Computer implemented processing method optimized for dynamically computing, discovery and generating new materials, comprising defining a material dataset including a property vector of emergent properties for each compound of the dataset, defining a target compound, defining a correlation matrix correlated to the compounds of the material dataset, applying a clustering algorithm identifying one or more communities close to the target compound and among them iteratively search or predict via ML a candidate compound that is closer to the target than a predetermined final threshold value reducing significantly the computational resources requested.
METODO DI ELABORAZIONE IMPLEMENTATO DA COMPUTER OTTIMIZZATO PER COMPUTARE, SCOPRIRE E GENERARE DINAMICAMENTE NUOVI MATERIALI
Bonetti Stefano;Bugliesi MIchele;Caldarelli Guido
2024
Abstract
Computer implemented processing method optimized for dynamically computing, discovery and generating new materials, comprising defining a material dataset including a property vector of emergent properties for each compound of the dataset, defining a target compound, defining a correlation matrix correlated to the compounds of the material dataset, applying a clustering algorithm identifying one or more communities close to the target compound and among them iteratively search or predict via ML a candidate compound that is closer to the target than a predetermined final threshold value reducing significantly the computational resources requested.| File | Dimensione | Formato | |
|---|---|---|---|
|
102024000015190.pdf
non disponibili
Tipologia:
Versione dell'editore
Licenza:
Copyright dell'editore
Dimensione
842.8 kB
Formato
Adobe PDF
|
842.8 kB | Adobe PDF | Visualizza/Apri |
I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.



