fPINNs: Fractional Physics-Informed Neural Networks
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Abstract
Physics-informed neural networks (PINNs), introduced in [M. Raissi, P. Perdikaris, and G. Karniadakis, J. Comput. Phys., 378 (2019), pp. 686--707], are effective in solving integer-order partial differential equations (PDEs) based on scattered and noisy data. PINNs employ standard feedforward neural networks (NNs) with the PDEs explicitly encoded into the NN using automatic differentiation, while the sum of the mean-squared PDE residuals and the mean-squared error in initial-boundary conditions is minimized with respect to the NN parameters. Here we extend PINNs to fractional PINNs (fPINNs) to solve space-time fractional advection-diffusion equations (fractional ADEs), and we study systematically their convergence, hence explaining both fPINNs and PINNs for the first time. Specifically, we demonstrate their accuracy and effectiveness in solving multidimensional forward and inverse problems with forcing terms whose values are only known at randomly scattered spatio-temporal coordinates ( black-box (BB) forcing terms). A novel element of the fPINNs is the hybrid approach that we introduce for constructing the residual in the loss function using both automatic differentiation for the integer-order operators and numerical discretization for the fractional operators. This approach bypasses the difficulties stemming from the fact that automatic differentiation is not applicable to fractional operators because the standard chain rule in integer calculus is not valid in fractional calculus. To discretize the fractional operators, we employ the Grünwald--Letnikov (GL) formula in one-dimensional fractional ADEs and the vector GL formula in conjunction with the directional fractional Laplacian in two- and three-dimensional fractional ADEs. We first consider the one-dimensional fractional Poisson equation and compare the convergence of the fPINNs against the finite difference method (FDM). We present the solution convergence using both the mean $L^2$ error as well as the standard deviation due to sensitivity to NN parameter initializations. Using different GL formulas we observe first-, second-, and third-order convergence rates for small size training sets but the error saturates for larger training sets. We explain these results by analyzing the four sources of numerical errors due to discretization, sampling, NN approximation, and optimization. The total error decays monotonically (below $10^{-5}$ for a third-order GL formula) but it saturates beyond that point due to the optimization error. We also analyze the relative balance between discretization and sampling errors and observe that the sampling size and the number of discretization points ( auxiliary points) should be comparable to achieve the highest accuracy. As we increase the depth of the NN up to certain value, the mean error decreases and the standard deviation increases, whereas the width has essentially no effect unless its value is either too small or too large. We next consider time-dependent fractional ADEs and compare white-box (WB) and BB forcing. We observe that for the WB forcing, our results are similar to the aforementioned cases; however, for the BB forcing fPINNs outperform FDM. Subsequently, we consider multidimensional time-, space-, and space-time-fractional ADEs using the directional fractional Laplacian and we observe relative errors of $10^{-3}\sim10^{-4}$. Finally, we solve several inverse problems in one, two, and three dimensions to identify the fractional orders, diffusion coefficients, and transport velocities and obtain accurate results given proper initializations even in the presence of significant noise.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We also used the extended stochastic gradient descent Adam algorithm [18] to optimize the loss function.”
MethodRaissi, M., Perdikaris, P., & Karniadakis, G. E. (2019) · Journal of Computational Physics · doi:10.1016/j.jcp.2018.10.045 · Cited by 20,384 · cited 4×
“We just need to add the parameters to be identified in the inverse problem to the list of parameters to be optimized in the forward problem without changing anything else [35].”
BackgroundMethodInfluentialSelf-citationModel-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512 · cited 1×
“We can tune these attributes of NN architecture automatically by leveraging metalearning techniques [65, 66].”
MethodImproving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382 · cited 1×
“Additionally, the noise in the data can be naturally taken into account by employing regularization techniques, such as L(1), L(2) and L∞ regularization [32], early stopping [33], as well as dropout [34, 35].”
MethodDiscovering governing equations from data by sparse identification of nonlinear dynamical systems
Brunton, S. L., Proctor, J. L., & Kutz, J. N. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1517384113 · Cited by 4,796 · cited 10×
“In this paper, we focus on the identification of the parameters of fractional PDEs whose overall form is known but some coefficients and most importantly the operators themselves are not known.”
BackgroundInfluentialNeural Architecture Search with Reinforcement Learning
Zoph, B., & Le, Q. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01578 · Cited by 3,974 · cited 1×
“We can tune these attributes of NN architecture automatically by leveraging meta-learning techniques [54].”
MethodArtificial neural networks for solving ordinary and partial differential equations
Lagaris, I. E., Likas, A., & Fotiadis, D. I. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/72.712178 · Cited by 2,412 · cited 1×
“In particular, we concentrate on physics-informed neural networks (PINNs) [7, 46, 19, 35], which belong to the second aforementioned category.”
BackgroundHidden physics models: Machine learning of nonlinear partial differential equations
Raissi, M., & Karniadakis, G. E. (2018) · Journal of Computational Physics · doi:10.1016/j.jcp.2017.11.039 · Cited by 1,349 · cited 1×
“Other examples include, but not limited to, [21, 22, 23].”
