Leo-Ji2020 / meteoai

The papers or tutorials and relative source code of artificial intelligence for meteorology, ocean and environment science.

meteoai

The papers or tutorials and relative source code of artificial intelligence for meteorology, ocean and environment science.

Classification, Detection, Cluster

• A cloud detection algorithm for satellite imagery based on deep learning : Code

• Deep Convolutional Encoder-Decoder Networks for Uncertainty Quantification of Dynamic Multiphase Flow in Heterogeneous Media : Code

• A daily global mesoscale ocean eddy dataset from satellite altimetry : Code

• Detecting Climate Change Effects on Vb Cyclones in a 50-Member Single-Model Ensemble Using Machine Learning : Zenodo

Satellite & Weather Radar

• Reconstruction of Cloud Vertical Structure with a Generative Adversarial Network : Code

• RainNet: a convolutional neural network for radar-based precipitation nowcasting : Code

• Deep learning for precipitation nowcasting: A benchmark and a new model : Code

Downscaling

• Configuration and Intercomparison of Deep Learning Neural Models for Statistical Downscaling : Code

Weather and Climate Forecast

• Nowcasting lightning occurrence from commonly available meteorological parameters using machine learning techniques: The codes relevant to this paper are available upon request from the corresponding author.

• Predicting Weather Forecast Uncertainty with Machine Learning : Code

• Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting : Code

• STConvS2S: Spatiotemporal Convolutional Sequence to Sequence Network for Weather Forecasting : Code

• WeatherBench: A benchmark dataset for data-driven weather forecasting : Code

• Interpretable Deep Learning for Spatial Analysis of Severe Hailstorms : Code

• Deep learning for prediction of meteorological fronts: Keras tutorial : Code

• Storm-Based Probabilistic Hail Forecasting with Machine Learning Applied to Convection-Allowing Ensembles : Code

• Improving Subseasonal Forecasting in the Western US with Machine Learning : Code

• Weather and climate forecasting with neural networks: using GCMs with different complexity as study-ground : Zenodo

• Improving Subseasonal Forecasting in the Western US with Machine Learning : Code

Extreme Events

• Analog Forecasting of Extreme-Causing Weather Patterns Using Deep Learning : Code

• Using machine learning to predict extreme events in complex systems : Code

• The Application of Machine Learning Techniques to Improve El Niño Prediction Skill : Code

• ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events : Code

• Deep learning for multi-year ENSO forecasts : Code

Numerical Model

• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems : Code

Parameterization

• Deep learning to represent sub-grid processes in climate models : Code

• Could machine learning break the convection parameterization deadlock? : Code

• A data-driven approach to precipitation parameterizations using convolutional encoder-decoder neural networks : Code

• Deep learning to represent subgrid processes in climate models : Zenodo, Gitlab

• Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model : Zenodo

Post-processing

• Neural networks for post-processing ensemble weather forecasts : Code

Data Assimilation

• Combining data assimilation and machine learning to emulate a dynamical model from sparse and noisy observations- a case study with the Lorenz 96 model : Code

Uncertainty Quantification

• Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data : Code

• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification : Code

• Adversarial uncertainty quantification in physics-informed neural networks : Code

Interpretable

• Interpretable Deep Learning for Spatial Analysis of Severe Hailstorms : Code

• Interpretation of deep-learning models for predicting thunderstorm rotation: Python tutorial : Code

• Interpretable Machine Learning: A Guide for Making Black Box Models Explainable : Code

Partial Differential Equations

• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations : Code

• Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations : Code

• Learning data-driven discretizations for partial differential equations : Code