BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Computational materials design with machine learning and atomistic
  simulations
DTSTART:20230404T153000
DTEND:20230404T163000
DTSTAMP:20260408T085306Z
UID:46a9e0d41e582b4e0d01a55c4e08fd163ddca80ad5ed38529e6a5539
CATEGORIES:Conferences - Seminars
DESCRIPTION:Rafael Gomez-Bombarelli is the Jeffrey Cheah Career Developmen
 t Professor in MIT's Department of Materials Science and Engineering. His 
 work aims to fuse machine learning and atomistic simulations for designing
  materials and their transformations. Through collaborations at MIT and be
 yond\, Rafael’s group develops new practical materials such as catalysts
 \, therapeutic peptides\, organic electronics or electrolytes for batterie
 s.\n\nRafael joined MIT in 2018 after earning BS\, MS\, and PhD (2011) deg
 rees in chemistry from Universidad de Salamanca (Spain) and carrying postd
 octoral work at Heriot-Watt\, Harvard and at Kyulux North America. His mac
 hine learning work has received faculty awards from the Dreyfus Foundation
  and Google. Rafael was a co-founder of Calculario\, a Harvard spinout com
 pany\, and served as Chief Learning Officer of ZebiAI\, a drug discovery s
 tartup.\nDesigning new materials is vital for addressing pressing societal
  challenges in health\, energy\, and sustainability. The computational tec
 hniques of atomistic simulation and machine learning (ML) offer an avenue 
 to rapidly invent new materials and navigate this enormous space. By popu
 lating the continuum between physics-based simulations and machine learnin
 g\, the Learning Matter Lab seeks to enable rapid\, computation-first de
 sign of materials that accelerate the materials discovery cycle. \n\nAtom
 istic simulations\, using techniques from quantum mechanics or statistical
  mechanics can predict the properties of hypothetical materials\, and by e
 ngineering high-throughput simulation pipelines\, Gomez-Bombarelli can eva
 luate millions of candidates and find compositions or structures that opti
 mize a given property. Simulations are\, nevertheless\, relatively costly\
 , and may lack accuracy compared to experiment. This is where the synergy 
 with ML enables a new paradigm: surrogate models bypass simulations by int
 erpolating among pre-existing calculations at a fraction of the cost\, whi
 le embedding physics-based priors in ML ensures robustness and transferabi
 lity.\n\n 
LOCATION:https://epfl.zoom.us/j/68447908297?pwd=OU5JUGJUSUhZc0ZNYjQ2WENvYl
 NRdz09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR