Skip to main content
European Commission logo
italiano italiano
CORDIS - Risultati della ricerca dell’UE
CORDIS

Realistic and Informative Simulations with machine learnING

Descrizione del progetto

Simulazioni migliorate per l’osservazione delle stelle

Il nostro interesse nell’astronoma risale a tempi antichi. L’astronomia, incentivata da sviluppi e miglioramenti, nonché dall’impiego di apparecchiature più avanzate e da conoscenze scientifiche approfondite, continua a essere oggi un campo di studi con molto seguito. Attualmente, la ricerca astronomica dipende in grande misura dalle simulazioni. Sfortunatamente, non esistono modi per misurare in termini pratici la realisticità delle simulazioni e le simulazioni numeriche tendono a essere troppo lente e costose per la prototipazione di nuove tecniche o per il miglioramento del significato statistico. Il progetto RISING, finanziato dall’UE, affronterà queste problematiche sviluppando un quadro comprendente strumenti di apprendimento automatico per diversi utilizzi, che troverà un’applicazione immediata nelle simulazioni dinamiche degli ammassi stellari e nelle simulazioni idrodinamiche delle loro nubi madri.

Obiettivo

Contemporary astronomical research relies heavily on simulations. However, the current state of the art has no objective way to measure how `realistic’ a simulation is, nor how informative it is with respect to the scientific questions it was designed to address. Comparison between simulation and observation is left to the subjective judgment of the individual researcher. The set up of simulation sets, the choice of parameters and ingredients to include, and the number of runs to execute are all also left to the researcher’s preferences, given hardware constraints. Numerical astronomy has, as of now, no shared standard of experiment design. Additionally, numerical simulations are often so slow and expensive that it is impossible to quickly and cheaply produce new outputs to improve statistical significance or for rapid prototyping new techniques. To address these issues, I will develop the RISING framework. RISING (Realistic and Informative Simulations with machine learnING) is a bundle of machine learning tools: anomaly detection tools to measure the realism of simulations, active learning tools to plan optimal sets of simulations under resource constraints, and generative modeling tools to obtain credible simulation outputs without running the underlying simulation. RISING will find immediate application on dynamical simulations of star clusters and hydrodynamical simulations of their parent clouds, which are being run in large numbers by the ERC-funded DEMOBLACK group led by my host, Prof. Michela Mapelli. RISING will be written in Python 3.7 using the Keras API on top of Tensorflow, integrated with frameworks for multi-scale, multi-physics simulations, such as AMUSE , whose author is Prof. Portegies-Zwart (Leiden Univ.) with which Prof. Mapelli has a current ongoing collaboration. The source code of RISING and selected data products will be made freely available to the numerical astronomy community.

Coordinatore

UNIVERSITA DEGLI STUDI DI PADOVA
Contribution nette de l'UE
€ 255 768,00
Indirizzo
VIA 8 FEBBRAIO 2
35122 Padova
Italia

Mostra sulla mappa

Regione
Nord-Est Veneto Padova
Tipo di attività
Higher or Secondary Education Establishments
Collegamenti
Costo totale
€ 255 768,00

Partner (1)