Litcius/Paper detail

Predicting glass transition temperature and melting point of organic compounds <i>via</i> machine learning and molecular embeddings

Tommaso Galeazzo, Manabu Shiraiwa

2022Environmental Science Atmospheres41 citationsDOIOpen Access PDF

Abstract

We developed tgBoost a machine learning model to predict glass transition temperature ( T g) of organic species considering their molecular structure and functionality for better predictions of the phase state of secondary organic aerosols.

Topics & Concepts

Melting pointGlass transitionPhase transitionMelting temperatureTransition (genetics)Point (geometry)ThermodynamicsMaterials scienceChemical physicsStatistical physicsComputer scienceChemistryPhysicsMathematicsComposite materialPolymerGeometryGeneBiochemistryAtmospheric chemistry and aerosolsGlass properties and applicationsOptical properties and cooling technologies in crystalline materials
Predicting glass transition temperature and melting point of organic compounds <i>via</i> machine learning and molecular embeddings | Litcius