BackgroundSelf-citationApplication of a fractional advection‐dispersion equation
Benson, D. A., Wheatcraft, S. W., & Meerschaert, M. M. (2000) · Water Resources Research · doi:10.1029/2000wr900031 · Cited by 1,301 · cited 1×
“Among these are solute transport in fractured and porous media [2, 3], acoustic wave propagation with frequency-dependent dissipation [4, 5, 6, 7], laminar and turbulent flows [8, 9, 10], viscoelastic constitutive laws [11], just to mention a few.”
BackgroundA fully discrete difference scheme for a diffusion-wave system
Sun, Z.-Z., & Wu, X. (2006) · Applied Numerical Mathematics · doi:10.1016/j.apnum.2005.03.003 · Cited by 1,235 · cited 2×
“The truncating error for the L1 scheme is (\Delta t) 2 - \gamma [44].”
Method
Research works printed but not linked: 31
- [62] Avrim Blum and Ronald L Rivest. Training a 3-node neural network is np-complete. In Advances in neural information processing systems , pages 494-501, 1989. -
- [13] Samuel H Rudy, Steven L Brunton, Joshua L Proctor, and J Nathan Kutz. Data-driven discovery of partial differential equations. Science Advances , 3(4):e1602614, 2017. -
- [14] Zichao Long, Yiping Lu, Xianzhong Ma, and Bin Dong. PDE-net: Learning PDEs from data. In Jennifer Dy and Andreas Krause, editors, Proceedings of the 35th International Conference on Machine Learning , volume 80 of Proceedings of Machine Learning Research , pages 32083216, Stockholmsmässan, Stockholm Sweden, 10-15 Jul 2018. PMLR. -
- [11] Francesco Mainardi. Fractional calculus and waves in linear viscoelasticity: an introduction to mathematical models . World Scientific, 2010. -
- [5] Bradley E Treeby and BT Cox. Modeling power law absorption and dispersion for acoustic propagation using the fractional laplacian. The Journal of the Acoustical Society of America , 127(5):2741-2748, 2010. -
- 10.1007/978-3-642-14574-2 · doi:10.1007/978-3-642-14574-2
- [57] Rudolf Gorenflo, Anatoli˘ ı Aleksandrovich Kilbas, Francesco Mainardi, Sergei V Rogosin, et al. Mittag-Leffler functions, related topics and applications , volume 2. Springer, 2014. -
- [19] Vladimir I Gorbachenko, Tatiana V Lazovskaya, Dmitriy A Tarkhov, Alexander N Vasilyev, and Maxim V Zhukov. Neural network technique in some inverse problems of mathematical physics. In International Symposium on Neural Networks , pages 310-316. Springer, 2016. -
- [59] Xavier Glorot and Yoshua Bengio. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics , pages 249-256, 2010. -
- 10.1007/978-3-319-40663-3_36 · doi:10.1007/978-3-319-40663-3_36
- 10.1007/978-3-662-43930-2 · doi:10.1007/978-3-662-43930-2
- [47] A Anatolii Aleksandrovich Kilbas, Hari Mohan Srivastava, and Juan J Trujillo. Theory and applications of fractional differential equations , volume 204. Elsevier Science Limited, 2006. -
- [23] Mamikon Gulian, Maziar Raissi, Paris Perdikaris, and George Karniadakis. Machine learning of space-fractional differential equations. arXiv preprint arXiv:1808.00931 , 2018. - · arXiv
- [24] Tianping Chen and Hong Chen. Approximations of continuous functionals by neural networks with application to dynamic systems. IEEE Transactions on Neural Networks , 4(6):910-918, 1993. -
- [7] Tieyuan Zhu and Jerry M Harris. Modeling acoustic wave propagation in heterogeneous attenuating media using decoupled fractional laplacians. Geophysics , 79(3):T105-T116, 2014. -
- [54] Bangti Jin, Raytcho Lazarov, and Zhi Zhou. An analysis of the l1 scheme for the subdiffusion equation with nonsmooth data. IMA Journal of Numerical Analysis , 36(1):197-221, 2015. -
- Kilbas A. A. A., 2006, North-Holland Math. Stud. 204
- [61] Jason D Lee, Max Simchowitz, Michael I Jordan, and Benjamin Recht. Gradient descent only converges to minimizers. In Conference on Learning Theory , pages 1246-1257, 2016. -
- [67] Lihua Lei, Cheng Ju, Jianbo Chen, and Michael I Jordan. Non-convex finite-sum optimization via scsg methods. In Advances in Neural Information Processing Systems , pages 2348-2358, 2017. -
- [68] Chenxin Ma, Jakub Konečn` y, Martin Jaggi, Virginia Smith, Michael I Jordan, Peter Richtárik, and Martin Takáč. Distributed optimization with arbitrary local solvers. Optimization Methods and Software , 32(4):813-848, 2017.
- 10.1142/p614 · doi:10.1142/p614
- Meerschaert M. M., 2004, Fract. Calc. Appl. Anal., 7, 61
- [41] Ying Zhang and Xiang Xu. Inverse source problem for a fractional diffusion equation. Inverse problems , 27(3):035010, 2011. -
- [42] Bangti Jin and William Rundell. An inverse problem for a one-dimensional time-fractional diffusion problem. Inverse Problems , 28(7):075010, 2012. -
- [50] Igor Podlubny. Fractional differential equations: an introduction to fractional derivatives, fractional differential equations, to methods of their solution and some of their applications. Mathematics in science and engineering , 198:261-300, 1999. -
- [51] Kai Diethelm. The analysis of fractional differential equations: An application-oriented exposition using differential operators of Caputo type . Springer Science & Business Media, 2010. -
- [32] Yoshua Bengio, Ian J Goodfellow, and Aaron Courville. Deep learning. Nature , 521(7553):436444, 2015. -
- Samko S. G., 1993, Gordon and Breach
- [64] John Paul Roop. Computational aspects of fem approximation of fractional advection dispersion equations on bounded domains in r2. Journal of Computational and Applied Mathematics , 193(1):243-268, 2006. -
- [9] Vladimir V Uchaikin. Fractional derivatives for physicists and engineers , volume 2. Springer, 2013. -
- [35] Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research , 15(1):1929-1958, 2014. -
Cited by
Items 401–500 of 1,000
Liu, H., Wang, L., Zhang, Y., Lu, G., & Liu, L. (2023) · Physical review. E · doi:10.1103/physreve.108.045303 · Cited by 13
GPINN with Neural Tangent Kernel Technique for Nonlinear Two Point Boundary Value Problems
Jha, N., & Mallik, E. (2024) · Neural Processing Letters · doi:10.1007/s11063-024-11644-7 · Cited by 13
“PINNS have also been used in solving some families of fractional differential equations which are hard to solve using standard methods [24].”
Meshfree Variational-Physics-Informed Neural Networks (MF-VPINN): An Adaptive Training Strategy
Berrone, S., & Pintore, M. (2024) · Algorithms · doi:10.3390/a17090415 · Cited by 13
“Moreover, it is even possible to change the neural network architecture or the training strategy as in [14, 30, 31, 32, 33, 34, 35]; between the methods based on different architectures, we highlight some works based on the novel Kolmogorov–Arnold Network (KAN) [36] architecture [37, 38] and on a…”
MethodZheng, J., & Yang, Y. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112370 · Cited by 14
Li, T., & Xiao, T. (2025) · Actuators · doi:10.3390/act14010014 · Cited by 13
“Subsequent developments, such as the fractional PINN developed by Pang et al. [26] and the physics-informed neural operators developed by Li et al. [27], have expanded the applicability of PINNs to more complex domains, including fractional differential equations and high-dimensional PDEs.”
Shi, J., Liu, X., & Yang, X. (2025) · Nonlinear Dynamics · doi:10.1007/s11071-024-10786-6 · Cited by 13
“Pang et al. [31] proposed the fPINN by combining PINN with the finite difference method of fractional operators.”
InfluentialZhang, Z., Xiong, X., Zhang, S., Wang, W., Yang, X., Zhang, S., & Yang, C. (2025) · Physics of Fluids · doi:10.1063/5.0259583 · Cited by 13
CuPINN: Optimizing PINNs through curvature minimization and residual landscape flattening
Moayedi, R. Z., Abbaszadeh, M., & Dehghan, M. (2025) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2025.118180 · Cited by 15
Lee, Y., Liu, S., Zou, Z., Kahana, A., Turkel, E., Ranade, R., Pathak, J., & Karniadakis, G. E. (2025) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2025.118231 · Cited by 13
Self-citationAn Asymptotically Compatible Coupling Formulation for Nonlocal Interface Problems with Jumps
Glusa, C., D’Elia, M., Capodaglio, G., Gunzburger, M., & Bochev, P. B. (2023) · SIAM Journal on Scientific Computing · doi:10.1137/22m1490351 · Cited by 13
An Extrinsic Approach Based on Physics-Informed Neural Networks for PDEs on Surfaces
Tang, Z., Fu, Z., & Reutskiy, S. (2022) · Mathematics · doi:10.3390/math10162861 · Cited by 13
Physics Informed Neural Networks applied to liquid state theory
Carvalho, F. S., & Braga, J. P. (2022) · Journal of Molecular Liquids · doi:10.1016/j.molliq.2022.120504 · Cited by 13
Xing, B., Liu, H., Tang, X., & Shi, L. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3217207 · Cited by 13
“For example, singularly perturbed differential equations [21], fractional differential equations [22], [23], [24], stochastic differential equations [25], [26], stiff differential equations [27], delay differential equations [28], differential-algebraic equations [29].”
BackgroundFractional Gradient Optimizers for PyTorch: Enhancing GAN and BERT
Herrera-Alcántara, O., & Castelán-Aguilar, J. R. (2023) · Fractal and Fractional · doi:10.3390/fractalfract7070500 · Cited by 13
Investigation of Physics-Informed Neural Networks to Reconstruct a Flow Field with High Resolution
Yang, Z., Xu, Y., Jing, J. P., Fu, X., Wang, B.-F., Ren, H., Zhang, M., & Sun, T. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11112045 · Cited by 13
Efficient quadrature rules for finite element discretizations of nonlocal equations
Aulisa, E., Capodaglio, G., Chierici, A., & D’Elia, M. (2021) · Numerical Methods for Partial Differential Equations · doi:10.1002/num.22833 · Cited by 13
“The kernel γ depends on the application and determines the regularity properties of the solutions; the choice of its parameters or functional form is among the most investigated open questions in the current nonlocal literature [42, 11, 20, 21, 30, 43, 44, 55, 57, 56].”
BackgroundMeasuring Tissue Elastic Properties Using Physics Based Neural Networks
Mallampati, A., & Almekkawy, M. K. (2021) · IEEE UFFC Latin America Ultrasonics Symposium (LAUS) · doi:10.1109/laus53676.2021.9639231 · Cited by 13
On the prescription of boundary conditions for nonlocal Poisson's and peridynamics models
D’Elia, M., & Yu, Y. (2021) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.2172/1817978 · Cited by 13
Adaptive Deep Density Approximation for Fractional Fokker–Planck Equations
Zeng, L., Wan, X., & Zhou, T. (2023) · Journal of Scientific Computing · doi:10.1007/s10915-023-02379-z · Cited by 12
“For example, a finite difference method is applied in [24], and a directly Monte Carlo sampling approach was proposed in [15].”
MethodNeural Control of Parametric Solutions for High-Dimensional Evolution PDEs
Gaby, N., Ye, X., & Zhou, H. (2024) · SIAM Journal on Scientific Computing · doi:10.1137/23m1549870 · Cited by 12
Artificial intelligence and machine learning in aerodynamics
Kou, J., & Xiao, T. (2024) · Metascience in Aerospace · doi:10.3934/mina.2024009 · Cited by 14
Zhang, B., & Yang, C. (2024) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2024.101589 · Cited by 18
“And it has been expanded for solving integro-differential equations, fractional differential equations [46], and stochastic differential equations [47].”
Li, N., & Wang, M. (2024) · Nonlinear Dynamics · doi:10.1007/s11071-024-10359-7 · Cited by 12
Neuromorphic Computing Network for Underwater Image Enhancement and Beyond
Xiao, F., Liu, J., Huang, Y., Cheng, E., & Yuan, F. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3473020 · Cited by 14
“Due to the high flexibility and expressiveness of function approximation, PINNs have been extended to solve various PDEs, such as integral differential equations [51] and stochastic differential equations [52].”
MethodSinc Kolmogorov-Arnold network and its application for solving PDEs with singularities
Yu, T., Qiu, J., Jiang, Y., & Oseledets, I. V. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109033 · Cited by 12
Neural fractional differential networks for modeling complex dynamical systems
Vellappandi, M., & Lee, S. (2024) · Nonlinear Dynamics · doi:10.1007/s11071-024-10795-5 · Cited by 12
“Neural networks have revolutionized machine learning by enabling the modeling of complex, non-linear relationships across various domains [5].”
Adaptive finite element interpolated neural networks
Badia, S., Li, W., & Martín, A. F. (2025) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2025.117806 · Cited by 12
Zhang, L., Du, M., Bai, X., Chen, Y., & Zhang, D. (2025) · Physical Review Research · doi:10.1103/physrevresearch.7.013164 · Cited by 12
Chen, J., Li, B., & Yuen, M. (2025) · Communications in Nonlinear Science and Numerical Simulation · doi:10.1016/j.cnsns.2025.109049 · Cited by 16
Yuan, S., Liu, Y., Yan, L., Zhang, R., & Wu, S. (2025) · Fractal and Fractional · doi:10.3390/fractalfract9080541 · Cited by 12
Zhang, Z., Xiong, X., Zhang, S., Wang, W., Zhong, Y., Yang, C., & Yang, X. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129839 · Cited by 12
Kumar, Y., Vats, R. K., Nain, A. K., & Yadav, S. (2025) · Mathematical Methods in the Applied Sciences · doi:10.1002/mma.70395 · Cited by 12
“To overcome these challenges, Pang et al. [25] proposed a fractional physics-informed neural network (fPINN), a specialized approach for solving space-time fractional advection-diffusion equations.”
Tipu, G. H., Mateen, A., DAVLETOV, E. Y., Davletov, I. Y., & Javed, F. (2026) · Modern Physics Letters B · doi:10.1142/s0217984926500363 · Cited by 12
Sun, J., Dong, H., & Fang, Y. H. (2024) · Journal of Systems Science and Complexity · doi:10.1007/s11424-024-3349-z · Cited by 13
“To enhance the applicability of the PINNs, fractional PINNs, stochastic PINNs, Bayesian PINNs and other methods have been proposed, respectively [18–20] .”
