A comparative analysis of dynamics in the generalized Lorenz model with feedforward neural network validation

Ahmed Omar Alzahrani; Israr Ahmad; Ahmed Mohammed Alghamdi; Adel Aboud Bahaddad; Khalid Ali Almarhabi; Ahmed Omar Alzahrani; Israr Ahmad; Ahmed Mohammed Alghamdi; Adel Aboud Bahaddad; Khalid Ali Almarhabi

doi:10.3934/math.2026633

AIMS Mathematics

2026, Volume 11, Issue 6: 15402-15434. doi: 10.3934/math.2026633

Previous Article Next Article

Research article

A comparative analysis of dynamics in the generalized Lorenz model with feedforward neural network validation

1.
Department of Information Systems and Technology, College of Computer Science and Engineering, University of Jeddah, Jeddah 21493, Saudi Arabia
2.
Department of Mathematics, Government Post Graduate Jahanzeb College, Swat 19130, Khyber Pakhtunkhwa, Pakistan
3.
Department of Software Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah 21493, Saudi Arabia
4.
Department of Information System, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia
5.
Department of Computer Science, College of Engineering and Computing in Al-Qunfudah, Umm Al-Qura University, Makkah 24381, Saudi Arabia

Received: 02 March 2026 Revised: 08 May 2026 Accepted: 12 May 2026 Published: 01 June 2026
MSC : 03C65, 26A33, 34A08, 92B20

This paper presents a comprehensive analysis of the Lorenz model under the generalized $ \psi $-Hilfer fractional derivative, which offers remarkable flexibility through its fractional order $ \theta $, type parameter $ \kappa $, and auxiliary function $ \psi(t) $. The primary contributions of this work are threefold: First, we provided a detailed qualitative study establishing the existence, uniqueness, and Ulam-Hyers stability using fixed point theory. Second, we developed a novel hybrid numerical scheme specifically designed for the $ \psi $-Hilfer fractional Lorenz system. Third, we validated the numerical solutions using a feedforward neural network trained on numerically generated data, providing independent verification of our results. Quantitative performance metrics confirmed excellent agreement between numerical solutions and neural network approximations, with mean squared error values ranging from 1.085 to 5.186 and $ R^2 $ values between 0.937 and 0.983 across all state variables. MATLAB simulations comprise two-dimensional and three-dimensional visualizations, which demonstrated how variations in the fractional order $ \theta $ and type parameter $ \kappa $ significantly influence solution profiles, with decreasing fractional order enhancing memory effects and stabilizing system dynamics. Our work demonstrates how the additional flexibility of the $ \psi $-Hilfer operator enables more accurate modeling of memory effects in chaotic systems, while neural network validation provides a robust framework for solution verification.
- Lorenz model,
- $ \psi $-Hilfer derivative,
- hybrid numerical scheme,
- neural networks,
- chaotic dynamics
Citation: Ahmed Omar Alzahrani, Israr Ahmad, Ahmed Mohammed Alghamdi, Adel Aboud Bahaddad, Khalid Ali Almarhabi. A comparative analysis of dynamics in the generalized Lorenz model with feedforward neural network validation[J]. AIMS Mathematics, 2026, 11(6): 15402-15434. doi: 10.3934/math.2026633

Related Papers:

Abstract

This paper presents a comprehensive analysis of the Lorenz model under the generalized $ \psi $-Hilfer fractional derivative, which offers remarkable flexibility through its fractional order $ \theta $, type parameter $ \kappa $, and auxiliary function $ \psi(t) $. The primary contributions of this work are threefold: First, we provided a detailed qualitative study establishing the existence, uniqueness, and Ulam-Hyers stability using fixed point theory. Second, we developed a novel hybrid numerical scheme specifically designed for the $ \psi $-Hilfer fractional Lorenz system. Third, we validated the numerical solutions using a feedforward neural network trained on numerically generated data, providing independent verification of our results. Quantitative performance metrics confirmed excellent agreement between numerical solutions and neural network approximations, with mean squared error values ranging from 1.085 to 5.186 and $ R^2 $ values between 0.937 and 0.983 across all state variables. MATLAB simulations comprise two-dimensional and three-dimensional visualizations, which demonstrated how variations in the fractional order $ \theta $ and type parameter $ \kappa $ significantly influence solution profiles, with decreasing fractional order enhancing memory effects and stabilizing system dynamics. Our work demonstrates how the additional flexibility of the $ \psi $-Hilfer operator enables more accurate modeling of memory effects in chaotic systems, while neural network validation provides a robust framework for solution verification.

References

[1]	J. Padilla, Numerical validation of the discrete extramental clock law: Hierarchical emergence of objective time from ordinal conjunctions in chaotic systems, Preprints, 2025.
[2]	K. M. Cuomo, A. V. Oppenheim, S. H. Strogatz, Synchronization of Lorenz-based chaotic circuits with applications to communications, IEEE Trans. Circuits Syst. Ⅱ Analog Digit. Signal Process., 40 (2002), 626–633. https://doi.org/10.1109/82.246163 doi: 10.1109/82.246163
[3]	D. Viswanath, S. Şahutoğlu, Complex singularities and the Lorenz attractor, SIAM Rev., 52 (2010), 294–314. https://doi.org/10.1137/090753474 doi: 10.1137/090753474
[4]	C. Letellier, L. A. Aguirre, Dynamical analysis of fractional-order Rössler and modified Lorenz systems, Phys. Lett. A, 377 (2013), 1707–1719. https://doi.org/10.1016/j.physleta.2013.05.006 doi: 10.1016/j.physleta.2013.05.006
[5]	I. Petráš, The fractional-order Lorenz-type systems: A review, Fract. Calc. Appl. Anal., 25 (2022), 362–377. https://doi.org/10.1007/s13540-022-00016-4 doi: 10.1007/s13540-022-00016-4
[6]	S. Harikrishnan, O. Baghani, K. Kanagarajan, Qualitative analysis of fractional differential equations with $\psi$-Hilfer fractional derivative, Comput. Methods Differ. Equ., 10 (2022), 1–11. https://doi.org/10.22034/cmde.2020.37370.1670 doi: 10.22034/cmde.2020.37370.1670
[7]	I. Mallah, I. Ahmed, A. Akgul, F. Jarad, S. Alha, On psi-Hilfer generalized proportional fractional operators, AIMS Mathematics, 7 (2021), 82–103. https://doi.org/10.3934/math.2022005 doi: 10.3934/math.2022005
[8]	A. H. Bukhari, M. Shoaib, A. K. Kiani, N. I. Chaudhary, M. A. Z. Raja, et al., Dynamical analysis of nonlinear fractional order Lorenz system with a novel design of intelligent solution predictive radial base networks, Math. Comput. Simul., 213 (2023), 324–347. https://doi.org/10.1016/j.matcom.2023.06.005 doi: 10.1016/j.matcom.2023.06.005
[9]	S. Taimur, M. A. Z. Raja, M. J. A. A. Raja, S. A. Hassan, S. Z. Abbasi, A. K. Kiani, et al., A hybrid intelligent computational framework for diverse firing patterns in a fractional-order locally active memristive neuron model, Chaos Solit. Fract., 208 (2026), 118209. https://doi.org/10.1016/j.chaos.2026.118209 doi: 10.1016/j.chaos.2026.118209
[10]	Z. Shah, M. A. Z. Raja, M. Shoaib, S. Javeed, T. Muhammad, M. Ali, et al., Computing intelligence for the magnetised chemically reactive bidirectional radiative nanofluid flow through the Bayesian regularisation back-propagated neural network, Pramana, 98 (2024), 130. https://doi.org/10.1007/s12043-024-02794-3 doi: 10.1007/s12043-024-02794-3
[11]	Z. Shah, M. A. Z. Raja, W. A. Khan, M. Shoaib, V. Tirth, A. Algahtani, et al., Computational intelligence paradigm with Levenberg-Marquardt networks for dynamics of Reynolds nanofluid model for Casson fluid flow, Tribol. Int., 191 (2024), 109180. https://doi.org/10.1016/j.triboint.2023.109180 doi: 10.1016/j.triboint.2023.109180
[12]	A. Akbar, H. Ullah, M. A. Z. Raja, K. S. Nisar, S. Islam, M. Shoaib, A design of neural networks to study MHD and heat transfer in two phase model of nano-fluid flow in the presence of thermal radiation, Waves Random Complex Media, 36 (2026), 157–180. https://doi.org/10.1080/17455030.2022.2152905 doi: 10.1080/17455030.2022.2152905
[13]	I. Ali, M. A. Z. Raja, C. Y. Chang, M. P. Khan, M. Shoaib, C. M. Shu, Machine learning knowledge-driven neuroarchitecture for analysis of three-dimensional boundary layer flow of Sisko nanofluid model with impact of magnetic field, Z. Angew. Math. Mech., 106 (2026), e70350. https://doi.org/10.1002/zamm.70350 doi: 10.1002/zamm.70350
[14]	Z. I. Butt, I. Ahmad, M. A. Z. Raja, M. Shoaib, Radiative magneto-thermal modeling of tri hybrid nanofluid in blood: A Biomedical intelligent framework for hyperthermia cancer therapy, J. Therm. Biol., 136 (2026), 104382. https://doi.org/10.1016/j.jtherbio.2026.104382 doi: 10.1016/j.jtherbio.2026.104382
[15]	I. Grigorenko, E. Grigorenko, Chaotic dynamics of the fractional Lorenz system, Phys. Rev. Lett., 91 (2003), 034101. https://doi.org/10.1103/PhysRevLett.91.034101 doi: 10.1103/PhysRevLett.91.034101
