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 801–900 of 1,000
A new numerical method for solving neuro-cognitive models via Chebyshev deep neural network (CDNN)
Mohammadi, K. M., Babaei, M., Hajimohammadi, Z., & Parand, K. (2025) · Applications of Mathematics · doi:10.21136/am.2025.0082-24 · Cited by 2
“Fractional Physics-Informed Neural Networks (fPINNs) were introduced in [26] to solve space-time fractional advection-diffusion equations along with their convergence analysis.”
Shaker, F., Hayati, M. M., Majidi, H., Abapour, M., Shafie‐khah, M., & Nazari‐Heris, M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-32984-5.00011-8 · Cited by 5
Surrogate Modeling of Landau Damping with Deep Operator Networks
Shekarpaz, S., Dong, C., & Huang, Z. (2025) · The Astrophysical Journal · doi:10.3847/1538-4357/adf3ac · Cited by 2
Physics-informed neural networks for fractional Navier-Stokes equations: fPINNs and f-XPINNs
Zhao, S., & Wang, Z. (2025) · Physica Scripta · doi:10.1088/1402-4896/ae19a5 · Cited by 2
Yu, X., Zhang, Y., Sun, H., Chen, Z., & Yuntian, C. (2026) · Journal of Hydrology · doi:10.1016/j.jhydrol.2026.136326 · Cited by 2
Ålund, O., Iaccarino, G., & Nordström, J. (2020) · Journal of Computational Physics · doi:10.1016/j.jcp.2020.109873 · Cited by 2
“Some previous attempts at incorporating machine learning techniques for PDEs have emerged in the literature recently.”
InfluentialBoundary-to-solution mapping for groundwater flows in a Toth basin
Sun, J., Li, J., Hao, Y., Qi, C., Ma, C., Sun, H., Begashaw, N., Comert, G., sun, Y., & Wang, Q. (2023) · Advances in Water Resources · doi:10.1016/j.advwatres.2023.104448 · Cited by 2
“We will address these issues holistically by solving the PDE boundary value problem with respect to two distinct boundary conditions using DeepONet [9, 20].”
MethodControl of Fractional Diffusion Problems via Dynamic Programming Equations
Alla, A., D’Elia, M., Glusa, C., & Oliveira, H. (2023) · Journal of Peridynamics and Nonlocal Modeling · doi:10.1007/s42102-023-00101-z · Cited by 2
“Applications of interest span a large spectrum of scientific and engineering fields, including fracture mechanics [46, 62], anomalous subsurface transport [12, 26, 59, 60, 64], phase transitions [16, 22, 40], image processing [1, 30, 42], magnetohydrodynamics [58], stochastic processes [14, 23, 53, 54], and turbulence…”
Ahmadi, M. A. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-24010-2.00007-x · Cited by 2
Jokar, M., Patnaik, S., & Semperlotti, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.13582 · Cited by 2
“Recently, researchers have employed physics informed neural networks [47], that are deep fully connected and feed forward networks, to solve the inverse problem consisting in the determination of the order characterising turbulent flows [48–50].”
BackgroundHigh-Order Partial Differential Equations Solved by the Improved Self-Adaptive PinnsPreprint
Hu, W. Y., Zheng, S., Dong, C., Chen, M., Fei, J.-X., & Gao, R. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5056812 · Cited by 2
DGNN: A Neural PDE Solver Induced by Discontinuous Galerkin MethodsPreprint
Chen, G., Xu, S., Ni, D., & Zeng, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.10021 · Cited by 2
“Then, the problem can be formulated as the minimization problem: PINNs have been further extended to address various types of PDEs, such as fractional advection-diffusion equations (fPINN) [Pang et al., 2019], Navier-Stokes equations (NSFnets) [Jin et al., 2021], etc.”
Fractional models of Reynolds-averaged Navier-Stokes equations for Turbulent flowsPreprint
Mehta, P. P. (2021) · arXiv (Cornell University) · doi:10.13140/rg.2.2.18036.88967 · Cited by 2
Zolfaghari, S., Xie, Y., Yang, J., & Jamali, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.08232 · Cited by 2
“…including PPINN for parallel-in-time learning [40], MPINN for multi-fidelity data integration [41, 42, 43, 34, 44, 45], and fPINN for fractional di ff erential equations [46, 47, 48], along with approaches such as nPINNs and DeepONet for modeling nonlocal and operator-based systems [49, 50, 51].”