Xu, S.-Y., Yang, A., & Zhou, Q. (2024) · Ukrainian Journal of Physical Optics · doi:10.3116/16091833/ukr.j.phys.opt.2024.s1137 · Cited by 12
An Artificial Neural Network Approach for Solving Space Fractional Differential Equations
Dai, P., & Yu, X. (2022) · Symmetry · doi:10.3390/sym14030535 · Cited by 12
“[27], Pang et al. solve space-time fractional advection-diffusion equations by fractional PINNs.”
Sandia National Laboratories (SNL-CA), ;. C. L., D’Elia, M., (NNSA), U. N. N. S. A., Sandia National Laboratories (SNL-NM), A., & Gulian, M. (2021) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.2172/1763574 · Cited by 12
Liu, J., Pan, H., Sun, W., Jing, H., & Gong, B. (2024) · Mathematical Geosciences · doi:10.1007/s11004-024-10152-7 · Cited by 11
Cao, Z., Liu, K., Luo, K., Wang, S., Jiang, L., & Fan, J. (2024) · Physics of Fluids · doi:10.1063/5.0235674 · Cited by 11
PINN based on multi-scale strategy for solving Navier–Stokes equation
Li, S., & Lai, S. (2025) · Results in Applied Mathematics · doi:10.1016/j.rinam.2024.100526 · Cited by 11
Yang, Y., Luo, F., Chen, Z., Tao, A., Zhao, H., Dong, Y., Tian, P., & Zheng, J. (2025) · Ocean Modelling · doi:10.1016/j.ocemod.2025.102601 · Cited by 11
Xiong, X., Lu, K., Zhang, Z., Zeng, Z., Zhou, S., Deng, Z., & Hu, R. (2025) · Communications in Nonlinear Science and Numerical Simulation · doi:10.1016/j.cnsns.2025.109414 · Cited by 11
Physics-informed neural networks for complex fluids: opportunities and limitations
Sa, J., Jeon, B., Seo, Y.-J., Lim, J., & Choi, S. Q. (2025) · Korea-Australia Rheology Journal · doi:10.1007/s13367-025-00140-6 · Cited by 18
Solving Time-Fractional Partial Integro-Differential Equations Using Tensor Neural Network
Lin, Z., Ma, Q., Xie, H., & Yin, X. (2026) · SIAM Journal on Scientific Computing · doi:10.1137/25m1748895 · Cited by 11
Ouyang, W., Zhu, M., Xiong, W., Liu, S., & Lu, L. (2026) · Advanced Intelligent Discovery · doi:10.1002/aidi.202500214 · Cited by 11
Self-citationShan, S., Zhu, M., Lin, Y., & Lu, L. (2026) · Communications Physics · doi:10.1038/s42005-026-02677-6 · Cited by 11
Self-citationSaha, S. K., Park, C., Knapik, S., Guo, J., Huang, O., & Liu, W. K. (2023) · Computational Mechanics · doi:10.1007/s00466-023-02292-0 · Cited by 13
Solving the non-local Fokker–Planck equations by deep learning
Jiang, S., & Li, X. (2023) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0128935 · Cited by 11
“A parallel work by Pang et al [16] combines PiNN with one-dimensional and multi-dimensional Grunwald-Letnikov numerical schemes and Gauss-Legendre quadrature rule to discretize the fractional laplacian and solves forward and inverse problem of fractional advection-diffusion equations in one, two and three dimensions i…”
BackgroundMethodInfluentialPhysics-informed Neural Networks approach to solve the Blasius function
Krishna, G., Nair, M. S., Nair, P. P., & Anil Lal, S. (2023) · International Conference on Electrical, Computer and Communication Technologies (ICECCT) · doi:10.1109/icecct56650.2023.10179704 · Cited by 11
Fractional and tempered fractional models for Reynolds-averaged Navier–Stokes equations
Mehta, P. P. (2023) · Journal of Turbulence · doi:10.1080/14685248.2023.2274100 · Cited by 11
“PINNs are deep neural network where the loss comprises of two parts, namely, data and equations along with weights, λ (hyperparameter) to balance the two components of the loss [32] [33], to accelerate the convergence, as shown in the expression below (53).”
BackgroundShekarpaz, S., Zeng, F., & Karniadakis, G. E. (2024) · Communications in Computational Physics · doi:10.4208/cicp.oa-2023-0121 · Cited by 11
“PINNs have been applied successfully to a broad range of ordinary and partial differential equations, including fractional equations [48], integro-differential equations, stochastic partial differential equations [68], and inverse problems [44].”
MethodSelf-citationAğraz, M. (2024) · Scientific Reports · doi:10.1038/s41598-024-67483-y · Cited by 11
“These include stochastic PINNs 23 , fractional PINNs (fPINNs) 24 , conservative physics-informed neural networks (CPINNs) 25 , parareal physics-informed neural networks (PPINNs) 26 , extended physics-informed neural networks (XPINNs) 27 , non-local PINNs (nPINNs) 28 , PINNs’ variational formulation…”
BackgroundThe physics informed neural networks for the unsteady Stokes problems
Yue, J., & Li, J. (2022) · International Journal for Numerical Methods in Fluids · doi:10.1002/fld.5095 · Cited by 11
A data-driven framework for discovering fractional differential equations in complex systems
Yu, X., Xu, H., Zhiping, M., Hongguang, S., Zhang, Y., Zhibo, C., Dongxiao, Z., & Yuntian, C. (2025) · Nonlinear Dynamics · doi:10.1007/s11071-025-11373-z · Cited by 18
“However, these approaches are heavily dependent on prior knowledge of the equation structures.”
