{"categories":[{"label":"Atmospheric Science","url":"https://skillfed.io/packages/category/scientific-engineering-atmospheric-science"}],"enrichment":{"capability":"Herbie downloads numerical weather prediction model data (GRIB2 files) from NOAA, ECMWF, and other sources, then loads it into xarray for analysis and visualization.","skillfed_tags":["weather-data","atmospheric-science","grib2"],"use_cases":["Download high-resolution HRRR surface forecasts for regional weather analysis or nowcasting applications.","Retrieve specific atmospheric variables (e.g., temperature at 850 mb) from global GFS forecasts for ensemble analysis.","Batch-download multiple forecast hours across a date range for machine learning training on weather patterns.","Access ECMWF IFS data for comparison with NOAA models in research or operational workflows.","Extract point-specific data (e.g., at a weather station location) from GRIB2 files without processing entire grids."],"what_it_does":"Herbie is a Python interface to numerical weather prediction model data from NOAA (HRRR, GFS, RAP, GEFS, NAM, and others), ECMWF (IFS, AIFS), and additional sources. It abstracts away the complexity of locating and downloading GRIB2 files from multiple archives (NOMADS, AWS, Google Cloud, Azure) by automatically searching available sources and downloading either full files or subsets by variable. The package integrates tightly with xarray and pandas, allowing you to load downloaded data directly into analysis-ready formats.\n\nTypical workflows involve creating a Herbie object with a date, model name, and product type, then either downloading raw GRIB2 files or reading specific variables directly into xarray Datasets. It includes a command-line interface for scripting and batch operations, plus built-in helpers for Cartopy-based mapping. The package is designed for researchers, meteorologists, and data scientists working with atmospheric forecasts\u2014both for real-time operational use and historical analysis.","worth_installing":"Yes. Herbie is actively maintained, has no known vulnerabilities, uses a permissive MIT license, and solves a real problem for weather data workflows. Install friction is low and dependencies are standard scientific Python packages. Suitable for research, operational meteorology, and data science projects involving atmospheric forecasts."},"id":"herbie-data","links":{"html":"https://skillfed.io/packages/herbie-data","md":"https://skillfed.io/packages/herbie-data.md","pypi":"https://pypi.org/project/herbie-data/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-03-07","license_spdx":null,"license_treatment":"permissive","name":"herbie-data","python_support":"supports_current","summary":"Download numerical weather prediction GRIB2 model data."},"popularity":{"monthly_downloads":184844,"position":10023,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"2026.3.0"}