Investigation of exact solitary wave solutions for the modified Veronese web equation via new residual neural network approach
Royal Society Open Science · 01.07.2026 · 13 (7)
DOI: 10.1098/rsos.260379 ↗Kurz gefasst
Fachartikel in der Zeitschrift Royal Society Open Science, online erschienen am 08.07.2026. Verfasst von Muhammad Qasim und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This work addresses the main inducements: the modified extended direct algebraic approach and residual neural network (MEDARNN) structures to obtain the exact analytical solutions for the (2+1)-dimensional modified Veronese web (MVW) equation. This is an integrable nonlinear partial differential equation (NLPDE) and is used to admit a differential covering with non-removable physical parameters. We present for the first time a novel analytical technique called the MEDARNN method, which combines models of residual neural networks (RNNs) with the auxiliary equation to provide precise solutions for NLPDEs. In addition, by establishing particular activation functions within the ‘2-2-2-1’ and ‘2-2-3-1’ NNs models, the introduction of a novel activation function derived from the auxiliary equations solutions is a significant innovation of this approach, creating a new mathematical connection between deep learning and differential equation theory. The different forms of solutions, such as shock, complex solitary-shock, shock-singular and periodic-singular forms, exhibit both single and coupled wave structures. For the physical interpretation of some of the constructed solutions are draw in the form of three-dimensional (3D), two-dimensional (2D) and corresponding contours by choosing the different values of parameters. This paper offers a new methodological approach for dealing with NLPDEs that is widely applicable in engineering and science domains.
Zitieren
APA
Qasim, M., Baber, M. Z., Ahmad, H., Yildirim, Y., Ceesay, B., & Ahmed, N. (2026). Investigation of exact solitary wave solutions for the modified Veronese web equation via new residual neural network approach. Royal Society Open Science, 13(7). https://doi.org/10.1098/rsos.260379
Vancouver
Qasim M, Baber MZ, Ahmad H, Yildirim Y, Ceesay B, Ahmed N. Investigation of exact solitary wave solutions for the modified Veronese web equation via new residual neural network approach. Royal Society Open Science. 2026;13(7). doi:10.1098/rsos.260379
BibTeX
@article{Qasim2026,
author = {Qasim, Muhammad and Baber, Muhammad Zafarullah and Ahmad, Hijaz and Yildirim, Yakup and Ceesay, Baboucarr and Ahmed, Nauman},
title = {Investigation of exact solitary wave solutions for the modified Veronese web equation via new residual neural network approach},
journal = {Royal Society Open Science},
year = {2026},
volume = {13},
number = {7},
doi = {10.1098/rsos.260379}
}
EUVIMED