Chen, P., Hu, T., & Guilleminot, J. (2023) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2023.116684 · Cited by 10
Singular layer physics informed neural network method for plane parallel flows
Chang, T.-Y., Gie, G., Hong, Y., & Jung, C. (2024) · Computers & Mathematics with Applications · doi:10.1016/j.camwa.2024.04.025 · Cited by 10
Non-diffusive neural network method for hyperbolic conservation laws
Lorin, E., & Novruzi, A. (2024) · Journal of Computational Physics · doi:10.1016/j.jcp.2024.113161 · Cited by 10
“We refer to [10, 11, 12] for details.”
Physics-informed neural networks for weakly compressible flows using Galerkin–Boltzmann formulation
Aygun, A., & Karakus, A. (2024) · Physics of Fluids · doi:10.1063/5.0235756 · Cited by 10
Physics Informed Neural Network Method for Solving Delay Hilfer Fractional Differential Equations
Rahimkhani, P., Sabermahani, S., & Hassani, H. (2025) · International Journal of Numerical Modelling Electronic Networks Devices and Fields · doi:10.1002/jnm.70070 · Cited by 10
Shao, X., Xu, L., Zhang, S., Sun, G., & Wu, C. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3665811 · Cited by 10
“Pio-neered by Pang et al. [13], fPINNs have enabled data-driven solution and parameter identification of fractional-order PDEs, with recent variants improving numerical stability through Monte Carlo integration, score-based formulations, and analytically tractable basis functions [14], [15], [16].”
Applications of physics-informed neural networks in fluid flow in porous media - A review study
Samarkanov, O. L., Riazi, M., Irawan, S., & Kamrava, S. (2026) · Energy and AI · doi:10.1016/j.egyai.2026.100747 · Cited by 11
Research on simulation of gun muzzle flow field empowered by artificial intelligence
Zhou, M., Qian, L., Cao, C., Chen, G., Kong, J., & Tong, M. (2023) · Defence Technology · doi:10.1016/j.dt.2023.02.006 · Cited by 10
Zhang, H., Cai, S.-J., Li, J.-Y., Liu, Y., & Zhang, Z. (2023) · Nonlinear Dynamics · doi:10.1007/s11071-023-08361-6 · Cited by 10
“In particular, more well-directed neural networks such as the Bayesian PINN [23], discrete PINN framework based on graph convolutional network and variational structure of PDE [24], auxiliary PINN [25], fractional PINN [26,27], variational PINN [28] were designed to eliminate roadblocks in more complex and realistic a…”
MethodCao, F., Guo, X., Gao, F., & Yuan, D. (2023) · Mathematics · doi:10.3390/math11081843 · Cited by 10
Deep learning algorithms for solving differential equations: a survey
Kumar, H., & Yadav, N. (2023) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/0952813x.2023.2242356 · Cited by 19
“In addition, PINNs are further extended to solve integro differential equations, fractional differential equations (Pang et al., 2019), and stochastic differential equations (Nabian & Meidani, 2018; D. Zhang et al., 2020).”
Adaptive deep neural networks for solving corner singular problems
Zeng, S., Liang, Y., & Zhang, Q. (2023) · Engineering Analysis with Boundary Elements · doi:10.1016/j.enganabound.2023.11.022 · Cited by 10
Zhang, S., Guo, X., Li, C., Zhao, R., Yang, C., Wang, W., & Zhong, Y. (2023) · International journal of computational fluid dynamics · doi:10.1080/10618562.2023.2295286 · Cited by 10
Physics-informed machine learning in asymptotic homogenization of elliptic equations
Soyarslan, C., & Pradas, M. (2024) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2024.117043 · Cited by 13
“, [9, 10, 11]; and it is expected to become more prominent with the advent of accessible, scalable, and modular deep learning frameworks (such as, e.”
BackgroundYuan, L., Ni, Y., Rui, E.-Z., & Zhang, W. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2647/19/192013 · Cited by 10
“PIML has been used to successfully solve the forward and inverse problems of kinds of equations such as partial differential equations (PDEs) [20, 21], integral-differential equations (IDEs) [22, 23], stochastic differential equations [24] and fractional differential equations [22].”
