This work describes the percolation phenomena in different structures through deep neural networks and previously calculated statistical data of percolation. Despite being relatively simple and easy to calculate at small scales, the percolation process is computationally time-consuming at large scales; here, a significant computation is necessary to determine if a cluster percolates or not. We propose to train deep neural networks on small systems and scale to large systems. Our results show a reasonable accuracy rate on recognition of images, particularly on fully convolutional neural networks for the continuum case, a recent improvement on classical convolutional neural networks, improving the recognition of percolation phenomena, portability, and scalability.
Skip Nav Destination
Article navigation
15 May 2023
IWOSP 2021, INTERNATIONAL WORKSHOP ON STATISTICAL PHYSICS
1–3 December 2021
Antofagasta, Chile
Research Article|
May 15 2023
Percolation detection using convolutional deep neural networks
Esteban Iriarte;
Esteban Iriarte
a)
1)
Departamento de Física, Facultad de Ciencias Exactas, Universidad Andrés Bello
, Chile
Search for other works by this author on:
Joaquín Peralta;
Joaquín Peralta
b)
1)
Departamento de Física, Facultad de Ciencias Exactas, Universidad Andrés Bello
, Chile
b)Corresponding author:[email protected]
Search for other works by this author on:
Claudia Loyola;
Claudia Loyola
1)
Departamento de Física, Facultad de Ciencias Exactas, Universidad Andrés Bello
, Chile
Search for other works by this author on:
Sergio Davis
Sergio Davis
1)
Departamento de Física, Facultad de Ciencias Exactas, Universidad Andrés Bello
, Chile
2)
Research Center on the Intersection in Plasma Physics, Matter and Complexity, P2mc
, Comisión Chilena de Energía Nuclear, Chile
Search for other works by this author on:
b)Corresponding author:[email protected]
a)
Electronic mail: [email protected]
AIP Conf. Proc. 2731, 050004 (2023)
Citation
Esteban Iriarte, Joaquín Peralta, Claudia Loyola, Sergio Davis; Percolation detection using convolutional deep neural networks. AIP Conf. Proc. 15 May 2023; 2731 (1): 050004. https://doi.org/10.1063/5.0133188
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
27
Views
Citing articles via
Design of a 100 MW solar power plant on wetland in Bangladesh
Apu Kowsar, Sumon Chandra Debnath, et al.
Inkjet- and flextrail-printing of silicon polymer-based inks for local passivating contacts
Zohreh Kiaee, Andreas Lösel, et al.
Production and characterization of corncob biochar for agricultural use
Praphatsorn Rattanaphaiboon, Nigran Homdoung, et al.
Related Content
Inference for unreliable grading: The case of recommendation letters
AIP Conf. Proc. (May 2023)
Applications of a neural network to detect the percolating transitions in a system with variable radius of defects
Chaos (August 2020)
Percolation approach to study connectivity in living neural networks
AIP Conference Proceedings (February 2007)
The Gas‐Sensing Characteristics Of Percolating 2‐D SnO 2 Nanowire Mats As A Platform For Electronic Nose Devices
AIP Conference Proceedings (May 2009)