Latest

• Crowdsourcing the Frontier: Advancing Hybrid Physics-ML Climate Simulation via a $50,000 Kaggle Competition
• Towards Accurate Extreme Event Likelihoods from Diffusion Model Climate Emulators
• NVIDIA Launches Earth-2 Family of Open Models — the World's First Fully Open, Accelerated Set of Models and Tools for AI Weather
• Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting
• Examining Fast Radiatively Driven Responses Using Machine-Learning Weather Emulators
• HealDA: Highlighting the Importance of Initial Errors in End-to-End AI Weather Forecasts
• Kilometer-Scale Convection-Allowing Model Emulation Using Generative Diffusion Modeling
• Learning Accurate Storm-Scale Evolution from Observations
• Subseasonal forecasting and MJO teleconnections in machine learning weather prediction models
• Surface Temperature Extremes Produced by Huge Machine Learning Hindcasts of Summer 2023
• Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Models
• Generative Data Assimilation of Sparse Weather Station Observations at Kilometer Scales
• Predict Extreme Weather Events in Minutes Without a Supercomputer
• ClimSim-Online: A Large Multi-Scale Dataset and Framework for Hybrid Physics-ML Climate Emulation
• Adaptive Flow Matching for Resolving Small-Scale Physics
• Stable Machine-Learning Parameterization of Subgrid Processes in a Comprehensive Atmospheric Model Learned From Embedded Convection-Permitting Simulations
• Heavy-Tailed Diffusion Models
• AI Chases the Storm: New NVIDIA Research Boosts Weather Prediction, Climate Simulation
• ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation