MAELSTROM presents a dataset to forecast the energy production of the near and mid-term future using machine learning. Weather forecast data of the past is used in conjunction with local production of energy to train a tool that can predict power production based on weather forecasts.
MAELSTROM presents a novel dataset to enable the users to explore deep learning methods for 2m temperature downscaling. This dataset includes 2m temperature and surface elevation.
MAELSTROM offers a benchmark machine learning dataset for temperature at 850 hPa and geopotential at 500hPa ensemble forecasts. The dataset consists of T (Temperature), Z(Geopotential), U (U component of wind), V (V component of wind), D (Divergence), W (Vertical velocity) and Q (Specific humidity) input variables with 11 ensemble members at 11 pressure levels and are based hindcast simulations of the European Centre for Medium Range Weather Forecasts. This dataset enables users to learn how to use deep learning for post-processing of ensemble weather forecasts.
MAELSTROM offers new datasets for 2m temperature and hourly precipitation short-range forecasts over Nordics/Northern Europe. The dataset consists of several terabytes of real-time observations and forecast outputs, which is provided on a 1796x2321 grid 47 input variables and 60 forecast lead times. This dataset allows the users to explore the use of deep learning for 2m temperature and precipitation predictions.
Now available for public use: This dataset enables the use of machine learning to learn the process of radiative heating -- one of the key processes in weather and climate models. The dataset will be available in several tiers with different sizes up to several terabytes. It enables users to accelerate the representation of interactions between the radiation from the sun and the Earth, and the vertical structure of the atmosphere, including clouds. The dataset has a very high resolution of 137 levels in the vertical direction.
If you want to learn more about the first versions of machine learning tools and solutions, including architectures and loss functions, that will be studied for the six machine learning benchmark datasets, you can check this report. We present the results of a survey of customized machine learning solutions and tools that MAELSTROM applications will adopt.
This report will present the first set of customized machine learning solutions that have been developed for the six MAELSTROM applications. Please have a look at the document, download the data, train your own machine learning solution that is beating our benchmark, and let us know!
How much better did we get and how efficient are our solutions on high performance computing architectures? If you are interested, please have a look at this report.
A high-risk high-gain task! This task will develop tangent linear and adjoint versions of the ML solutions that were developed to emulate the radiation and cloud parameterization schemes of the European Centre for Medium-Range Weather Forecasts. The tangent linear and adjoint versions of the neural network emulators will be tested within the 4DVar data assimilation framework within analysis experiments and the results will be reported here.
Are we ready to use machine learning solutions within operational weather and climate predictions? This report summarizes tests that run the six MAELSTROM machine learning applications as if they were used for operational predictions. The task will use the latest machine learning software framework and aims to develop production-ready products for weather and climate predictions.