The project

The Helmholtz Representation Model for Climate Science (HClimRep) project seeks to leverage the success of foundation modeling in weather forecasting and apply it to climate timescales. This pioneering initiative focuses on developing a comprehensive AI‑based climate model that captures the complex interactions among the atmosphere, ocean, and sea ice across seasonal to decadal time scales.

Our Prototype

The HClimRep prototype is based on the WeatherGenerator framework and aims to extend it by incorporating additional vertical levels of the atmosphere and additional Earth system compartments (e.g., oceanic fields).

Research Objectives

Our goal is to build a Foundation Model for Climate Science that:

The following simulations showcase the current outcomes associated with each research objective. These visualisations reflect the latest stage of the project’s research and will be updated as the work progresses.

 1. Delivers reliable AI‑based simulations across extended timescales

2. Captures atmospheric dynamics from the lower troposphere through the stratosphere

3. Represents ocean and sea‑ice interactions with high fidelity

4. Adapts seamlessly to diverse downstream applications.

Project structure

The HClimRep project is organized into 10 work packages (WPs). The project spans two phases, with foundational model extensions in Phase 1 and the construction of a novel, multi-scale and multi-compartment model in Phase 2.

Phase 1 (Month 1-15)

WP 1

Onboaring

Objective

Build a community, provide training, support project partners, and organize a hackathon.

Done 100%

WP 2

AtmoRep Extension to the stratosphere (StratoRep)

Objective:

Extend AtmoRep to include stratospheric data and tracers, develop training concepts, and evaluate model performance.

Done 100%

WP 3

OceanRep Prototype Development

Objective

Develop processing strategies for ocean model data, pre-train OceanRep, build a sea ice component, and evaluate the model.

Done 100%

WP 4

Enable long-term Simulations

Objective

Develop strategies for long-term simulations of AtmoRep and OceanRep for seasonal to decadal timescales.

Done 50%

Phase 2 (Month 15-36)

WP 5

HClimRep Concept Development

Objective

Develop the model architecture and training strategies for multi-resolution, multi-model integration.

Done 33%

WP 6

HClimRep Core Model Development

Objective

Implement HClimRep code, perform test runs, and optimize training performance.

Done 33%

WP 7

Pre-training of HClimRep

Objective

Supervise pre-training experiments, monitor performance, and evaluate model checkpoints.

5%

WP 8

Exploration of Downstream Tasks

Objective

Develop embedding networks for downstream applications, fine-tune, and evaluate results.

Done 20%

The following two work packages span throughout the entire project duration:

WP 9

Data Management

Objective

Manage input and output data, prepare data publications, and ensure data accessibility.

Done 100%

WP 10

Project Coordination

Objective

Coordinate project activities, maintain the project website, organize meetings, and monitor progress.

Done 70%