A professionally curated list of Large Foundation Models for Weather and Climate Data Understanding (e.g., time-series, spatio-temporal series, video streams, graphs, and text) with awesome resources (paper, code, data, etc.), which aims to comprehensively and systematically summarize the recent advances to the best of our knowledge.
OPEN TO COLLABORATION! If you have any new insights in any relevant research direction or just want to chat, please drop me an email (shengchao.chen.uts AT gmail DOT com).
[New, Paper] Our research paper: Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models has accepted by NeurIPS 2024, which introduces a language model-based solution for real-world multi-device meteorological variable modeling. [Code and dataset coming soon]
[Paper] Our survey: Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey has appeared on arXiv, which is the first work to comprehensively and systematically summarize DL-based weather and climate data understanding, paving the way for the development of weather and climate foundation models. 🌤️⛈️❄️
Abstract: Recent advances in deep learning (DL) have significantly enhanced our capability to analyze and interpret weather and climate data, especially at fine spatio-temporal scales, helping unravel the chaotic and nonlinear patterns of Earth's systems. The emergence of Foundation Models, particularly Large Language Models (LLMs), has catalyzed advances in Artificial General Intelligence, delivering outstanding outcomes across various tasks through fine-tuning. The success of LLMs presents a novel opportunity to rethink the task of weather and climate data understanding: Is it possible to utilize or evolve Foundation Models for weather and climate data to enhance the accuracy of task completion? This survey evaluates the potential of adapting Foundation Models to enhance weather and climate data analysis. We present a concise, up-to-date review of cutting-edge AI techniques tailored for this domain, concentrating on time series and textual information. We cover four key areas: data types, model architectures, application scopes, and task-specific datasets. Furthermore, we address prevailing challenges, provide insights, and outline future research directions, empowering practitioners to advance the field. The survey distills the latest innovations in data-driven models, underscoring foundational strength, progress, applications, resources, and research frontiers, thus offering a roadmap for transformative advancements in weather and climate data understanding.
We will continue to update this list with the newest resources. If you find any missed resources (paper/code) or errors, please feel free to open an issue or make a pull request.
Definition: Pre-trained from large-scale weather/climate dataset and able to perform various weather/cliamte-related tasks.
| Publication | Venue | Year | Resource |
|---|---|---|---|
| Aurora: A Foundation Model of the Atmosphere | Microsoft Research AI for Science | 2024 | [paper] |
| Pangu-Weather: Accurate Medium-Range Global Weather Forecasting with 3D Neural Networks | Nature | 2023 | [paper] [code] |
| ClimaX: A Foundation Model for Weather and Climate | ICML | 2023 | [paper] [code] |
| GraphCast: Learning Skillful Medium-Range Global Weather Forecasting | arXiv | 2022 | [paper] [code] |
| FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operator | arXiv | 2022 | [paper] [code] |
| W-MAE: Pre-Trained Weather Model with Masked Autoencoder for Multi-Variable Weather Forecasting | arXiv | 2023 | [paper] [code] |
| FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead | arXiv | 2023 | [[paper] |
| FuXi: A cascade machine learning forecasting system for 15-day global weather forecast | arXiv | 2023 | [[paper] [code] |
| OceanGPT: A Large Language Model for Ocean Science Tasks | arXiv | 2023 | [paper] [code] |
Remark: Note that in this categorization, we use basic network architectures (e.g., RNN, Transformer), etc., and applications (e.g., prediction, weather pattern understanding, etc.) to make an enumeration of advanced related work.