MethodLiu, Q., Zhou, Y., Li, K., & Zhang, S. (2022) · Nonlinear Dynamics · doi:10.1007/s11071-022-07803-x · Cited by 10
“In recent years, the PINN algorithm has been used widely to solve many famous PDEs, such as the Schrödinger equation, Allen–Cahn equation, Navier–Stokes equation, KdV equation and Burgers equation [31], the Klein–Gordon equation and Helmholtz equation [34], aswell as the space-time fractional advection-diffusion equat…”
MethodEfficient coupled deep neural networks for the time-dependent coupled Stokes-Darcy problems
Yue, J., & Li, J. (2022) · Applied Mathematics and Computation · doi:10.1016/j.amc.2022.127514 · Cited by 10
MGIC: Multigrid-in-Channels Neural Network Architectures
Eliasof, M., Ephrath, J., Ruthotto, L., & Treister, E. (2023) · SIAM Journal on Scientific Computing · doi:10.1137/21m1430194 · Cited by 14
“This property is important, especially in applications where we wish to model implicit function via a neural networks, such as signed-distance fields for shape reconstruction and completion [31], and solution of PDEs [30, 33, 3, 26]—these works in particular approximate functions in an unsupervised manner.”
BackgroundTeng, Y., Zhang, X., Wang, Z., & Ju, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.11045 · Cited by 12
“This approach later has been extended to solve inverse problems [Raissi et al., 2018], fractional differential equations [Pang et al., 2019], stochastic differential equations, and tasks about uncertainty quantification in [Nabian and Meidani, 2018; Yang et al., 2018a; Zhang et al., 2019a; Zhang et…”
BackgroundExponential stability of fractional‐order uncertain systems with asynchronous switching and impulses
Zhang, J., & Nie, X. (2024) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.7345 · Cited by 9
Ernst, L., & Urban, K. (2024) · IMA Journal of Numerical Analysis · doi:10.1093/imanum/drae011 · Cited by 9
Zhang, J., Leng, Y., Wu, C., & Su, C. (2024) · Nonlinear Dynamics · doi:10.1007/s11071-024-10309-3 · Cited by 9
“In addition, the following methods have been developed: fractional-order PINN [30], Parareal PINN [ 31], variational PINN [32], Bayesian PINN [33], distributed PINN [34], nonlocal PINN [35], and regional decomposition PINN [36–38].”
InfluentialSimavilla, D. N., Bonfanti, A., García, I., Español, P., & Ellero, M. (2025) · Journal of Fluid Mechanics · doi:10.1017/jfm.2025.10325 · Cited by 15
“PINNs are currently employed to solve forward and inverse PDE problems [19], fractional equations [21], integral-differential equations [22], and stochastic PDEs [23].”
Accelerating the convergence of physics-informed neural networks for seismic wave simulation
Zou, J., Liu, C., Wang, Y., Song, C., bin Waheed, U., & Zhao, P. (2024) · Geophysics · doi:10.1190/geo2024-0264.1 · Cited by 9
Singh, A. K., Mehra, M., & Pulch, R. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10752-8 · Cited by 11
“• Due to the non-applicability of automatic differentiation in the case of non-local operators, in 2019, Pang [25] introduced fractional physics informed neural networks (fPINNs) to solve and learn fractional differential equations (fractional operators are one of the non-local operators).”
Time series forecasting of microalgae cultivation for a sustainable wastewater treatment
Sundaram, K. M., Kumar, D., Lee, J., Barathi, S., & Rajendran, K. (2025) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2025.106845 · Cited by 13
Modified hard-constrained PINNs for physically consistent microgrid transient response modeling
Chen, L., Wang, Y., Sun, W. M., Shang, L., Dong, X., & Wang, B. (2025) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2025.110726 · Cited by 9
PINN-parafoil: A physics-informed neural network method for complex parafoil dynamics simulating
Yan, Y., Fan, Y., Ning, L., Su, C., Wang, P., & Cao, Y. (2025) · Journal of Computational Science · doi:10.1016/j.jocs.2025.102639 · Cited by 9
Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learning
Kuang, K., Dean, F., Jedlicki, J. B., Ouyang, D., Philippakis, A., Sontag, D. A., & Alaa, A. M. (2024) · neural information processing systems · doi:10.52202/079017-0187 · Cited by 33
Newman, T. B., Nemeth, C., Jones, M. A., & Jonathan, P. (2025) · The Annals of Applied Statistics · doi:10.1214/25-aoas2101 · Cited by 9
Chen, J., Li, B., & Yuen, M. (2025) · Computers & Mathematics with Applications · doi:10.1016/j.camwa.2025.09.007 · Cited by 10
Distributed multigrid neural solvers on megavoxel domains
Balu, A., Botelho, S., Khara, B., Rao, V., Sarkar, S., Hegde, C., Krishnamurthy, A., Adavani, S. S., & Ganapathysubramanian, B. (2021) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1145/3458817.3476218 · Cited by 12
“In recent years, several data-driven 36,40 and data-free 11,14,28,30,33,37,39,43 ? approaches for solving partial differential equations (PDEs) have been proposed.”
