2022
DOI: 10.1103/physrevresearch.4.023174
|View full text |Cite
|
Sign up to set email alerts
|

Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
13
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
2

Relationship

1
8

Authors

Journals

citations
Cited by 43 publications
(13 citation statements)
references
References 34 publications
0
13
0
Order By: Relevance
“…A potential approach is to combine symbolic regression with DeepGS (Y. Chen et al, 2022;. We can expect to discover the close-form physics equation that describes the physical laws for soil moisture flow and contains soil hydraulic properties.…”
Section: Limitations and Future Perspectivesmentioning
confidence: 99%
See 1 more Smart Citation
“…A potential approach is to combine symbolic regression with DeepGS (Y. Chen et al, 2022;. We can expect to discover the close-form physics equation that describes the physical laws for soil moisture flow and contains soil hydraulic properties.…”
Section: Limitations and Future Perspectivesmentioning
confidence: 99%
“…It has been demonstrated that failing to include correct candidate terms is likely to result in a non‐parsimonious equation, where redundant terms are found to replenish the lost pattern of the correct term (Z. Chen et al., 2021). A potential approach is to combine symbolic regression with DeepGS (Y. Chen et al., 2022; Xu & Zhang, 2021). We can expect to discover the close‐form physics equation that describes the physical laws for soil moisture flow and contains soil hydraulic properties.…”
Section: Limitations and Future Perspectivesmentioning
confidence: 99%
“…Except for the solving of PDEs, the scientific discoveries of PDEs by symbolic learning [10,11,45] and sparse regression [8,42,56] have also been studied. To learn the nonlinear responses without fixing certain finite difference approximations, convolutional kernels are widely used as learnable differential operators [35,36].…”
Section: Dynamical System Modelingmentioning
confidence: 99%
“…Many canonical dynamic models used to derive the fundamental governing equations of systems from observations are rooted in conservation laws and phenomenological behaviors in physical engineering and biological science [5]. Due to the complexity of dynamic systems and the uncertainty of variables, revealing the underlying governing equations representing the physical laws of the system from timeseries data that gives a general description of the spatiotemporal activities is a tremendous challenge [3,[6][7][8][9][10][11][12].…”
Section: Introductionmentioning
confidence: 99%