Wang, X., Sun, M., Guo, Y., Yuan, C., Sun, X., Wei, Z., & Jin, X. (2024) · Journal of Computational Physics · doi:10.1016/j.jcp.2024.112804 · Cited by 1
Machine Learning Opportunities in Flight Test: Preflight Checks
Walker, J., & Claudio, D. (2024) · SN Computer Science · doi:10.1007/s42979-024-02874-6 · Cited by 2
Approximation of solution operators for high-dimensional PDEs
Gaby, N., & Ye, X. (2025) · Journal of Computational Physics · doi:10.1016/j.jcp.2024.113709 · Cited by 1
Convergence of physics-informed neural networks for fully nonlinear PDEs
Arakelyan, A., & Barkhudaryan, R. (2026) · Journal of Computational and Applied Mathematics · doi:10.1016/j.cam.2026.117740 · Cited by 1
Physics-Informed Deep Learning Method for Surrogate Modeling in Elastic Mechanics
Li, D., Lu, X., Wang, H., Liu, G. L. A. X., & Liu, X. (2025) · Advances in Applied Mathematics and Mechanics · doi:10.4208/aamm.oa-2023-0253 · Cited by 1
Reproducing kernel neural networks for nonlinear integro-differential equations
Fu, X., Yang, J., Wu, B., Gao, Y., & Yao, H. (2025) · Journal of Applied Mathematics and Computing · doi:10.1007/s12190-025-02588-9 · Cited by 1
“In [20 ], fractional PINNs (fPINNs) are systematically developed to address both forward simulation and inverse identification challenges in space-time fractional differential equations involving integral-form fractional derivative operators.”
Ding, X., Cao, K., Zhao, J., & Feng, X. (2025) · Physics of Fluids · doi:10.1063/5.0274928 · Cited by 1
Chen, T., Zhang, Z., Yan, Y., & Zhang, F. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9911-7_18 · Cited by 1
The DeepXDE framework for solving transient heat conduction problems
Feng, X., Meng, Z., Cheng, H., & Ma, L. (2025) · Journal of mechanics of materials and structures · doi:10.2140/jomms.2025.20.363 · Cited by 1
Wang, W., Pan, J., Gao, F., Liu, H., & Zhou, L. (2025) · International Journal of Computer Mathematics · doi:10.1080/00207160.2025.2558832 · Cited by 1
“In solving differential equations, the main types of networks with mature applications include: single hidden layer neural networks [65], Recurrent Neural Networks (RNN) [8], Physical-Informed Neural Networks (PINN) [23,43], Deep ReLU Neural Networks [41], Residual Neural Network [36], etc.”
Layer separation deep learning model with auxiliary variables for partial differential equations
Liu, Y., & Gu, Y. (2025) · Journal of Computational Physics · doi:10.1016/j.jcp.2025.114414 · Cited by 1
Lai, P., Chen, Y., Yang, D., Wang, R., Wang, F., & Xu, H. (2026) · Journal of Computational Physics · doi:10.1016/j.jcp.2026.115358 · Cited by 1
Generalizable Physics-Informed Learning for Stochastic Safety-Critical Systems
Wang, Z., Chern, A., & Nakahira, Y. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3622907 · Cited by 1
“Additionally, recent theoretical analyses address approximation errors [24], [25], [26], [27], generalization capabilities [28], [29], [30], [31], and convergence rates [32], [33], [34].”
Fan, H., Yap, S. P., Zhang, S., & El‐Shafie, A. (2025) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2025.070880 · Cited by 1
Potential identification via Tikhonov-PINNs
Ji, X., Jiang, Z., Song, P., & Yuan, C. (2025) · Inverse Problems · doi:10.1088/1361-6420/ae199a · Cited by 4
“The original scheme of PINNs has been employed for the recovery of constant coefficients in partial differential equations (PDEs) as well as for estimating the derivative order in fractional PDEs [22, 23].”
