Description du projet
Des solutions d’apprentissage automatique personnalisées pour les modèles météorologiques et climatiques
Le changement climatique étant décrit comme la plus grande menace à laquelle l’homme moderne ait jamais été confronté, il est essentiel de développer les outils nécessaires pour faire face à ses effets potentiels. L’apprentissage automatique peut contribuer à améliorer la modélisation météorologique et climatique. Dans cette optique, le projet MAELSTROM, financé par l’UE, a pour objectif d’améliorer l’architecture informatique européenne afin de faciliter l’évaluation des impacts climatiques futurs. Concrètement, il fera progresser les conceptions de système de calcul pour des performances d’application et une efficacité énergétique optimales, un cadre logiciel pour optimiser la convivialité et l’efficacité de la formation pour un apprentissage automatique à l’échelle, et des applications d’apprentissage automatique à grande échelle pour le domaine des sciences météorologiques et climatiques. Il concevra des systèmes de calcul personnalisés, optimisés pour les besoins des applications, afin de renforcer le portefeuille européen de calcul intensif.
Objectif
To develop Europe’s computer architecture of the future, MAELSTROM will co-design bespoke compute system designs for optimal application performance and energy efficiency, a software framework to optimise usability and training efficiency for machine learning at scale, and large-scale machine learning applications for the domain of weather and climate science.
The MAELSTROM compute system designs will benchmark the applications across a range of computing systems regarding energy consumption, time-to-solution, numerical precision and solution accuracy. Customised compute systems will be designed that are optimised for application needs to strengthen Europe’s high-performance computing portfolio and to pull recent hardware developments, driven by general machine learning applications, toward needs of weather and climate applications.
The MAELSTROM software framework will enable scientists to apply and compare machine learning tools and libraries efficiently across a wide range of computer systems. A user interface will link application developers with compute system designers, and automated benchmarking and error detection of machine learning solutions will be performed during the development phase. Tools will be published as open source.
The MAELSTROM machine learning applications will cover all important components of the workflow of weather and climate predictions including the processing of observations, the assimilation of observations to generate initial and reference conditions, model simulations, as well as post-processing of model data and the development of forecast products. For each application, benchmark datasets with up to 10 terabytes of data will be published online for training and machine learning tool-developments at the scale of the fastest supercomputers in the world. MAELSTROM machine learning solutions will serve as blueprint for a wide range of machine learning applications on supercomputers in the future.
Champ scientifique
- natural sciencesearth and related environmental sciencesatmospheric sciencesmeteorology
- natural sciencesearth and related environmental sciencesatmospheric sciencesclimatology
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringcomputer hardwaresupercomputers
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
- natural sciencescomputer and information sciencessoftwaresoftware applications
Programme(s)
Régime de financement
RIA - Research and Innovation actionCoordinateur
RG2 9AX Reading
Royaume-Uni