repowisegoogle-research/arco-era5

google-research / arco-era5

Recipes for reproducing Analysis-Ready & Cloud Optimized (ARCO) ERA5 datasets.

Python★ 508
Use in your agentAsk this codebase

github.com/google-research/arco-era5Indexed at c33bb37Up to date with upstream

What is arco-era5?

arco-era5 is a set of recipes for reproducing Analysis-Ready and Cloud Optimized ERA5 datasets for cloud-based climate analysis and machine learning workflows. It converts GRIB data to Zarr and creates regular latitude-longitude versions with preprocessing and chunk optimization. The project is primarily written in Python, with Dockerfile and shell files.

Written by a model from the README and the source

41 files and 262 symbols in 6 modules, led by Python (32 files) and Dockerfile (3).

Start reading

Code health

9.2out of 10Excellent
Full health report

Use google-research/arco-era5 in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/google-research/arco-era5
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is arco-era5 put together?")
  • get_why("why is arco-era5 structured this way?")

Explore arco-era5

Key features of arco-era5

  • arco-era5 converts GRIB data to Zarr without other data modifications for its cloud-optimized ERA5 output.
  • arco-era5 creates analysis-ready ERA5 datasets on regular latitude-longitude grids for research and machine learning workflows.
  • arco-era5 provides raw GRIB and NetCDF data alongside cloud-optimized and analysis-ready dataset forms.
  • arco-era5 supports reproducible processing through scripts and documented cloud deployment steps.
  • arco-era5 includes processing for meteorologically valuable land and atmosphere variables.

How google-research/arco-era5 works

arco-era5 uses scripts in src to process ERA5 data through ingestion and dataset-generation stages. The raw directory handles raw data inputs, while data_automate contains automation for recurring processing. The deployment directory defines cloud job setup, including deployment/create_job.py, which creates Cloud Run jobs. The resulting data is organized into raw, cloud-optimized, and analysis-ready Zarr stores. The docs directory provides project documentation, and root-level configuration files support installation and execution.

The codebase has 41 files and 262 symbols in 6 modules, led by Python, Dockerfile and Shell. Code health is 9.2 out of 10, rated excellent.

Getting started with arco-era5

  1. Change into the project directory and install it with pip.
    cd arco-era5
  2. Install the project in editable mode.
    pip install -e .

Commands copied from the README

google-research/arco-era5 FAQ

What is arco-era5?

arco-era5 provides recipes for reproducing Analysis-Ready and Cloud Optimized ERA5 datasets. It produces Zarr data for cloud-based climate analysis and machine learning workflows.

How does arco-era5 work?

arco-era5 converts ERA5 GRIB data to Zarr and creates regular latitude-longitude datasets with preprocessing and chunk optimization. Its scripts support raw ingestion, automated processing, and cloud job deployment.

How do I install arco-era5?

Install arco-era5 by cloning the repository, changing into its directory, and running pip install -e .. Cloud deployment also requires configured cloud storage, permissions, licenses, and environment variables.

What language is arco-era5 written in?

arco-era5 is primarily written in Python. The repository also includes Dockerfile and shell files.

How is the arco-era5 code organized?

arco-era5 places core processing code in src, raw inputs in raw, automation in data_automate, deployment code in deployment, and documentation in docs. The deployment/create_job.py script creates cloud jobs.

Who is arco-era5 for?

arco-era5 is for researchers and machine learning workflows that use cloud-accessible ERA5 data. It offers both preprocessed analysis-ready data and cloud-optimized data for users who need control over interpolation.

What license does arco-era5 use?

arco-era5 uses the Apache-2.0 license.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of google-research/arco-era5 from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.