The forward and inverse analysis of tunnel based on weak form physics-informed deep learning
Peng, Y., Cui, Z.-H., Liu, J., Liu, Y., Li, Z., & Yang, Z. (2025) · KSCE Journal of Civil Engineering · doi:10.1016/j.kscej.2025.100434 · Cited by 1
Bansal, S., Boro, P., & Natesan, S. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114208 · Cited by 1
A Concise Review on the Numerical Treatment of Generalized Fractional Equations
Li, X., & Wong, P. J. Y. (2025) · Mathematics · doi:10.3390/math13223713 · Cited by 1
Training variation of physically-informed deep learning models
Lenau, A. T., Dimiduk, D., & Niezgoda, S. (2025) · Machine Learning: Science and Technology · doi:10.1088/2632-2153/ae5e18
“Sampling sizes ranged from [2,30] to estimate the model variation for a given number of training sessions within that range.”
Wang, C., Wu, Y., Liu, W., Mao, Y., & Hou, S. (2025) · International Journal of Solids and Structures · doi:10.1016/j.ijsolstr.2025.113773 · Cited by 1
Żurawski, M., Rodak, D., & Zalewski, R. (2025) · Advances in Science and Technology – Research Journal · doi:10.12913/22998624/210455 · Cited by 1
PDE-GANet: Partial differential equation discovery powered by adversarial learning
Wang, B., Gao, Y., & Guo, S. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108387 · Cited by 1
Zhang, T., Zhang, D., Yi, R., Guo, Z., & Shi, S. (2025) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2025.131201 · Cited by 1
Gupta, N., & Maheshwari, A. (2026) · Physica Scripta · doi:10.1088/1402-4896/ae6ad3 · Cited by 1
Towhiduzzaman, M., Mohit, M. A. A., & Asaduzzaman, A. Z. M. (2025) · Physics Open · doi:10.1016/j.physo.2025.100356 · Cited by 1
Li, K. L. K., Zhang, Y., Huang, Y., Xie, C., & Xiang, X. (2025) · Communications in Computational Physics · doi:10.4208/cicp.oa-2024-0263 · Cited by 1
A Multi-phase additive Dual-PINN framework with distance-weighted role priors
Abbas, N., Colao, V., Macrì, D., & Spataro, W. (2026) · Mathematics and Computers in Simulation · doi:10.1016/j.matcom.2026.10.042 · Cited by 1
Hao, X., Shi, J., Cao, Y., & Yang, X. (2025) · International Conference on Computer Engineering and Intelligent Control (ICCEIC) · doi:10.1109/icceic67916.2025.11309018 · Cited by 1
“Pang et al. (2019) [19] applied the Grünwald-Letnikov formula for processing fractional derivatives and integrated it with PINNs to solve the forward and inverse problems of fractional convection-diffusion equations, thus broadening the scope of PINNs to fractional PINNs (fPINNs).”
Weak Minimization-Sampling Network for Solving PDEs
Zhenqian, E., & Gao, W. (2026) · Communications in Computational Physics · doi:10.4208/cicp.oa-2024-0153 · Cited by 1
Lin, Q., & Shiue, M. (2026) · Mathematics and Computers in Simulation · doi:10.1016/j.matcom.2025.12.021 · Cited by 1
Li, H., & Tan, Z. (2026) · Applied Mathematics and Computation · doi:10.1016/j.amc.2025.129917 · Cited by 1
A data-driven integrable BFGS algorithm (IBA-PDE) for discovering PDEs
Tian, S., & Li, B. (2026) · Physica D Nonlinear Phenomena · doi:10.1016/j.physd.2026.135135 · Cited by 1
Progressive learning-based multi-stage Physics-Informed Neural Network
Liu, H., Liu, Q., Wang, G., & Zhang, X. (2026) · Nonlinear Dynamics · doi:10.1007/s11071-025-12040-z · Cited by 1
“Owing to these improvements, PINN is employed to a wide range of partial differential equations (PDEs), including integral differential equations [36], fractional differential equations [37], and stochastic differential equations [38].”
