Tag - uncertainty | ECMWF eLearning

Understanding Uncertainty in Weather Forecasts

Learn about the main sources of uncertainty in weather forecasting and how they are addressed in early warning systems.

Level: Others

Certification course: No

What you'll learn:

In this eLearning module, we explain the basics of weather forecast uncertainty and how it can be accounted for when communicating forecasts through a forecast ‘value chain’. In this module, your learning level will be assessed through a set of quiz questions.

Hide last updated info: No

Hide number of enrollments: No

Hide full description label: No

Atmospheric composition: No

Climate: No

Computing services and tools: No

Data applications: No

Forecasting: Yes

Machine learning: No

Numerical weather prediction: Yes

Click to enter this course

Category: Forecasting

The ECMWF sub-seasonal (extended range) forecasts: Introduction

Learn about sources of predictability, seasonal forecast skill and the ECMWF sub-seasonal forecasting system.

Level: Fundamentals

Certification course: No

What you'll learn:

An overview of ECMWF forecasts at medium, sub-seasonal and seasonal ranges
The basis of sub-seasonal forecasts
The ECMWF sub-seasonal ensemble forecasting system
Evaluation and performance of sub-seasonal forecasts

Full description:

Sub-seasonal (or extended range) forecasts provide outlooks up to 46 days. This lesson examines sources of predictability, seasonal forecast skill and the ECMWF sub-seasonal forecasting system.

Estimated duration: 40 minutes

Hide last updated info: No

Hide number of enrollments: No

Hide full description label: No

Atmospheric composition: No

Climate: No

Computing services and tools: No

Data applications: No

Forecasting: No

Machine learning: No

Numerical weather prediction: No

Click to enter this course

Category: Forecasting

Ensemble Forecasting: Sources of forecast uncertainty (introduction)

Learn about sources of error in NWP, how they are quantified, and how ensembles are evaluated.

Level: Fundamentals

Certification course: No

What you'll learn:

Sources of forecast uncertainty
How ensembles quantify forecast uncertainty
How to extract information from the ensemble and evaluate performance
Communicating uncertainty

Full description:

Ensembles are run to account for uncertainties in initial conditions. This lesson explores the sources of error in NWP, how they are quantified, and how ensembles are evaluated.

Estimated duration: 40 minutes

Hide last updated info: No

Hide number of enrollments: No

Hide full description label: No

Atmospheric composition: No

Climate: No

Computing services and tools: No

Data applications: No

Forecasting: No

Machine learning: No

Numerical weather prediction: Yes

Click to enter this course

Category: Forecasting

Representing model uncertainty with stochastic physics

Explore sources of uncertainty in NWP and how this is represented in the IFS using stochastic physics.

Level: Others

Certification course: No

What you'll learn:

Sources of model uncertainty
How model uncertainty is represented in ensemble forecasts, and in particular in the IFS
How process-level model uncertainty is accounted for, including the Stochastically Perturbed Parameterisation Tendencies scheme

Hide last updated info: No

Hide number of enrollments: No

Hide full description label: No

Atmospheric composition: No

Climate: No

Computing services and tools: No

Data applications: No

Forecasting: No

Machine learning: No

Numerical weather prediction: No

Click to enter this course

Category: Numerical Weather Prediction

Sources of Uncertainty

Learn about uncertainties and chaotic behaviour in NWP, why ensembles are needed and how they are used at ECMWF.

Level: Fundamentals

Certification course: No

What you'll learn:

Sources of forecast uncertainty and chaotic behaviour
Ensembles as a tool for capturing uncertainty and probabilistic prediction
ECMWF model setup, initial conditions

Estimated duration: 40 minutes

Hide last updated info: No

Hide number of enrollments: No

Hide full description label: No

Atmospheric composition: No

Climate: No

Computing services and tools: No

Data applications: No

Forecasting: No

Machine learning: No

Numerical weather prediction: No

Click to enter this course

Category: Numerical Weather Prediction

MLWC MOOC 2: Concepts of Machine Learning in Weather and Climate

Five modules covering decision trees, deep learning, uncertainty and generative models, and physics-guided approaches.

Level: Fundamentals

Certification course: No

What you'll learn:

The main concepts of data retrieval using CliMetLab
Theory and application of regression and decision trees
Theory underlying deep neural networks, and software tools to apply them to practical problems
Uncertainty quantification using Bayesian and generative approaches
Physics-constrained approaches

By the end of this course, participants should have a sound understanding of the theory underpinning key ML approaches, and how these can be applied in practice.

Prerequisites:

Please complete MOOC MLWC - 1. ML in Weather & Climate first, or ensure you are familiar with the topics covered there. Basic proficiency with Python, knowledge of statistics and experience in weather/climate is assumed.

Full description:

In this second tier of our MOOC on Machine Learning (ML) in Weather and Climate, we go deeper into the theory underpinning ML, and the tools that are used to implement it, using Python case studies in weather and climate.

This five-module course covers regression trees and random forests, explores workflows in ML, and dives deeper into the ingredients of deep neural networks, including architectures, training, tuning and evaluating models. We will also explore approaches to quantify uncertainty, including generative ML models and Bayesian neural networks. The last module covers physics-guided ML approaches with applications to post-processing.

This course is aimed at those with a technical/weather background, some experience in Python, and a solid understanding of statistics. Ideally you will have already taken Tier 1 of this MOOC or already be familiar with the concepts there.

This course features a mixture of interactive modules, webinar recordings, quizzes, podcasts, and contains a number of detailed code examples.

Please note that this course ran live in early 2023 and reflected the state of the art at that point in time.

Estimated duration: 14 hours

Hide last updated info: No

Hide number of enrollments: No

Hide full description label: No

Atmospheric composition: No

Climate: Yes

Computing services and tools: No

Data applications: No

Forecasting: No

Machine learning: No

Numerical weather prediction: No

Click to enter this course

Category: Machine Learning

Climate Projections

About climate projections, differences between climate models, and how to choose from climate projection data.

Level: Fundamentals

Certification course: No

What you'll learn:

What climate projections are
How to choose climate models
Where to find climate projections in the Climate Data Store
How to choose climate projection data

Hide last updated info: No

Hide number of enrollments: No

Hide full description label: No

Atmospheric composition: No

Climate: No

Computing services and tools: No

Data applications: No

Forecasting: No

Machine learning: No

Numerical weather prediction: No

Click to enter this course

Category: Climate

Uncertainty, Robustness and Confidence

This lesson teaches about sources of uncertainty in climate projections, what robust signals are, and when we can be confident in a change.

Level: Others

Certification course: No

What you'll learn:

The differences between uncertainty, robustness and confidence
How model data can be used to define robust messages
When you can be confident about a climate change signal and when not

Hide last updated info: No

Hide number of enrollments: No

Hide full description label: No

Atmospheric composition: No

Climate: No

Computing services and tools: No

Data applications: No

Forecasting: No

Machine learning: No

Numerical weather prediction: No

Click to enter this course

Category: Climate

uncertainty

Courses tagged with "uncertainty"