Turbulence at the Exascale Podcast I had the immense pleasure of being invited by Sylvain Laizet (from Imperial College, London) to be part of his Turbulence at the Exascale podcast! Very fun and inspiring conversation, where we talked about simulations, AI, interpretability of deep-learning models and many more topics:https://www.youtube.com/watch?v=6fssvdha6e0https://www.youtube.com/watch?v=6fssvdha6e0
New article in Nature Machine Intelligence Our recent article published in Nature Machine Intelligence discusses the importance of interpretability of deep-learning models, in particular when used to achieve the Sustainable Development Goals: https://www.nature.com/articles/s42256-021-00414-y Do not miss the video discussion with the co-author of the study, Beril Sirmacek, where we talk about the implications for AI …
Online Lecture on AI, CFD and sustainability I was delighted to speak with the #NVIDIA #AI #TechnologyCenter about #artificialintelligence, #CFD and #sustainability ! You can find the whole #lecture below!https://www.youtube.com/watch?v=uAejPGr4Ywc#machinelearning #computationalfluiddynamics #fluidmechanics #sdgs2030 #sdgsimpact
Webinar by Steven Brunton on machine learning and fluid mechanics Yesterday we had the second #seminar of the #AdvancedComputing and #machinelearning thematic area at Engineering Mechanics, KTH Royal Institute of Technology. We were delighted to have Steven Brunton with us, who gave a very exciting presentation and discussed the potential of #machinelearningmodels in #fluidmechanics!#ai #deeplearning #neuralnetworks #datadrivenYou can find the video here: https://play.kth.se/media/AC%26ML+Seminar+Steven+Brunton/0_7uu61efp Share this article Share on twitter Share …
Master thesis on: Predicting the dynamics of coherent structures in turbulence through deep learning This project aims at using data-driven methods, in particular based on deep learning, to study the dynamics of the coherent structures in turbulent flows. We will focus on intense Reynolds-stress events and on vortical structures, and we will consider canonical wall-bounded …
New review paper on urban flows In our latest review paper we assess novel experimental, numerical and data-driven methods to study the flow in urban environments, with the aim of improving air quality and urban sustainability. This was developed in collaboration with Pablo Torres and Soledad Le Clainche. The article is available open access here: https://www.mdpi.com/1996-1073/14/5/1310 Below you can see a visualization from one of the …
New paper on COVID-19 contact-tracing smartphone apps Building on previous work regarding contact-tracing apps for COVID-19, we have developed a complete framework to analyze the technical, social and governance aspects of their deployment. We analyze a total of 17 apps and provide recommendations for their deployment! You can find the article open access here: https://www.mdpi.com/2071-1050/13/5/2912 …
New review paper on COVID-19 contact-tracing apps Leer más »
How to use deep learning in fluid mechanics? If you are interested in applying deep-learning tools to fluid mechanics and turbulence, perhaps you can find good ideas in my 2020 seminar delivered for the Australasian Fluid Mechanics Series. Here we discuss how to use recurrent neural networks (RNNs) for temporal predictions in turbulence, and convolutional …
