Diogo H. G. Duarte

Diogo H. G. Duarte

Auto-generated profile, based on publicly available information

Diogo H. G. Duarte

Universidade Federal do Rio Grande do Norte

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 February 2025 in Physical Review E
Verified
Journal Article
Closed access
DDD. H. G. Duarte
D. H. G. Duarte
PLPaulo Douglas Santos de Lima
Paulo Douglas Santos de Lima
JAJoão de Araújo
João de Araújo
Recent advances in machine learning have introduced physics-informed neural networks (PINN) as a valuable tool for addressing dynamics through governing equations and experimental observations. Outliers can be present in measurements and significantly affect the accuracy of the solutions provided by PINN. To overcome this limitation, we construct an outlier-resistant PINN (OrPINN) based on Tsallis statistics. We investigate the robustness of OrPINN in describing the acoustic and linear elastic wave dynamics under various outlier-level scenarios. We find that the OrPINN can improve the accuracy of the solutions even when the data is highly corrupted.

6 February 2026 in Physical Review E
Verified
Journal Article
Closed access
EAE. A. B. Alves
E. A. B. Alves
PLPaulo Douglas Santos de Lima
Paulo Douglas Santos de Lima
DDD. H. G. Duarte
D. H. G. Duarte
Mauro FerreiraMauro Ferreira
Mauro Ferreira
JAJoão de Araújo
João de Araújo
Claudionor BezerraClaudionor Bezerra
Claudionor Bezerra
Mode conversion in nonhomogeneous elastic media makes it challenging to interpret physical properties accurately. Decomposing these modes correctly is crucial across various scientific areas. Recent machine learning approaches have been proposed to address this problem, utilizing the Helmholtz decomposition technique. In this paper, we investigate the capabilities of a physics-informed neural network (PINN) in separating P and S modes by solving a scalar Poisson equation. This scalar formulation offers a dimensionally scalable reduction in computational cost compared to the traditional vector formulation. We verify the proposed method in both homogeneous and realistic nonhomogeneous elastic models as showcases. The obtained separated modes closely match those from conventional numerical techniques, while exhibiting reduced transverse wave leakage.


30 May 2026 in International Journal of Modern Physics C
Verified
Journal Article
Closed access
PDF file
APAlberto B. de Palhares
Alberto B. de Palhares
JVJoab M. Varela
Joab M. Varela
DDDiogo H. G. Duarte
Diogo H. G. Duarte
RCRafael Chaves
Rafael Chaves