Layer-wise relevance propagation for backbone identification in discrete fracture networks

被引：3

作者：

Berrone, Stefano ^{[1
,3
,4
]}

Della Santa, Francesco ^{[1
,3
,4
]}

Mastropietro, Antonio ^{[1
,3
,5
]}

Pieraccini, Sandra ^{[2
,4
]}

Vaccarino, Francesco ^{[1
,3
,6
]}

机构：

[1] Politecn Torino, Dept Math Sci, Turin, Italy

[2] Politecn Torino, Dept Mech & Aerosp Engn, Turin, Italy

[3] Politecn Torino, SmartData PoliTO Ctr Big Data & Machine Learning, Turin, Italy

[4] INdAM GNCS Res Grp, Rome, Italy

[5] Addfor Ind Srl, Turin, Italy

[6] ISI Fdn, Turin, Italy

来源：

JOURNAL OF COMPUTATIONAL SCIENCE | 2021年 / 55卷

关键词：

Layer-wise Relevance Propagation; Deep Learning; Neural Networks; Discrete Fracture Network; Feature selection; TRANSIENT DARCY FLOW; HYBRID MORTAR METHOD; STEADY-STATE METHOD; SOLVING FLOW; MODELING FLOW; POROUS-MEDIA; SIMULATIONS; MATRIX; COMPUTATION;

D O I：

10.1016/j.jocs.2021.101458

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

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.

引用

页数：16

共 50 条

[1] Interpreting Convolutional Neural Networks via Layer-Wise Relevance Propagation
Jia, Wohuan
Zhang, Shaoshuai
Jiang, Yue
Xu, Li
ARTIFICIAL INTELLIGENCE AND SECURITY, ICAIS 2022, PT I, 2022, 13338 : 457 - 467
[2] Explaining Therapy Predictions with Layer-wise Relevance Propagation in Neural Networks
Yang, Yinchong
Tresp, Volker
Wunderle, Marius
Fasching, Peter A.
2018 IEEE INTERNATIONAL CONFERENCE ON HEALTHCARE INFORMATICS (ICHI), 2018, : 152 - 162
[3] Layer-Wise Relevance Propagation for Neural Networks with Local Renormalization Layers
Binder, Alexander
Montavon, Gregoire
Lapuschkin, Sebastian
Mueller, Klaus-Robert
Samek, Wojciech
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT II, 2016, 9887 : 63 - 71
[4] Evaluating Layer-wise Relevance Propagation Explainability Maps for Artificial Neural Networks
Ranguelova, Elena
Pauwels, Eric J.
Berkhout, Joost
2018 IEEE 14TH INTERNATIONAL CONFERENCE ON E-SCIENCE (E-SCIENCE 2018), 2018, : 377 - 378
[5] Explanation of Multi-Label Neural Networks with Layer-Wise Relevance Propagation
Bello, Marilyn
Napoles, Gonzalo
Vanhoof, Koen
Garcia, Maria M.
Bello, Rafael
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
[6] Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation
Sarmiento, Paulo Yanez
Witzke, Simon
Klein, Nadja
Renard, Bernhard Y.
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: RESEARCH TRACK, PT IV, ECML PKDD 2024, 2024, 14944 : 336 - 351
[7] A Visual Designer of Layer-wise Relevance Propagation Models
Huang, Xinyi
Jamonnak, Suphanut
Zhao, Ye
Wu, Tsung Heng
Xu, Wei
COMPUTER GRAPHICS FORUM, 2021, 40 (03) : 227 - 238
[8] Layer-Wise Relevance Propagation with Conservation Property for ResNet
Otsuki, Seitaro
Iida, Tsumugi
Doublet, Felix
Hirakawa, Tsubasa
Yamashita, Takayoshi
Fujiyoshi, Hironobu
Sugiura, Komei
COMPUTER VISION-ECCV 2024, PT XLIII, 2025, 15101 : 349 - 364
[9] Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
Iwana, Brian Kenji
Kuroki, Ryohei
Uchida, Seiichi
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 4176 - 4185
[10] ASL: Adversarial Attack by Stacking Layer-wise Relevance Propagation
Wang, Pengju
Liu, Jing
PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 796 - 801

← 1 2 3 4 5 →