This page provides an overview of how to access and use WeatherNext forecasts in Google BigQuery. BigQuery is a serverless, highly scalable data warehouse that lets you analyze petabytes of data using standard SQL. It is an excellent choice for:
- Large-scale data analysis: Run complex analytical SQL queries on the entire WeatherNext dataset without worrying about infrastructure.
- Custom data integration: Easily join WeatherNext forecasts with your own datasets, such as business locations or sensor data, for deeper insights.
- Scalable machine learning: Use BigQuery ML to train, evaluate, and run machine learning models directly on the weather data.
Available datasets
WeatherNext provides its state-of-the-art weather forecasting models as public datasets in BigQuery, available through the Analytics Hub.
How to access the data
To access the datasets, you will need to fill out the WeatherNext Data Request form.
To query the data, you first need to add the datasets to your BigQuery project from the Analytics Hub listings linked above. Click "Add dataset to project" to subscribe.
When subscribing, you have to set a project name and a dataset name. After which, you can query the tables using those fully qualified names as follows:
WeatherNext Graph: [your project name].[your dataset name].59572747_4_0
WeatherNext Gen:
[your project name].[your dataset name].126478713_1_0
WeatherNext 2: [your project name].[your dataset name].weathernext_2_0_0
Starter guide and sample code
For an in-depth tutorial and sample code, check out the WeatherNext 2 Starter Guide - BigQuery notebook.
Things to be aware of
Terms of use
- Historical Data (forecasts more than 48 hours old): Licensed under the Creative Commons Attribution International License, Version 4.0 (CC BY 4.0).
- Real-Time Data (forecasts generated within past 48 hours): Made available under the GDM Real-Time Weather Forecasting Experimental Data Terms of Use.
Citations
If you use this data in your research, be sure to cite the appropriate papers and datasets. You can find the citation information on the dataset pages.