Giter Club home page Giter Club logo

opencastkit's Introduction

OpenCastKit: an open-source solutions of global data-driven high-resolution weather forecasting

简体中文 | English

本项目是由幻方AI团队复现优化,并开源的全球AI气象预报模型工具库。基于 FourCastNetGraphCast 的论文,我们构建了一个新的全球AI气象预报项目——OpenCastKit,它能够与欧洲中期天气预报中心(ECMWF)的传统物理模型——高分辨率综合预测系统(IFS),进行直接比较。

我们将基于1979年1月到2022年12月的ERA5数据训练出来的模型参数开源到 Hugging Face 仓库中,并上线了一个每日更新的 HF-Earth,展示模型的预测效果。

下面是一些预测案例:

台风路径预测与真实路径比较

汽水浓度预测与真实情况比较

依赖

  • hfai >= 7.9.5
  • torch >=1.8

训练

原始数据来自欧洲中期天气预报中心(ECMWF)提供的一个公开可用的综合数据集 ERA5 ,需要通过 data_factory/convert_ear5_hourly.py 脚本提出数据特征,转化为高性能训练样本格式 FFRecord 下的样本数据。

训练 FourCastNet

本地运行:

   python train_fourcastnet.py --pretrain-epochs 100 --fintune-epochs 40 --batch-size 4

也可以提交任务至幻方萤火集群,使用96张A100进行数据并行训练

   hfai python train_fourcastnet.py --pretrain-epochs 100 --fintune-epochs 40 --batch-size 4 -- -n 12 --name train_fourcastnet

训练 GraphCast

本地运行:

   python train_graphcast.py --epochs 200 --batch-size 2

也可以提交任务至幻方萤火集群,使用256张A100进行流水线并行训练

   hfai python train_graphcast.py --epochs 200 --batch-size 2 -- -n 32 --name train_graphcast

引用

@article{pathak2022fourcastnet,
  title={Fourcastnet: A global data-driven high-resolution weather model using adaptive fourier neural operators},
  author={Pathak, Jaideep and Subramanian, Shashank and Harrington, Peter and Raja, Sanjeev and Chattopadhyay, Ashesh and Mardani, Morteza and Kurth, Thorsten and Hall, David and Li, Zongyi and Azizzadenesheli, Kamyar and others},
  journal={arXiv preprint arXiv:2202.11214},
  year={2022}
}
@article{remi2022graphcast,
  title={GraphCast: Learning skillful medium-range global weather forecasting},
  author={Remi Lam, Alvaro Sanchez-Gonzalez, Matthew Willson, Peter Wirnsberger, Meire Fortunato, Alexander Pritzel, Suman Ravuri, Timo Ewalds, Ferran Alet, Zach Eaton-Rosen, Weihua Hu, Alexander Merose, Stephan Hoyer, George Holland, Jacklynn Stott, Oriol Vinyals, Shakir Mohamed, Peter Battaglia},
  journal={arXiv preprint arXiv:2212.12794},
  year={2022}
}

opencastkit's People

Contributors

vachelhu avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.