal meteorological drought prediction: A deep learning approach. [Paper]
- Deep learning-oriented c-gan models for vegetative drought prediction on peninsular india. [Paper]
- Predicting tropical cyclogenesis us- ing a deep learning method from gridded satellite and era5 reanalysis data in the western north pacific basin. [Paper]
- Predicting tropical cyclone formation with deep learning. [Paper]
- Improvement in forecasting short-term tropical cyclone intensity change and their rapid intensification using deep learning. [Paper]
- Tropical cyclone track forecasting using fused deep learning from aligned reanalysis data. [Paper]
- A novel data-driven tropical cyclone track prediction model based on cnn and gru with multi-dimensional feature selection. [Paper]
- Near real-time hurricane rainfall forecasting using convolutional neural network models with integrated multi-satellite retrievals for gpm (imerg) product. [Paper]
- Advanced hybrid cnn-bilstm model augmented with ga and ffo for enhanced cyclone intensity forecasting. [Paper]
- Forecasting formation of a tropical cyclone using reanalysis data. [Paper]
- Predicting landfall’s location and time of a tropical cyclone using reanalysis data. [Paper]
- Deep learning for down-scaling tropical cyclone rainfall to hazard-relevant spatial scales. [Paper]
- Tropical cyclone forecast using multitask deep learning framework. [Paper]
- Forecasting tropical cyclones with cascaded diffusion models. [Paper]
- Advancing storm surge forecasting from scarce observation data: A causal-inference based spatio-temporal graph neural network approach. [Paper]
- Wildfire spreading prediction using multimodal data and deep neural network approach. [Paper]
- Deep learning provides substantial improvements to county-level fire weather forecasting over the western united states. [Paper]
- Next-day wildfire spread: A machine learning dataset to predict wildfire spreading from remote-sensing data. [Paper]
- The large-scale wildfire spread prediction using a multi-kernel convolutional neural network. [Paper]
- Comparison of recurrent neural network architectures for wildfire spread modeling. [Paper]
- Comparative analysis of hybrid long short-term memory models for fire danger index forecasting with weather data. [Paper]
- A comparative study on forest fire prediction using arima, sarima, lstm, and gru methods. [Paper]
- Cnn-bilstm: A novel deep learning model for near-real-time daily wildfire spread prediction. [Paper]
- Firepred: A hybrid multi-temporal convolutional neural network model for wildfire spread prediction. [Paper]
- Recurrent convolutional deep neural networks for modeling time-resolved wildfire spread behavior. [Paper]
- Spatiotemporal attention convlstm networks for predicting and physically interpreting wildfire spread. [Paper]
- Capturing and interpreting wildfire spread dynamics: attention-based spatiotemporal models using convlstm networks. [Paper]
- Mitigating greenhouse gas emissions through generative adversarial networks based wildfire prediction. [Paper]
- Modeling wildfire spread with an irregular graph network. [Paper]
- Forest fire prediction based on time series networks and remote sensing images. [Paper]
- SolarSeer: Ultrafast and accurate 24-hour solar irradiance forecasts outperforming numerical weather prediction across the USA.[Paper][Code]
- Data-driven solar forecasting enables near-optimal economic decisions. [Paper]
- Data-driven Surface Solar Irradiance Estimation using Neural Operators at Global Scale. [Paper]
- A machine learning model for hub-height short-term wind speed prediction. [Paper]
- ChatClimate: Grounding conversational AI in climate science, in Nature Communications Earth & Environment 2023. [Paper]
- spateGAN: Spatio-Temporal Downscaling of Rainfall Fields Using a cGAN Approach, Earth and Space Science 2023. [Paper]
- OceanGPT: A Large Language Model for Ocean Science Tasks, in arXiv 2023. [paper] [official code]
- IBMWeatherGen: Stochastic Weather Generator Tool, [Code]
@article{shi2025deep,
title={Deep learning and foundation models for weather prediction: A survey},
author={Shi, Jimeng and Shirali, Azam and Jin, Bowen and Zhou, Sizhe and Hu, Wei and Rangaraj, Rahuul and Wang, Shaowen and Han, Jiawei and Wang, Zhaonan and Lall, Upmanu and others},
journal={arXiv preprint arXiv:2501.06907},
year={2025}
}