BackgroundStudy on pile driving and sound propagation in shallow water using physics-informed neural network
Jiang, Q., Wang, X., Yu, M., Tang, M., Zhan, B., & Dong, S. (2023) · Ocean Engineering · doi:10.1016/j.oceaneng.2023.114684 · Cited by 9
Han, J., Xue, L., Jia, Y. J., Mwasmwasa, M. S., Nanguka, F., Sangweni, C., Liu, H., & Li, Q. (2023) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2023.031093 · Cited by 9
The Calderón’s Problem via DeepONets
Castro, J., Muñoz, C., & Valenzuela, N. (2024) · Vietnam Journal of Mathematics · doi:10.1007/s10013-023-00674-8 · Cited by 17
“See [RK18, RPK19, PLK19, MJK20] and references therein for a detailed introduction to the subject.”
BackgroundSolving Euler equations with gradient-weighted multi-input high-dimensional feature neural network
Zhao, J., Wu, W., Feng, X., & Xu, H. (2024) · Physics of Fluids · doi:10.1063/5.0194523 · Cited by 9
Gauss Newton Method for Solving Variational Problems of PDEs with Neural Network Discretizaitons
Hao, W., Hong, Q., & Jin, X. (2024) · Journal of Scientific Computing · doi:10.1007/s10915-024-02535-z · Cited by 9
“This approach has been successfully applied to a wide range of practical problems with remarkable success [4, 11, 15, 21].”
Background(2024) · Journal of Mathematics and Computer Science · doi:10.22436/jmcs.036.02.01 · Cited by 9
“For a more detailed explanation, refer to [23, 37].”
Performance Comparison of Prediction of Hydraulic Jump Length Under Multiple Neural Network Models
Xu, Z., Liu, Z., & Peng, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3430075 · Cited by 9
“The core idea of PINN (Physics-Informed Neural Networks) is to use neural networks to fit given data points while satisfying known physical constraints, integrating data and prior knowledge [44], [45], [46], [47] or physical laws [48], [49], [50].”
Deep Learning for Solving and Estimating Dynamic Macro-finance Models
Fan, B., Qiao, E., Jiao, A., Gu, Z., Li, W., & Lu, L. (2024) · Computational Economics · doi:10.1007/s10614-024-10693-3 · Cited by 14
“PINN has achieved success in both forward and inverse complex problems in a diverse range of fields, including optics (Chen et al., 2020; Lu et al., 2021b), systems biology (Yazdani et al., 2020; Daneker et al., 2023), fluid mechanics (Raissi et al., 2020; Tartakovsky et al., 2020), solid mechanics (Wu et al., 2022),…”
InfluentialSelf-citationZhang, J., & Nie, X. (2024) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2024.107406 · Cited by 9
Variable-Order Time-Fractional Kelvin Peridynamics for Rock Steady Creep
Liu, C., Dong, T., Qi, Y., & Guo, X. (2025) · Fractal and Fractional · doi:10.3390/fractalfract9040197 · Cited by 9
PINNs failure region localization and refinement through white-box adversarial attack
Shi, S., Li, Y., Guo, Z., Wu, B., & Zhao, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132055 · Cited by 10
“They are also gaining increasing attention in areas such as fractional equations Pang, Lu and Karniadakis (2019), integro-differential equations Yuan, Ni, Deng and Hao (2022), and stochastic PDEs Zhang, Guo and Karni-adakis (2020).”
Adaptive Hybrid B-Spline PINN for Fractional Equations
Padhy, B., Mahapatra, P. S., & Samantara, T. (2026) · Annals of Mathematics and Computer Science · doi:10.56947/amcs.v35.864 · Cited by 9
“Physics-informed neural networks (PINNs) [15, 16] offer a mesh-free alternative but suffer from slow convergence and lack of theoretical error guarantees.”
Approximation of an optimal control problem for the time-fractional Fokker-Planck equation
Camilli, F., Duisembay, S., & Tang, Q. (2021) · Journal of Dynamics and Games · doi:10.3934/jdg.2021013 · Cited by 9
The coupled deep neural networks for coupling of the Stokes and Darcy–Forchheimer problems
Yue, J., Li, J., Zhang, W., & Chen, Z. (2022) · Chinese Physics B · doi:10.1088/1674-1056/ac7554 · Cited by 9
Metadata
- Authors
- Pang, G., Lu, L., & Karniadakis, G. E.
- Venue
- SIAM Journal on Scientific Computing
- Published
- 2019-01
- Volume
- 41
- Issue
- 4
- Pages
- A2603-A2626
- ISSN
- 1064-8275 (ISSN-L)
- 1095-7197
- OpenAlex
- W2900501930
- Cited by
- 1,105
- References
- 38
- Citations by year
- 2026: 253 · 2025: 260 · 2024: 195 · 2023: 155 · 2022: 119 · 2021: 82 · 2020: 35 · 2019: 6
- FWCI
- 28.01
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- SIAM Journal on Scientific Computing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Army Research Office (W911NF-18-1-0301, W911NF-15-1-0562)
- U.S. Department of Energy (DE-SC0019434, DE-SC0019453)
- Topics
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Model Reduction and Neural Networks
- Physical Sciences › Mathematics › Modeling and Simulation › Fractional Differential Equations Solutions
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- physics-informed neural networks, fractional advection-diffusion equation, fractional Poisson equation, convergence analysis, inverse problems, sampling error, optimization error
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.