BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Materials Informatics Applied to the Energy Sector
DTSTART:20260501T090000Z
DTEND:20260501T100000Z
DTSTAMP:20260515T143000Z
UID:indico-event-18598@indico.psi.ch
CONTACT:iurii.timrov@psi.ch
DESCRIPTION:Speakers: James Moraes de Almeida (LNNano/CNPEM (Brazilian Nan
 otechnology National Laboratory))\n\nMaterials informatics represents the 
 powerful convergence of high-throughput computational simulations\, Machin
 e Learning (ML)\, and Natural Language Processing (NLP) to accelerate mate
 rials discovery. While automated quantum and classical simulations have es
 tablished vast databases of material properties\, recent advancements in N
 LP and Large Language Models (LLMs) now enable the massive\, algorithmic e
 xtraction of materials data directly from scientific literature. By integr
 ating these diverse data sources to train robust ML algorithms\, we can ef
 ficiently predict material behavior and bypass computationally expensive c
 alculations. In this talk\, I will present practical applications of these
  synergistic techniques within the energy sector. Specifically\, I will di
 scuss large-scale literature data extraction using NLP and LLMs for high-e
 ntropy oxide phase prediction. Furthermore\, I will highlight the deployme
 nt of active machine learning workflows for selecting water/oil interface 
 surfactants and optimizing nanoparticles for the Hydrogen Evolution Reacti
 on (HER).\nPlease contact Dr. Timrov (iurii.timrov@psi.ch) if you want to 
 discuss with the speaker.\n\nhttps://indico.psi.ch/event/18598/
LOCATION:OSGA/EG6
URL:https://indico.psi.ch/event/18598/
END:VEVENT
END:VCALENDAR