Recurrent Neural Network-based Models
| Publication | Venue | Year | Resource |
|---|---|---|---|
| MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions | CVPR | 2021 | [paper] [official code] |
| Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting | NeurIPS | 2015 | [paper] [official code] |
| Dwfh: An improved data-driven deep weather forecasting hybrid model using transductive long short term memory (t-lstm) | EAAI | 2023 | [paper] |
| Spatiotemporal inference network for precipitation nowcasting with multi-modal fusion | IEEE Journal of Selected Topics in Applied Earth Observation and Remote Sensing | 2023 | [paper] |
| Understanding the role of weather data for earth surface forecasting using a convlstm-based model | CVPR | 2023 | [paper] [official code] |
| Spatio-temporal weather forecasting and attention mechanism on convolutional lstms | arXiv | 2021 | [paper] [official code] |
| Convolutional tensor-train lstm for spatio-temporal learning | NeurIPS | 2020 | [paper] [official code] |
| Predrnn: A recurrent neural network for spatiotemporal predictive learning | IEEE T-PAMI | 2022 | [paper] [official code] |
| Eidetic 3d lstm: A model for video prediction and beyond | ICLR | 2018 | [paper] [official code] |
| Predrann: the spatiotemporal attention convolution recurrent neural network for precipitation nowcasting | Knowledge-Based Systems | 2022 | [paper] |
| Time-series prediction of hourly atmospheric pressure using anfis and lstm approaches | Neural Computing and Applications | 2022 | [paper] |
| Ilf-lstm: Enhanced loss function in lstm to predict the sea surface temperature | Soft Computing | 2022 | [paper] |
| Swinlstm: Improving spatiotemporal prediction accuracy using swin transformer and lstm | ICCV | 2023 | [paper] [official code] |
| Swinrdm: integrate swinrnn with diffusion model towards high-resolution and high quality weather forecasting | AAAI | 2023 | [paper] |
| Swinvrnn: A data-driven ensemble forecasting model via learned distribution perturbation | Journal of Advances in Modeling Earth Systems | 2023 | [paper] |
| Comparison of BLSTM-Attention and BLSTM-Transformer Models for Wind Speed Prediction | Bulgarian Academy of Sciences | 2022 | [paper] |
| A generative adversarial gated recurrent unit model for precipitation nowcasting | IEEE Geoscience and Remote Sensing Letters | 2019 | [paper] [official code] |
| Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields With a Generative Adversarial Network | IEEE Transactions on Geoscience and Remote Sensing | 2020 | [paper] [official code] |
| Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows | ICCV | 2021 | [paper] [official code] |
| Towards data-driven physics-informed global precipitation forecasting from satellite imagery | NeurIPS | 2020 | [paper] |
Diffusion Models-based Approaches
| Publication | Venue | Year | Resource |
|---|---|---|---|
| SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting | AAAI | 2023 | [Paper] |
| Swinvrnn: A data-driven ensemble forecasting model via learned distribution perturbation | Journal of Advances in Modeling Earth Systems | 2023 | [Paper] |
| SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models | arXiv | 2023 | [Paper] |
| DiTTO: Diffusion-inspired Temporal Transformer Operator | arXiv | 2023 | [Paper] |
| PreDiff: Precipitation Nowcasting with Latent Diffusion Models | arXiv | 2023 | [Paper] |
| Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification | arXiv | 2023 | [Paper] [official code] |
| ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models | arXiv | 2021 | [Paper] [official code] |
| PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers | arXiv | 2023 | [Paper] |
| Diffusion Models for High-Resolution Solar Forecasts | arXiv | 2023 | [Paper] |
| Generative Residual Diffusion Modeling for Km-scale Atmospheric Downscaling | arXiv | 2023 | [Paper] |
| DiffMet: Diffusion models and deep learning for precipitation nowcasting | Master thesis | 2023 | [[Paper]] |
| (https://www.duo.uio.no/handle/10852/103253) |
Generative Adversarial Networks (GANs)-based Approaches
| Publication | Venue | Year | Resource |
|---|---|---|---|
| Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks | arXiv | 2015 | [Paper] [official code] |
| Large Scale GAN Training for High Fidelity Natural Image Synthesis | arXiv | 2018 | [Paper] [official code] |
| Progressive Growing of GANs for Improved Quality, Stability, and Variation | arXiv | 2018 | [Paper] [official code] |
| A generative adversarial network approach to (ensemble) weather prediction | Neural Networks | 2021 | [Paper] |
| Climate-StyleGAN: Modeling Turbulent Climate Dynamics Using Style-GAN | AI for Earth Science Workshop | 2020 | [Paper] |
| Dynamic Multiscale Fusion Generative Adversarial Network for Radar Image Extrapolation | IEEE Transactions on Geoscience and Remote Sensing | 2022 | [Paper] |
| Generative modeling of spatio-temporal weather patterns with extreme event conditioning | arXiv | 2021 | [Paper] |
| Skilful precipitation nowcasting using deep generative models of radar | Nature | 2021 | [Paper] [official code] |
| SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal Patterns with an Autoregressive Embedding Loss | AAAI | 2022 | [Paper] [official code] |
| MPL-GAN: Toward Realistic Meteorological Predictive Learning Using Conditional GAN | IEEE Access | 2020 | [Paper] |
| PCT-CycleGAN: Paired Complementary Temporal Cycle-Consistent Adversarial Networks for Radar-Based Precipitation Nowcasting | 32nd ACM International Conference on Information and Knowledge Management | 2023 | [Paper] |
| A generative adversarial gated recurrent unit model for precipitation nowcasting | IEEE Geoscience and Remote Sensing Letters | 2019 | [Paper] |
| Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields With a Generative Adversarial Network | IEEE Transactions on Geoscience and Remote Sensing | 2020 | [Paper] [official code] |
| Clgan: a generative adversarial network (gan)-based video prediction model for precipitation nowcasting | Geoscientific Model Development | 2023 | [Paper] |
| Experimental study on generative adversarial network for precipitation nowcasting | IEEE Transactions on Geoscience and Remote Sensing | 2022 | [Paper] |
| Skillful radar-based heavy rainfall nowcasting using task-segmented generative adversarial network | IEEE Transactions on Geoscience and Remote Sensing | 2023 | [Paper] |
| A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts | Journal of Advances in Modeling Earth Systems | 2022 | [Paper] |
| Algorithmic Hallucinations of Near-Surface Winds: Statistical Downscaling with Generative Adversarial Networks to Convection-Permitting Scales | Artificial Intelligence for the Earth Systems | 2023 | [Paper] |
| MSTCGAN: Multiscale Time Conditional Generative Adversarial Network for Long-Term Satellite Image Sequence Prediction | IEEE Transactions on Geoscience and Remote Sensing | 2022 | [Paper] |
| Very Short-Term Rainfall Prediction Using Ground Radar Observations and Conditional Generative Adversarial Networks | IEEE Transactions on Geoscience and Remote Sensing | 2021 | [Paper] |
| Physically constrained generative adversarial networks for improving precipitation fields from Earth system models | Nature Machine Intelligence | 2022 | [Paper] |
| Producing realistic climate data with generative adversarial networks | Nonlinear Processes in Geophysics | 2021 | [Paper] [official code] |
| TemperatureGAN: Generative Modeling of Regional Atmospheric Temperatures | arXiv | 2023 | [Paper] |
| A Generative Adversarial Network for Climate Tipping Point Discovery (TIP-GAN) | arXiv | 2023 | [Paper] |
| Physics-Guided Generative Adversarial Networks for Sea Subsurface Temperature Prediction | IEEE Transactions on Neural Networks and Learning Systems | 2021 | [Paper] |
