PORTO @ 
Archivio Istituzionale della Ricerca
IRIS è la soluzione IT che facilita la raccolta e la gestione dei dati relativi alle attività e ai prodotti della ricerca. Fornisce a ricercatori, amministratori e valutatori gli strumenti per monitorare i risultati della ricerca, aumentarne la visibilità e allocare in modo efficace le risorse disponibili.
EnglishIn the framework of flow simulations in Discrete Fracture Networks, we consider the problem of identifying possible backbones, namely preferential channels in the network. Backbones can indeed be fruitfully used to reduce the computational cost of simulations or to analyze clogging and waste storage problems. With a suitably trained Neural Network at hand, we use the Layer-wise Relevance Propagation method to detect the relevance of each fracture in a Discrete Fracture Network and thus identifying the backbone.
Backbone Identification in Discrete Fracture Networks Using Layer-Wise Relevance Propagation for Neural Network Feature Selection / Berrone, Stefano; Della Santa, Francesco; Mastropietro, Antonio; Pieraccini, Sandra; Vaccarino, Francesco. - ELETTRONICO. - (2020).
| Titolo: | Backbone Identification in Discrete Fracture Networks Using Layer-Wise Relevance Propagation for Neural Network Feature Selection | |
| Autori: | ||
| Data di pubblicazione: | 2020 | |
| Abstract: | In the framework of flow simulations in Discrete Fracture Networks, we consider the problem of identifying possible backbones, namely preferential channels in the network. Backbones can indeed be fruitfully used to reduce the computational cost of simulations or to analyze clogging and waste storage problems. With a suitably trained Neural Network at hand, we use the Layer-wise Relevance Propagation method to detect the relevance of each fracture in a Discrete Fracture Network and thus identifying the backbone. | |
| Appare nelle tipologie: | 5.12 Altro |
File in questo prodotto:
http://hdl.handle.net/11583/2844659
Copyright © 2021