Zheng, Y., Kang, K., Zhang, Z., Liu, H., Liu, Y., & Chen, Y. (2026) · Extreme Mechanics Letters · doi:10.1016/j.eml.2026.102457 · Cited by 1
Zhou, X.-Y., & Zuo, D.-W. (2026) · Optical and Quantum Electronics · doi:10.1007/s11082-026-08716-4 · Cited by 1
“PINN have been extended to other types of equations, including integro-differential equations (Jang 2025 ), fractional partial differ - ential equations (Pang et al. 2019 ), and stochastic partial differential equations (Zhang et al. 2020 ).”
Sfalsini, H., Galatro, D., Zhang, M., Mendez, Y. F., Trigo-Ferre, R., Jeffrey, M. A., Jácome, M., Costanzo-Alvarez, V., Bazylak, J., & Amon, C. H. (2026) · Environmental Challenges · doi:10.1016/j.envc.2026.101440 · Cited by 1
Aghaei, A. A., & Zaky, M. A. (2026) · Engineering Analysis with Boundary Elements · doi:10.1016/j.enganabound.2026.106709 · Cited by 1
Dnot: feature diffusion enhanced neural operator transformer for PDEs on general geometries
Yu, H., Cao, J., Liu, X., & Chen, Z. (2026) · Engineering With Computers · doi:10.1007/s00366-026-02296-3 · Cited by 1
“Since then, numerous PINN-based methods have been proposed to solve the PDE-governed forward and inverse problems [17–21].”
Azam, M., Alhwikem, D., Ullah, N., & Alhwikem, F. (2026) · Symmetry · doi:10.3390/sym18030526 · Cited by 1
“This property has facilitated their application to challenging PDE classes, including fractional PDEs (f-PINNs) [19] and stochastic PDEs [20,21].”
Herkalyuk, M. V., & Gilchuk, A. V. (2025) · Cherkasy University Bulletin: Physical and Mathematical Sciences · doi:10.31651/2076-5851-2025-11-57 · Cited by 1
An accelerated Alikhanov-DeepONet operator learning framework for time-fractional phase-field models
Su, G., Dwivedi, H. K., & Pan, J. (2026) · Journal of Computational and Applied Mathematics · doi:10.1016/j.cam.2026.117711 · Cited by 1
Fractional Diffusion on Graphs: Superposition of Laplacian Semigroups Incorporating Memory
Deniskin, N., & Estrada, E. (2026) · Fractal and Fractional · doi:10.3390/fractalfract10040273 · Cited by 1
“A rapidly growing line of research explores the integration of fractional derivatives into learning algorithms, leading to the development of fractional-order neural networks and related architectures, with emerging applications in machine learning and artificial intelligence [55, 32].”
An optimized neural network for fractional PDEs in option pricing
Rani, I., & Verma, C. K. (2026) · Applied Mathematical Modelling · doi:10.1016/j.apm.2026.116994 · Cited by 1
Sharma, A., & Yadav, N. (2026) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2026.108686 · Cited by 1
Karkadakattil, A. (2026) · Journal of Intelligent Manufacturing and Special Equipment · doi:10.1108/jimse-12-2025-0037 · Cited by 1
EarPCG: Recovering Heart Sounds from in-Ear Audio via Physics-Informed Neural Network
Zhou, J., Zhang, Y., Pu, H., Guo, P., Zheng, T., Cai, C., & Luo, J. (2026) · doi:10.1145/3774906.3800491 · Cited by 1
Trinh, P. T., & HUYNH, H. D. (2025) · Electronic Journal of Applied Mathematics · doi:10.61383/ejam.202534116 · Cited by 1
“For fractional operators, the fPINN approach was proposed in [13], and practical implementations are available in libraries such as DeepXDE [8].”
From Data to Physics: Physics-Informed Machine Learning Frameworks in Interdisciplinary Applications
Valentim, C. A., & David, S. A. (2026) · Dynamics · doi:10.3390/dynamics6020016 · Cited by 1
“However, a foundational aspect of this integration had already been established in [102], where the fractional PINN (or fPINN) was proposed to solve space-time fractional advection-diffusion equations.”