| Physical Knowledge-Enhanced Deep Neural Network for Sea Surface Temperature Prediction | IEEE Transactions on Geoscience and Remote Sensing | 2023 | [Paper] |
| Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization | arXiv | 2021 | [Paper] |
| A Space-Time Partial Differential Equation Based Physics-Guided Neural Network for Sea Surface Temperature Prediction | Remote Sensing | 2023 | [Paper] |
| Physics-informed generative neural network: an application to troposphere temperature prediction | Environmental Research Letters | 2021 | [Paper] |
Transformers-based Approaches
| Publication | Venue | Year | Resource |
|---|---|---|---|
| Oceanfourcast: Emulating Ocean Models with Transformers for Adjoint-based Data Assimilation | Copernicus Meetings | 2023 | [Paper] |
| Comprehensive Transformer-Based Model Architecture for Real-World Storm Prediction | Machine Learning and Knowledge Discovery in Databases | 2023 | [Paper] |
| Transformer-based nowcasting of radar composites from satellite images for severe weather | arXiv | 2023 | [Paper] |
| Transformer for EI Niño-Southern Oscillation Prediction | IEEE Geoscience and Remote Sensing Letters | 2021 | [Paper] |
| Spatiotemporal Swin-Transformer Network for Short Time Weather Forecasting | CIKM Workshops | 2021 | [Paper] |
| Towards physically consistent data-driven weather forecasting: Integrating data assimilation with equivariance-preserving deep spatial transformers | arXiv | 2021 | [Paper] |
| TENT: Tensorized Encoder Transformer for Temperature Forecasting | arXiv | 2021 | [Paper] [official code] |
| A Novel Transformer Network With Shifted Window Cross-Attention for Spatiotemporal Weather Forecasting | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing | 2023 | [Paper] |
| Spatio-temporal interpretable neural network for solar irradiation prediction using transformer | Energy and Buildings | 2023 | [Paper] |
| ClimaX: A foundation model for weather and climate | arXiv | 2023 | [Paper] [official code] |
| Accurate medium-range global weather forecasting with 3D neural networks | Nature | 2023 | [Paper] [official code] |
| W-MAE: Pre-trained weather model with masked autoencoder for multi-variable weather forecasting | arXiv | 2023 | [Paper] [official code] |
| FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead | arXiv | 2023 | [Paper] |
| Improving medium-range ensemble weather forecasts with hierarchical ensemble transformers | arXiv | 2023 | [Paper] |
| CliMedBERT: A Pre-trained Language Model for Climate and Health-related Text | arXiv | 2022 | [Paper] |
| ClimateBERT-NetZero: Detecting and Assessing Net Zero and Reduction Targets | arXiv | 2023 | [Paper] |
| Fine-tuning ClimateBert transformer with ClimaText for the disclosure analysis of climate-related financial risks | arXiv | 2023 | [Paper] |
| ChatClimate: Grounding Conversational AI in Climate Science | arXiv | 2023 | [Paper] |
| ClimateNLP: Analyzing Public Sentiment Towards Climate Change Using Natural Language Processing | arXiv | 2023 | [Paper] |
| Evaluating TCFD Reporting: A New Application of Zero-Shot Analysis to Climate-Related Financial Disclosures | arXiv | 2023 | [Paper] |
| Enhancing Large Language Models with Climate Resources | arXiv | 2023 | [Paper] |
Graph Neural Networks-based Approaches
| Publication | Venue | Year | Resource |
|---|---|---|---|
| ENSO-GTC: ENSO Deep Learning Forecast Model With a Global Spatial-Temporal Teleconnection Coupler | Journal of Advances in Modeling Earth Systems | 2022 | [Paper] [official code] |
| GraphCast: Learning skillful medium-range global weather forecasting | arXiv | 2022 | [Paper] [official code] |
| Forecasting Global Weather with Graph Neural Networks | arXiv | 2022 | [Paper] [official code] |
