Xiaoxu Tian
@xiaoxutian.bsky.social
Weather Analyst and NWP/DA scientist specializing in weather-driven energy impacts and forecasting. Opinions are my own.
Reposted by Xiaoxu Tian
🚨 WeatherBench Update
1. WeatherBench-X, our new evaluation code, is now on GitHub: github.com/google-resea...
2. New models (plus other small updates) on the WeatherBench website: sites.research.google/weatherbench/
1/n
1. WeatherBench-X, our new evaluation code, is now on GitHub: github.com/google-resea...
2. New models (plus other small updates) on the WeatherBench website: sites.research.google/weatherbench/
1/n
GitHub - google-research/weatherbenchX: A modular framework for evaluating weather forecasts
A modular framework for evaluating weather forecasts - google-research/weatherbenchX
github.com
February 13, 2025 at 7:38 AM
🚨 WeatherBench Update
1. WeatherBench-X, our new evaluation code, is now on GitHub: github.com/google-resea...
2. New models (plus other small updates) on the WeatherBench website: sites.research.google/weatherbench/
1/n
1. WeatherBench-X, our new evaluation code, is now on GitHub: github.com/google-resea...
2. New models (plus other small updates) on the WeatherBench website: sites.research.google/weatherbench/
1/n
🌩️ Excited to share my work on Jacobian-Enforced Neural Networks (JENN)! JENN fills the gap between ML weather models & data assimilation, enhancing sensitivity (Jacobian) accuracy without compromising forecasts. A game-changer for tools like GraphCast, Pangu & NeuralGCM! 🌍 #ML #WeatherForecasting
Jacobian-Enforced Neural Networks (JENN) for Improved Data Assimilation Consistency in Dynamical Models
Machine learning-based weather models have shown great promise in producing accurate forecasts but have struggled when applied to data assimilation tasks, unlike traditional numerical weather predicti...
arxiv.org
December 3, 2024 at 12:24 PM
🌩️ Excited to share my work on Jacobian-Enforced Neural Networks (JENN)! JENN fills the gap between ML weather models & data assimilation, enhancing sensitivity (Jacobian) accuracy without compromising forecasts. A game-changer for tools like GraphCast, Pangu & NeuralGCM! 🌍 #ML #WeatherForecasting
ML weather models like GraphCast & NeuralGCM show promise in weather forecasting, but can they be used for data assimilation? Our study looks into their tangent linear & adjoint models, finding challenges in robustness & unphysical noise. 🌦️ #AI #NWP
arxiv.org/abs/2411.14677
arxiv.org/abs/2411.14677
Exploring the Use of Machine Learning Weather Models in Data Assimilation
The use of machine learning (ML) models in meteorology has attracted significant attention for their potential to improve weather forecasting efficiency and accuracy. GraphCast and NeuralGCM, two prom...
arxiv.org
November 25, 2024 at 2:23 AM
ML weather models like GraphCast & NeuralGCM show promise in weather forecasting, but can they be used for data assimilation? Our study looks into their tangent linear & adjoint models, finding challenges in robustness & unphysical noise. 🌦️ #AI #NWP
arxiv.org/abs/2411.14677
arxiv.org/abs/2411.14677