Weak-form evolutionary Kolmogorov–Arnold Networks for solving partial differential equations
Kim, B., Zhang, J., & Lin, G. (2026) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2026.119065 · Cited by 1
Wang, T., Zhang, C. C., Xi, G., & Huang, Z. (2026) · Case Studies in Thermal Engineering · doi:10.1016/j.csite.2026.108226 · Cited by 1
Explicit-derivative hard-constrained PINNs for inflated membrane compression analysis
Shen, X., Li, Y., & Liu, C. (2026) · International Journal of Mechanical Sciences · doi:10.1016/j.ijmecsci.2026.111804 · Cited by 1
Mathematical Social Dynamics: Traditional and New Areas of Research
Vitanov, K. N., & Vitanov, N. K. (2026) · AppliedMath · doi:10.3390/appliedmath6060090 · Cited by 1
Saad, M., Sulaiman, M., Rahman, I. U., Alshammari, F. S., Laouini, G., & Salman, M. A. (2026) · Journal of Mathematics · doi:10.1155/jom/7301135 · Cited by 1
Chen, X., Zhao, W., Yang, J., Yang, W., & Liu, Y. (2026) · Fractal and Fractional · doi:10.3390/fractalfract10070446 · Cited by 1
“This integrated method is known as the fractional physics-informed neural network (fPINN) algorithm [17].”
Liu, Y., Chen, J., & Li, B. (2026) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2026.131799 · Cited by 2
Hu, X., Liao, X., Liao, Z., Wang, Z., & Gan, M. (2026) · Materials · doi:10.3390/ma19142978 · Cited by 1
“…studies [33], well-developed open-source platforms such as DeepXDE [34], and successful applications in heat transfer [35], fluid mechanics [36,37], and solid mechanics [38,39] demonstrate that physics residuals can effectively steer neural network solutions toward physically admissible…”
Pal, B., Ali, M. F., Sardar, P., Biswas, S., & Das, K. P. (2026) · International Journal of Dynamics and Control · doi:10.1007/s40435-026-02206-x · Cited by 1
“Several studies have demonstrated the effectiveness of PINNs in epidemiological modeling, including applications to COVID-19 transmission dynamics and parameter identi-fication [43, 44].”
Zhang, Z., & Li, J. (2026) · Journal of Computational Physics · doi:10.1016/j.jcp.2026.115218 · Cited by 1
Tian, Y., Peng, X., & He, J. (2026) · Advances in Differential Equations and Control Processes · doi:10.59400/adecp4514 · Cited by 1
“The foundational work of fPINNs was established by Pang et al. in 2019 [88].”
Thabet, H. (2026) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2026.118876 · Cited by 1
Ion-acoustic solitary waves in a fully relativistic astrophysical quantum plasma
Imran, A., Hossen, M. R., Ema, S. A., Fuad, M., & Mamun, A. A. (2026) · Chinese Journal of Physics · doi:10.1016/j.cjph.2026.07.045 · Cited by 1
Pashapour, M., Abbaszadeh, M., & Dehghan, M. (2026) · Engineering Analysis with Boundary Elements · doi:10.1016/j.enganabound.2026.106941 · Cited by 1
Rajchakit, G., Tajudeen, M. M., Banu, K. A., Lim, C. P., Tatar, N., & Huang, T. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109537 · Cited by 1
Meshless operator learning and nonuniform time stepping scheme for subdiffusion problems
Dwivedi, H. K., Li, X., Rajeev, R., & Peng, Y. (2026) · Communications in Nonlinear Science and Numerical Simulation · doi:10.1016/j.cnsns.2026.110883 · Cited by 1
Hasan, A. A., & Koroleva, A. P. (2026) · Computation · doi:10.3390/computation14100242 · Cited by 1
Exploring Datasets to Solve Partial Differential Equations with TensorFlow
Borzdynski, Ó. G., Borondo, F., & Curbelo, J. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-57802-2_42 · Cited by 1
Distributed Bayesian Parameter Inference for Physics-Informed Neural Networks
Bai, H., Bhar, K., George, J., & Busart, C. (2021) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc45484.2021.9683353 · Cited by 1
LaNets: Hybrid Lagrange Neural Networks for Solving Partial Differential燛quations
Li, Y., Xu, L., Mei, F., & Ying, S. (2022) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2022.021277 · Cited by 2
A Mixed Residual Hybrid Method For Failure Probability Estimation
Yao, C., Mei, J., & Li, K. (2022) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv57592.2022.10004221 · Cited by 1
Learning Interactions in Reaction Diffusion Equations by Neural Networks
Chen, S., Brunel, N., Yang, X., & Cui, X. (2023) · Entropy · doi:10.3390/e25030489 · Cited by 1
“The first class of approaches focuses on inferring coefficients from known data (e.g., [7,10,12,15,18,19]).”
BackgroundD’Elia, M., Littlewood, D. J., Trageser, J. E., Perego, M., & Bochev, P. (2023) · The IMA volumes in mathematics and its applications · doi:10.1007/978-3-031-34089-5_4 · Cited by 1
Numerical Solution of Boltzmann Equation Based on Adaptive Physics-Informed Neural Networks (aPINN)
Wu, B., & Zhong, L. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-3404-1_96 · Cited by 1
Ernst, L., & Urban, K. (2023) · International Conference on Computational Methods for Coupled Problems in Science and Engineering (COUPLED PROBLEMS) · doi:10.23967/c.coupled.2023.024 · Cited by 1
Solving the Inverse Problem of Laser with Complex-Valued Field by Physics-Informed Neural Networks
Chang, N., Huai, Y., & Li, H. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-8126-7_5 · Cited by 1
Structure-preserving discretization of fractional vector calculus using discrete exterior calculus
Jacobson, A., & Hu, X. (2023) · Computers & Mathematics with Applications · doi:10.1016/j.camwa.2023.11.012 · Cited by 1
Wei, Y.-Q., Liu, D., & Hua, C. (2023) · International Conference on Systems and Control (ICSC) · doi:10.1109/icsc58660.2023.10449848 · Cited by 1
“…successfully tackled a large number of physical phenomena with hereditary and memory characteristics such as viscoelasticity [1], complex networks [2], biological systems [3], etc. Mean-while, considerable research efforts have been devoted to fractional order systems and controllers [4],…”
BackgroundElastic full-waveform inversion using tools of neural networks
Zhang, W., & Chen, Z. (2024) · Physica Scripta · doi:10.1088/1402-4896/ad55be · Cited by 1
Jokar, M., Nair, S., & Semperlotti, F. (2026) · Mechanics Research Communications · doi:10.1016/j.mechrescom.2026.104790 · Cited by 1
“Examples include nonlinear systems [4–6], fluid mechanics [7,8], nano-optics [9], and physical systems with fractional governing equations [10,11].”
Machine Learning Solvers of Partial Differential Equations
Garikipati, K. (2024) · Interdisciplinary applied mathematics · doi:10.1007/978-3-031-62029-4_10 · Cited by 1
The variational physics-informed neural networks for time-fractional nonlinear conservation laws
Li, C., & Li, D. (2024) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2024.08.236 · Cited by 1
Hu, Z., Wang, J., Yan, X., Yao, J. P., Sun, H. Y., Yang, Y., Zhang, L., & Zhong, J. (2024) · Physics of Fluids · doi:10.1063/5.0238246 · Cited by 1
Chen, Y., Guo, W., & Zhong, X. (2025) · Journal of Computational Physics · doi:10.1016/j.jcp.2025.113768 · Cited by 1
Application of physics-informed neural networks for thin liquid film flows
Han, Q., Sun, X., Zhang, F., Shao, S., & Ma, C. (2025) · Fluid Dynamics Research · doi:10.1088/1873-7005/adb32e · Cited by 1
“Pang et al (Pang et al 2019) proposed fPINNs, extending PINNs to solve spatiotemporal fractional advection–diffusion equations.”
Guo, H., Lorin, E., Noxon, C., & Yang, X. (2025) · Journal of Scientific Computing · doi:10.1007/s10915-025-02850-z · Cited by 1
“The computation of the point spectrum of Schrödinger operators will be conducted usingneuralnetworks,specificallyemployingthePhysicsInformedNeuralNetworks(PINN) method[26–28].”
Physics Informed Neural Networks for Solving Predator-Prey Models
Slavova, A., & Ignatov, V. (2025) · Springer proceedings in mathematics & statistics · doi:10.1007/978-3-031-83398-4_15 · Cited by 1
Wang, M., Li, N., He, G., & Xu, T. (2025) · The European Physical Journal Special Topics · doi:10.1140/epjs/s11734-025-01846-y · Cited by 1
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.