| GE-STDGN: a novel spatio-temporal weather prediction model based on graph evolution | Applied Intelligence | 2022 | [Paper] [official code] |
| HiSTGNN: Hierarchical spatio-temporal graph neural network for weather forecasting | Information Sciences | 2023 | [Paper] |
| Convolutional GRU Network for Seasonal Prediction of the El Niño-Southern Oscillation | arXiv | 2023 | [Paper] |
| DK-STN: A Domain Knowledge Embedded Spatio-Temporal Network Model for MJO Forecast | Expert Systems With Applications, Forthcoming | 2023 | [Paper] |
| ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models | arXiv | 2021 | [Paper] [official code] |
| A Low Rank Weighted Graph Convolutional Approach to Weather Prediction | IEEE International Conference on Data Mining (ICDM) | 2018 | [Paper] [official code] |
| WeKG-MF: A Knowledge Graph of Observational Weather Data | European Semantic Web Conference | 2022 | [Paper] |
| Regional Heatwave Prediction Using Graph Neural Network and Weather Station Data | Geophysical Research Letters | 2023 | [Paper] |
| Graph-based Neural Weather Prediction for Limited Area Modeling | arXiv | 2023 | [Paper] [official code] |
| Joint Air Quality and Weather Prediction Based on Multi-Adversarial Spatiotemporal Networks | AAAI | 2021 | [Paper] |
| Semi-Supervised Air Quality Forecasting via Self-Supervised Hierarchical Graph Neural Network | IEEE Transactions on Knowledge and Data Engineering | 2022 | [Paper] |
| CNGAT: A Graph Neural Network Model for Radar Quantitative Precipitation Estimation | IEEE Transactions on Geoscience and Remote Sensing | 2021 | [Paper] |
| Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data | arXiv | 2023 | [Paper] [official code] |
| Spatial-temporal Prompt Learning for Federated Weather Forecasting | arXiv | 2023 | [Paper] |
Forecasting
| Publication | Venue | Year | Resource |
|---|---|---|---|
| Dwfh: An improved data-driven deep weather forecasting hybrid model using transductive long short term memory (t-lstm) | EAAI | 2023 | [Paper] |
| Swinrdm: integrate swinrnn with diffusion model towards high-resolution and highquality weather forecasting | AAAI | 2023 | [Paper] |
| Swinvrnn: A data-driven ensemble forecasting model via learned distribution perturbation | Journal of Advances in Modeling Earth Systems | 2023 | [Paper] |
| Time-series prediction of hourly atmospheric pressure using anfis and lstm approaches | Neural Computing and Applications | 2022 | [Paper] |
| Ilf-lstm: Enhanced loss function in lstm to predict the sea surface temperature | Soft Computing | 2022 | [Paper] |
| FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operator | arXiv | 2022 | [Paper] [official code] |
| An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | arXiv | 2020 | [Paper] [official code] |
| Improving medium-range ensemble weather forecasts with hierarchical ensemble transformers | arXiv | 2023 | [Paper] |
| TeleViT: Teleconnection-Driven Transformers Improve Subseasonal to Seasonal Wildfire Forecasting | ICCV | 2023 | [Paper] [official code] |
| Accurate Medium-Range Global Weather Forecasting with 3D Neural Networks | Nature | 2023 | [Paper] [official code] |
| FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead | arXiv | 2023 | [Paper] |
| FuXi: A cascade machine learning forecasting system for 15-day global weather forecast | arXiv | 2023 | [Paper] [official code] |
| FuXi-Extreme: Improving extreme rainfall and wind forecasts with diffusion model | arXiv | 2023 | [Paper] |
| Denoising Diffusion Probabilistic Models | NeurIPS | 2020 | [Paper] [official code] |
| ClimaX: A Foundation Model for Weather and Climate | arXiv | 2023 | [Paper] [official code] |
| W-MAE: Pre-Trained Weather Model with Masked Autoencoder for Multi-Variable Weather Forecasting | arXiv | 2023 | [Paper] [official code] |
| Masked Autoencoders Are Scalable Vision Learners | CVPR | 2022 | [Paper] [official code] |