[16]	G. Li, X. Zhang, H. Yang, Numerical analysis, circuit simulation, and control synchronization of fractional-order unified chaotic system, Mathematics, 7 (2019), 1077. https://doi.org/10.3390/math7111077 doi: 10.3390/math7111077
[17]	D. Dai, X. Li, Z. Li, W. Zhang, Y. Wang, Numerical simulation of the fractional-order Lorenz chaotic systems with Caputo fractional derivative, Comput. Model. Eng. Sci., 135 (2023), 1371–1392. https://doi.org/10.32604/cmes.2022.022323 doi: 10.32604/cmes.2022.022323
[18]	Y. Wang, Z. Wei, G. Feng, Attractor radius for fractional Lorenz systems and their application to the quantification of predictability limits, Chaos, 33 (2023), 013105. https://doi.org/10.1063/5.0113709 doi: 10.1063/5.0113709
[19]	K. M. Saad, M. S. Abdo, W. M. Hamanah, Existence and controllability analysis of multi-term fractional coupled systems with generalized-Caputo-Fabrizio operators, Sci. Rep., 15 (2025), 34434. https://doi.org/10.1038/s41598-025-17523-y doi: 10.1038/s41598-025-17523-y
[20]	M. Alqhtani, L. Sadek, Z. Hammouch, K. M. Saad, Efficient numerical schemes for linear fractional differential systems with applications to diffusion problems, J. Franklin Inst., 362 (2025), 108144. https://doi.org/10.1016/j.jfranklin.2025.108144 doi: 10.1016/j.jfranklin.2025.108144
[21]	Z. Lin, A. K. Pattanayak, A chaos synchronization diagnostic: Difference time series peak complexity (DTSPC), Entropy, 26 (2024), 1085. https://doi.org/10.3390/e26121085 doi: 10.3390/e26121085
[22]	S. F. Hafshejani, D. Gaur, A. Dasgupta, R. Benkoczi, N. R. Gosala, A. Iorio, A hybrid quantum solver for the Lorenz system, Entropy, 26 (2024), 1009. https://doi.org/10.3390/e26121009 doi: 10.3390/e26121009
[23]	A. E. Adeniji, K. S. Oyeleke, K. S. Ojo, A. M. Lasisi, Modeling and prediction of fractional-order chaotic Lorenz system using RNN and LSTM networks, J. Niger. Assoc. Math. Phys., 69 (2025), 139–152. https://doi.org/10.60787/jnamp.vol69no1.487 doi: 10.60787/jnamp.vol69no1.487
[24]	M. H. Fan, J. H. Zhao, L. Ding, X. Y. Ma, R. L. Fu, Predicting nonlinear dynamic systems by causal physics-informed neural networks with ResNet blocks, Neurocomputing, 656 (2025), 131589. https://doi.org/10.1016/j.neucom.2025.131589 doi: 10.1016/j.neucom.2025.131589
[25]	S. Scher, G. Messori, Generalization properties of feed-forward neural networks trained on Lorenz systems, Nonlin. Processes. Geophys., 26 (2019), 381–399. https://doi.org/10.5194/npg-26-381-2019 doi: 10.5194/npg-26-381-2019
[26]	X. Wang, J. Feng, Y. Xu, J. Kurths, Deep learning-based state prediction of the Lorenz system with control parameters, Chaos, 34 (2024), 033108. https://doi.org/10.1063/5.0187866 doi: 10.1063/5.0187866
[27]	T. Abdeljawad, K. Shah, I. Ahmad, M. Hleili, M. S. Alatawi, Using a finite difference scheme together with neural networks analysis for propagation of the long waves equation, AIMS Mathematics, 11 (2026), 825–856. https://doi.org/10.3934/math.2026036 doi: 10.3934/math.2026036
[28]	Asma, I. Ahmad, Z. Ali, S. Chasreechai, T. Sitthiwirattham, Analysis of a fractional order enzymatic reaction model with artificial neural network validation, Eur. J. Pure Appl. Math., 18 (2025), 6923. https://doi.org/10.29020/nybg.ejpam.v18i4.6923 doi: 10.29020/nybg.ejpam.v18i4.6923
[29]	N. Vieira, M. M. Rodrigues, M. Ferreira, Fractional gradient methods via $\psi$-Hilfer derivative, Fractal Fract., 7 (2023), 275. https://doi.org/10.3390/fractalfract7030275 doi: 10.3390/fractalfract7030275
[30]	I. Ahmad, Z. Ali, B. Khan, K. Shah, T. Abdeljawad, Exploring the dynamics of Gumboro-Salmonella co-infection with fractal fractional analysis, Alex. Eng. J., 117 (2025), 472–489. https://doi.org/10.1016/j.aej.2024.12.119 doi: 10.1016/j.aej.2024.12.119
[31]	E. Sousa, C. Li, A weighted finite difference method for the fractional diffusion equation based on the Riemann-Liouville derivative, Appl. Numer. Math., 90 (2015), 22–37. https://doi.org/10.1016/j.apnum.2014.11.007 doi: 10.1016/j.apnum.2014.11.007
[32]	Q. Yang, C. Zeng, Chaos in fractional conjugate Lorenz system and its scaling attractors, Commun. Nonlinear Sci. Numer. Simul., 15 (2010), 4041–4051. https://doi.org/10.1016/j.cnsns.2010.02.005 doi: 10.1016/j.cnsns.2010.02.005

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)