Layer-wise relevance propagation for backbone identification in discrete fracture networks
| Autor: | Francesco Vaccarino, Sandra Pieraccini, Francesco Della Santa, Antonio Mastropietro, Stefano Berrone |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Discrete fracture
Neural Networks General Computer Science Artificial neural network business.industry Computer science Discrete Fracture Networks Deep learning Feature selection Topology Theoretical Computer Science Layer-wise Relevance Propagation Identification (information) Deep Learning Flow (mathematics) Modeling and Simulation Fracture (geology) Relevance (information retrieval) Artificial intelligence Discrete Fracture Networks Neural Networks Deep Learning Layer-wise Relevance Propagation Feature Selection Feature Selection business |
| Zdroj: | Journal of Computational Science. 55:101458 |
| ISSN: | 1877-7503 |
| Popis: | 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 analyze clogging or leakage, relevant for example in waste storage problems, or to reduce the computational cost of simulations. With a suitably trained Neural Network at hand, we use the Layer-wise Relevance Propagation as a feature selection method to detect the expected relevance of each fracture in a Discrete Fracture Network and thus identifying the backbone. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect