Training

Machine Learning for Earth Systems Modelling – three online courses

Understanding and modelling our planet is rapidly evolving as machine learning becomes increasingly central to Earth system sciences. Under the Destination Earth (DestinE) initiative, three online courses on Machine Learning (ML) for Earth systems modelling are being developed and offered in 2026. This series of three short online courses introduce participants to the fast-moving world of ML in Earth system modelling, from foundational concepts to advanced prediction and hands-on applications.

Whether you are a researcher, practitioner, or technical specialist from a meteorological service, climate centre, academic institute, or industry, this training series will help you build the skills and confidence to:

understand the fundamentals of machine learning in Earth system science,
apply ML concepts within the DestinE ecosystem, and
engage with next-generation artificial intelligence (AI) modelling tools.

All three courses will be taught by ECMWF and European experts in AI and Machine Learning in Weather prediction and Climate science.

Interested? Show your interest by filling in this form: Machine Learning in Earth System Science – form. You will receive an update when new learning materials or courses become available.

Content

Machine Learning Training

Course information

You will explore how core ML concepts and architectures work (without heavy mathematics) and how they are applied in Earth System Science. You will learn about the role of ML in DestinE and its Digital Twins, how ML complements traditional physics-based models, and how emerging AI prediction systems such as AIFS, GraphCast, and hybrid approaches are reshaping weather and climate modelling. The course also introduces key cross-cutting topics, including ethics, regulation, explainability, and responsible AI, as well as future directions in Earth systems modelling.

Learning activities include video lectures, interactive notebooks, quizzes, and real-world examples that will help you build a solid foundation in AI-driven Earth systems modelling. This course prepares you for the more hands-on Courses 2 and 3.

This course examines how machine learning is transforming numerical weather prediction and how these methods are being operationalised within the DestinE initiative.
Course 2 provides a comprehensive, hands-on exploration of modern AI-based prediction systems used in Earth System Science. You will work with real ML workflows, including data pipelines, neural architectures, model training, benchmarking, and the Anemoi ecosystem used within DestinE. .

Learning activities include guided notebooks, practical modelling exercises, and expert-led sessions that reflect real-world workflows used in next-generation Digital Twins. This course strengthens practical skills and prepares you for the advanced applications covered in Course 3.
.

This course explores the frontier of AI in environmental modelling and its emerging applications.

Course 3 focuses on cutting-edge applications of machine learning in weather and climate science. Topics include AI weather prediction models at scale, downscaling, fire and flood prediction, anomaly detection, hybrid and foundation models, ML-based data assimilation, and end-to-end observation-driven approaches. .
Learning activities include expert-led panels, technical walkthroughs, tutorials, and applied notebooks using Anemoi and other open-source tools. By the end of the course, you will be equipped to extend and apply ML methods within your own Earth System Science workflows.

Objectives

These three online courses introduce the principles, methods, and applications of machine learning in Earth System Science. It provides a structured pathway from conceptual understanding to operational practice. The courses explain how ML models are developed, evaluated, and integrated into weather and climate workflows, and how they complement physical modelling. You will learn about current AI-based prediction systems, data and compute requirements, hybrid modelling approaches, and emerging techniques shaping next-generation prediction.

After completing all three online courses, you will be able to:

Understand core ML concepts and their relevance to Earth observations and prediction
Understand real-world AI use cases, including AIFS and other prediction models
Identify and describe the ethical, regulatory, and societal aspects of AI adoption
Develop practical understanding of different machine learning types, training processes, and validation techniques in forecasting contexts.
Explain neural architectures (CNNs, GNNs, Transformers) and their role in representing atmospheric dynamics.
Explore and evaluate data management, optimization strategies, and compute requirements for large-scale model training.
Apply machine learning workflows to real-world case studies in prediction and modelling.
Explain advanced topics, including foundational models, hybrid neural–physics systems, and ML-based data assimilation.
Evaluate explainability, fine-tuning, and continual learning strategies in evolving prediction systems.

Target audience

The first online course (Foundations, context and new frontiers) mainly targets a broad audience of high-level information users and policy/decision makers from both public and private sectors, academia, and industry. This course will also be of interest to a technical audience of non-ML meteorologists who want to be onboarded into the world of ML.

The second course (Architectures, data, and prediction) and third course (Applications and new directions) are firmly aimed at a technical audience, typically with a scientific background in Earth sciences in its broadest sense. Learners are expected to have at least a basic familiarity with programming and a background knowledge of statistics. For the more advanced parts of these courses, a more advanced level of ML knowledge will be assumed.

More to explore

ECMWF is offering a wide range of training in the field of ML in Weather and Climate:

Massive Open Online Course (MOOC) in Machine Learning in Weather and Climate is a self-paced and fully-online course, guiding you from the basics of machine learning up to practical implementations of ML models in Python.
Discover Anemoi is a six-part series of training webinars that uncovers the key components of the Anemoi framework. Watch the recordings of all webinars below and see the presentation slides to learn how Anemoi works and how to use it.
Browse our training catalogue for all of our training resources on machine learning.

Find out more about AI in DestinE, how AI is being used in weather forecasting at ECMWF in the AIFS Blog, browse our machine learning Jupyter Notebooks on GitHub, and see all of our upcoming training courses.