This page guides you through getting access to the WeatherNext model and setting
up your Google Cloud project. You can access the Model Card on [**Gemini
Enterprise Agent Platform Model
Garden**](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/weather-next-v2)
in the Google Cloud Console.

> [!NOTE]
> **Model Availability:** Only **WeatherNext 2** is
> available for on-demand deployment on Vertex AI. For operational forecast
> datasets from our latest model, see
> [WeatherNext 3](https://developers.google.com/weathernext/guides/models) and the
> [Quick Start](https://developers.google.com/weathernext/guides/access-forecast) guide.

## Build custom forecasts with WeatherNext 2

WeatherNext 2 on Gemini Enterprise Agent Platform gives you access to Google's
state-of-the-art weather model. Instead of consuming pre-computed, static
forecast datasets, you can now build applications that generate custom forecasts
on-demand, tuned to your specific technical requirements.

This approach provides a powerful set of capabilities:

- **Managed API:** Forecasts are generated using [persistent resources](https://docs.cloud.google.com/gemini-enterprise-agent-platform/machine-learning/training/persistent-resource-overview) or using [Dynamic Workload
  Scheduler](https://docs.cloud.google.com/gemini-enterprise-agent-platform/machine-learning/training/schedule-jobs-dws) on Gemini Enterprise Agent Platform. You can use a [Colab Enterprise
  notebook](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/weathernext/weathernext_2_ic_pc.ipynb) to manage and test the model and manage inference runs.
- **Granular Forecast Configuration:** Control the model's output using parameters to tailor each forecast to your use case:
  - **Probabilistic Forecasting:** Specify the number of **ensemble
    members** to quantify forecast uncertainty and build risk-aware applications.
  - **Custom Time Horizons:** Set the forecast **lead time** in hours for short-term operational needs or long-range strategic planning.
  - **Custom Initial Conditions:** Provide your own initial condition data to test different weather scenarios, use proprietary observations, or integrate alternative data sources such as GFS.
- **Cloud-Native Integration:** The model is designed for seamless integration with the Google Cloud ecosystem. Use the Zarr output in Google Cloud Storage to trigger event-driven workflows with [Cloud
  Functions](https://cloud.google.com/functions?e=48754805), run large-scale data transformations with [Dataflow](https://cloud.google.com/products/dataflow?e=48754805), or load results directly into BigQuery for analysis.

See the [working with the model](https://developers.google.com/weathernext/guides/working-vmg) page for
detailed instructions on configuring and running forecasts.

## Request access

To use WeatherNext 2 for generating forecasts, your Google Cloud project must be
added to an allowlist. To request access, contact your Google Cloud account team
or [reach out to
us](https://docs.google.com/forms/d/1o2GpGlXLAOkpNnH1E_3hyBG_-Lwr0pKUIMCNGqrNlhA/viewform?resourcekey=0-ltINY-zAkMWhHxC8aVUURQ).

Once your request is reviewed and approved, you will receive an email notifying
that your project has been added to the allowlist. Then you can begin using the
model.

[**View WeatherNext 2 on Gemini Enterprise Agent Platform**](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/weather-next-v2)

## Prerequisites

Once your project has been added to the allowlist, you will need the following:

1. A **Google Cloud Project** with billing enabled.
2. The **Gemini Enterprise Agent Platform API** enabled in your project.
3. **IAM Permissions** : Ensure your user account has the `Vertex AI User` role or equivalent permissions.
4. **GPU Quota** : Request quota for custom model training accelerators (`NVIDIA H100 80GB` or `NVIDIA A100 80GB` GPUs) in your chosen region. By default, GPU quota is set to 0. See the [quota increase
   request](https://developers.google.com/weathernext/guides/working-vmg#quota-increase-request) section for detailed instructions on which resource names to request based on your scheduling strategy.

## Things to be aware of

Your use of WeatherNext 2 on Gemini Enterprise Agent Platform is subject to the
[Google Cloud terms of use](https://cloud.google.com/terms/service-terms#1),
which you should familiarise yourself with. In particular, you (and your end
users) must not:

- Use WeatherNext 2 or the forecasts it generates to develop a similar or competing product or service;
- Use generated forecasts to: (a) substitute, replace, or circumvent the use of WeatherNext 2, directly or indirectly, or (ii) create or improve models similar to WeatherNext 2 unless as part of any authorised fine-tuning; and
- Reverse engineer or extract any components of WeatherNext 2.