| Masked Autoencoders As Spatiotemporal Learners | NeurIPS | 2022 | [Paper] [official code] |
| SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models | arXiv | 2023 | [Paper] |
| DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting | arXiv | 2023 | [Paper] [official code] |
| PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers | arXiv | 2023 | [Paper] |
| DiTTO: Diffusion-inspired Temporal Transformer Operator | arXiv | 2023 | [Paper] |
| TemperatureGAN: Generative Modeling of Regional Atmospheric Temperatures | arXiv | 2023 | [[ |
Precipitation Nowcasting
| Publication | Venue | Year | Resource |
|---|---|---|---|
| Dynamic Multiscale Fusion Generative Adversarial Network for Radar Image Extrapolation | IEEE Transactions on Geoscience and Remote Sensing | 2022 | [Paper] |
| MCSIP Net: Multichannel Satellite Image Prediction via Deep Neural Network | IEEE Transactions on Geoscience and Remote Sensing | 2019 | [Paper] |
| Developing Deep Learning Models for Storm Nowcasting | IEEE Transactions on Geoscience and Remote Sensing | 2021 | [Paper] |
| Enhancing Spatial Variability Representation of Radar Nowcasting with Generative Adversarial Networks | Remote Sensing | 2023 | [Paper] [official code] |
| NowCasting-Nets: Representation Learning to Mitigate Latency Gap of Satellite Precipitation Products Using Convolutional and Recurrent Neural Networks | IEEE Transactions on Geoscience and Remote Sensing | 2022 | [Paper] [official code] |
| Broad-UNet: Multi-scale feature learning for nowcasting tasks | Neural Networks | 2021 | [Paper] [official code] |
| Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting | NeurIPS | 2015 | [Paper] [official code] |
| MSTCGAN: Multiscale Time Conditional Generative Adversarial Network for Long-Term Satellite Image Sequence Prediction | IEEE Transactions on Geoscience and Remote Sensing | 2022 | [Paper] |
| MMSTN: A Multi-Modal Spatial-Temporal Network for Tropical Cyclone Short-Term Prediction | Geophysical Research Letters | 2022 | [Paper] |
| PFST-LSTM: A SpatioTemporal LSTM Model With Pseudoflow Prediction for Precipitation Nowcasting | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing | 2020 | [official code] |
| TempEE: Temporal-Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Auto-Regression | arXiv | 2023 | [Paper] |
| Nowformer : A Locally Enhanced Temporal Learner for Precipitation Nowcasting | [Paper] | ||
| Rainformer: Features Extraction Balanced Network for Radar-Based Precipitation Nowcasting | IEEE Geoscience and Remote Sensing Letters | 2022 | [Paper] [official code] |
| PTCT: Patches with 3D-Temporal Convolutional Transformer Network for Precipitation Nowcasting | arXiv | 2021 | [Paper] [official code] |
| Preformer: Simple and Efficient Design for Precipitation Nowcasting with Transformers | IEEE Geoscience and Remote Sensing Letters | 2023 | [Paper] |
| Motion-Guided Global–Local Aggregation Transformer Network for Precipitation Nowcasting | IEEE Transactions on Geoscience and Remote Sensing | 2022 | [Paper] |
| Predrnn: A recurrent neural network for spatiotemporal predictive learning | IEEE T-PAMI | 2022 | [Paper] [official code] |
| Eidetic 3d lstm: A model for video prediction and beyond | ICLR | 2018 | [Paper] [official code] |
| Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video Prediction | CVPR | 2020 | [Paper] |
| Partial differential equations | American Mathematical Society | 2022 | [Paper] |
| Metnet: A neural weather model for precipitation forecasting | arXiv | 2020 | [Paper] [official code] |
Weather and Climate Series Data
| Publication | Venue | Year | Resource |
|---|---|---|---|
| WEATHER-5K: A Large-scale Global Station Weather Dataset Towards Comprehensive Time-series Forecasting Benchmark | arXiv | 2024 | [Paper] [official project] |
| ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning | NeurIPS (Track on Datasets and Benchmarks) | 2023 | [Paper] [official project] |
| Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for Meteorological Forecasting Based on Real-Time Observation Data from Ground Weather Stations | AISTATS | 2023 | [Paper] [official project] |
| ClimateBench v1.0: A Benchmark for Data-Driven Climate Projections | Journal of Advances in Modeling Earth Systems | 2022 | [Paper] [official code] |
| WeatherBench: A Benchmark Data Set for Data-Driven Weather Forecasting | Journal of Advances in Modeling Earth Systems | 2020 | [Paper] [official code] |
| WeatherBench 2: A benchmark for the next generation of data-driven global weather models | arXiv | 2023 | [Paper] [official code] |
| ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling | arXiv | 2023 | [Paper] [official code] |
| An Evaluation and Intercomparison of Global Analyses from the National Meteorological Center and the European Centre for Medium Range Weather Forecasts | Bulletin of the American Meteorological Society | 1988 | [Paper] |
| SODA: A Reanalysis of Ocean Climate | Journal of Geophysical Research-Oceans | 2005 | [Paper] |
| DroughtED: A dataset and methodology for drought forecasting spanning multiple climate zones | ICML | 2021 | [Paper] |
| Digital Typhoon: Long-term Satellite Image Dataset for the Spatio-Temporal Modeling of Tropical Cyclones | arXiv | 2023 | [Paper] [official code] |
| EarthNet2021: A Large-Scale Dataset and Challenge for Earth Surface Forecasting as a Guided Video Prediction Task | Computer Vision and Pattern Recognition | 2021 | [Paper] [official code] |
| ClimateNet: an expert-labeled open dataset and deep learning architecture for enabling high-precision analyses of extreme weather | Geoscientific Model Development | 2021 | [Paper] [official code] |
| IowaRain: A Statewide Rain Event Dataset Based on Weather Radars and Quantitative Precipitation Estimation | arXiv | 2021 | [Paper] [official code] |
| ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events | NeurIPS | 2017 | [Paper] [official code] |
| Benchmark Dataset for Precipitation Forecasting by Post-Processing the Numerical Weather Prediction | arXiv | 2022 | [Paper] [official code] |
| A gridded dataset of hourly precipitation in Germany: Its construction, climatology and application | Meteorologische Zeitschrift | 2008 | [Paper] |
| PostRainBench: A comprehensive benchmark and a new model for precipitation forecasting | arXiv | 2023 | [Paper] |
| 1 km monthly temperature and precipitation dataset for China from 1901 to 2017 | Earth System Science Data | 2019 | [Paper] |
| ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models | arXiv | 2021 | [Paper] [official code] |
| Rain-F: A Fusion Dataset for Rainfall Prediction Using Convolutional Neural Network | IGARSS | 2021 | [Paper] |
| RAIN-F+: The Data-Driven Precipitation Prediction Model for Integrated Weather Observations | Remote Sensing | 2021 | [Paper] [official code] |
Weather and Climate Text Data
| Publication | Venue | Year | Resource |
|---|---|---|---|
| CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims | arXiv | 2021 | [Paper] [official code] |
| ClimateBERT-NetZero: Detecting and Assessing Net Zero and Reduction Targets | arXiv | 2023 | [Paper] |
| ClimaText: A Dataset for Climate Change Topic Detection | arXiv | 2020 | [Paper] |
| Towards Fine-grained Classification of Climate Change related Social Media Text | Association for Computational Linguistics: Student Research Workshop | 2022 | [Paper] |
| Neuralnere: Neural named entity relationship extraction for end-to-end climate change knowledge graph construction | ICML | 2021 | [Paper] |
@article{chen2023foundation,
title={Foundation models for weather and climate data understanding: A comprehensive survey},
author={Chen, Shengchao and Long, Guodong and Jiang, Jing and Liu, Dikai and Zhang, Chengqi},
journal={arXiv preprint arXiv:2312.03014},
year={2023}
}