Si avvisa che

in data 07-06-2022, alle ore 15:30 precise

presso il Politecnico di Milano, Dipartimento di Matematica, Aula Saleri sesto piano (Edificio 14 - La Nave),

nell’ambito delle attività del MOX, si svolgerà il seguente seminario:

Stefano Castruccio, University of Notre Dame

Titolo: Physics-Informed, Data-Driven and Hybrid Approaches to Space-Time Systems

Abstract: In this talk I will discuss two different approaches to characterize space-time systems. This first one is model-driven and loosely inspired by physics, assumes that the system is locally diffusive through a stochastic partial differential equation, and can be efficiently approximated with a Gaussian Markov random field. This approximation will be used to produce a stochastic generator of simulated multi-decadal global temperature, thereby offering a fast alternative to the generation of large climate model ensembles. The second approach is instead data-driven, and relies on (deep) neural networks in time. Instead of traditional machine learning methods aimed at inferring an extremely large parameter space, we instead rely on an alternative fast, sparse and computationally efficient echo state network dynamics on an appropriately dimensionally reduced spatial field. The additional computational time is then used to produce an ensemble and probabilistically calibrate the forecast. The approach will be used to produce air pollution forecasts from a citizen science network in San Francisco and forecasting wind energy in Saudi Arabia. Towards the end of the presentation, I will discuss how these two broad frameworks could be used in synergy to allow for improved predictability and understanding of space-time systems whose physical understanding is currently limited and/or largely influenced by parametrizations.

Link: https://mox.polimi.it/mox-seminars/?id_evento=2169

Il link per seguire il seminario online sarà reso disponibile su Link zoom: https://polimi-it.zoom.us/j/91015435557

L’evento è patrocinato da GRASPA https://graspa.org

Tutti gli interessati sono cordialmente invitati a partecipare, Laura Sangalli

—— Laura Maria Sangalli MOX - Dipartimento di Matematica Politecnico di Milano Piazza Leonardo da Vinci 32 20133 Milano - Italy tel: +39 02 2399 4554 fax: +39 02 2399 4568 email: laura.sangalli@polimi.itmailto:laura.sangalli@polimi.it url: http://mox.polimi.it/~sangalli