Neural networks are gaining widespread relevance for their versatility, holding the promise to yield a significant methodological shift in different domain of applied research. Here, we provide a simple pedagogical account of the basic functioning of a feedforward neural network. Then we move forward to reviewing two recent applications of machine learning to Earth and Materials Science. We will in particular begin by discussing a neural network based geothermobarometer, which returns reliable predictions of the pressure/temperature conditions of magma storage. Further, we will turn to illustrate how machine learning tools, tested on the list of minerals from the International Mineralogical Association, can help in the search for novel superconducting materials.
A short introduction to neural networks and their application to Earth and Materials Science / D. Fanelli, L. Bindi, L. Chicchi, C. Pereti, R. Sessoli, S. Tommasini. - In: RENDICONTI LINCEI. SCIENZE FISICHE E NATURALI. - ISSN 2037-4631. - ELETTRONICO. - 35:(2024), pp. 881-892. [10.1007/s12210-024-01271-8]
A short introduction to neural networks and their application to Earth and Materials Science
D. Fanelli
;L. BindiMembro del Collaboration Group
;L. ChicchiMembro del Collaboration Group
;R. SessoliMembro del Collaboration Group
;S. TommasiniMembro del Collaboration Group
2024
Abstract
Neural networks are gaining widespread relevance for their versatility, holding the promise to yield a significant methodological shift in different domain of applied research. Here, we provide a simple pedagogical account of the basic functioning of a feedforward neural network. Then we move forward to reviewing two recent applications of machine learning to Earth and Materials Science. We will in particular begin by discussing a neural network based geothermobarometer, which returns reliable predictions of the pressure/temperature conditions of magma storage. Further, we will turn to illustrate how machine learning tools, tested on the list of minerals from the International Mineralogical Association, can help in the search for novel superconducting materials.File | Dimensione | Formato | |
---|---|---|---|
Neural Network_geoscience.pdf
Accesso chiuso
Tipologia:
Pdf editoriale (Version of record)
Licenza:
Open Access
Dimensione
2.46 MB
Formato
Adobe PDF
|
2.46 MB | Adobe PDF | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.