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 501–600 of 1,000
PDNNs: The parallel deep neural networks for the Navier–Stokes equations coupled with heat equation
Zhang, W., & Li, J. (2022) · International Journal for Numerical Methods in Fluids · doi:10.1002/fld.5164 · Cited by 9
D’Elia, M., & Gulian, M. (2022) · Numerical Mathematics Theory Methods and Applications · doi:10.4208/nmtma.oa-2022-0001s · Cited by 9
Hajimohammadi, Z., Parand, K., & Ghodsi, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.14320 · Cited by 9
“Baker et al. (2019) selected deep neural networks for solving the differential equations.”
BackgroundKumar, J., Zarzoso, D., Grandgirard, V., Ebert, J., & Kesselheim, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4562288 · Cited by 9
A comprehensive analysis of PINNs: Variants, Applications, and ChallengesPreprint
Sophiya, A. A., Nair, A. K., Maleki, S., & Krishnababu, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.22761 · Cited by 9
“Inspired by the limitations of PINNs for solving fractional PDEs, the initial proposal of fPINNs was made by Pang et al. in their article [43].”
Physics-informed machine learning for combustion: A reviewPreprint
Wu, J., Wang, X., Zhang, G., Liu, J., Li, X., Zhang, Y., Zhang, H., Lyu, J., Wang, B., & Wu, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.03347 · Cited by 14
Chen, J., Shi, J., He, A., & Fang, H. (2024) · Scientific Reports · doi:10.1038/s41598-024-74600-4 · Cited by 8
“The experiment results are illustrated in Figure 27, 28, 29 and 30: The top panel of Fig.”
MethodMostajeran, F., & Hosseini, S. M. (2024) · Numerical Methods for Partial Differential Equations · doi:10.1002/num.23156 · Cited by 8
“Then, the authors minimized the loss function (48) with 𝑙 = 1 and 𝑛 = 1 on the whole space-time domain Ω 𝑇 to find the optimum parameters 𝜽 ∗ , that is, For more details, interested readers can read [15].”
InfluentialPhysics-informed data-driven cavitation model for a specific Mie–Grüneisen equation of state
Huang, M., Yao, C., Wang, P., Cheng, L., & Ying, W. (2024) · Journal of Computational Physics · doi:10.1016/j.jcp.2024.113703 · Cited by 9
Ahmad, T., Sulaiman, M., Bassir, D., Alshammari, F. S., & Laouini, G. (2025) · Fractal and Fractional · doi:10.3390/fractalfract9040225 · Cited by 8
Wang, X., Wang, X., Xu, H., & Qi, H. (2025) · Communications in Nonlinear Science and Numerical Simulation · doi:10.1016/j.cnsns.2025.108833 · Cited by 8
Yang, Y., Guo, Z., & Liu, Z. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13480 · Cited by 8
“This novel loss function architecture facilitates the implementation of physics-informed training, which harnesses insights derived from the integration of physical equations and sparse observational datasets (Pang et al., 2019; Yang et al., 2020).”
Momeni, H., Cherati, A. Y., & Valinejad, A. (2025) · Physica Scripta · doi:10.1088/1402-4896/adeaf8 · Cited by 8
Santra, S., & Behera, R. (2025) · Communications in Nonlinear Science and Numerical Simulation · doi:10.1016/j.cnsns.2025.109184 · Cited by 8
Boro, P., Raina, A., & Natesan, S. (2025) · Advances in Computational Science and Engineering · doi:10.3934/acse.2025019 · Cited by 8
MLD-PINN: A multi-level datasets training method in Physics-Informed Neural Networks
Tsai, Y.-H., Juan, H.-T., Chiu, P., & Lin, C. (2025) · Computers & Fluids · doi:10.1016/j.compfluid.2025.106849 · Cited by 8
Rizvi, S. T. R., & Bukhari, S. O. A. (2025) · Physics Letters A · doi:10.1016/j.physleta.2025.131190 · Cited by 8
Diverse methods of incorporating physics into neural networks: A comprehensive review
Rajabi, M. M., Fahs, M., Bajgiran, M. M., Younès, A., & Lehmann, F. (2026) · Journal of Hydrology · doi:10.1016/j.jhydrol.2025.134903 · Cited by 9
Dynamics and Chaos Analysis of the Fractional-Order Lü System Using a Hybrid Approach
Elbadri, M., Al-Kuleab, N., Saadeh, R., Hafez, M. A., & Abdoon, M. A. (2026) · Fractal and Fractional · doi:10.3390/fractalfract10010051 · Cited by 8
Li, P., Qiao, R., Xu, C., Yao, M., & Qu, Y. (2026) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0287618 · Cited by 8
Intelligent Intercommunicating Multiscale Engineering: The Engineering of the Future
Yuan, Y., & Zhu, J. (2023) · Engineering · doi:10.1016/j.eng.2023.03.021 · Cited by 8
Physics-Informed Machine Learning for Surrogate Modeling of Heat Transfer Phenomena
Suzuki, T., Hirohata, K., Ito, Y., Hato, T., & Kano, A. (2023) · Journal of Computational and Nonlinear Dynamics · doi:10.1115/1.4063224 · Cited by 11
Gradient auxiliary physics-informed neural network for nonlinear biharmonic equation
Liu, Y., & Ma, W. (2023) · Engineering Analysis with Boundary Elements · doi:10.1016/j.enganabound.2023.09.013 · Cited by 8
Improving the Efficiency of Training Physics-Informed Neural Networks Using Active Learning
Aikawa, Y., Ueda, N., & Tanaka, T. (2024) · New Generation Computing · doi:10.1007/s00354-024-00253-6 · Cited by 8
Data-driven constitutive meta-modeling of nonlinear rheology via multifidelity neural networks
Saadat, M., Hartt, W. H., Wagner, N. J., & Jamali, S. (2024) · Journal of Rheology · doi:10.1122/8.0000831 · Cited by 9
Guo, R., Wang, J., Yan, Y., Li, D., Jin, Y., & Shan, H. (2024) · Case Studies in Construction Materials · doi:10.1016/j.cscm.2024.e03769 · Cited by 8
Shi, R., Luo, J., Zhou, N., Liu, Y., Hong, C., Zhang, X.-P. S., & Chen, X. (2025) · Building and Environment · doi:10.1016/j.buildenv.2025.112634 · Cited by 8
Anand, R., Manikandan, K., & Serikbayev, N. (2025) · The European Physical Journal Plus · doi:10.1140/epjp/s13360-025-06170-x · Cited by 8
Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models
Botelho, S., Joshi, A., Khara, B., Rao, V., Sarkar, S., Hegde, C., Adavani, S. S., & Ganapathysubramanian, B. (2020) · doi:10.1109/mlhpcai4s51975.2020.00013 · Cited by 12
Efficient optimization-based quadrature for variational discretization of nonlocal problems
Pasetto, M., Shen, Z., D’Elia, M., Tian, X., Trask, N., & Kamensky, D. (2022) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2022.115104 · Cited by 8
“Its choice is nontrivial and non-intuitive; in fact, the selection of the optimal kernel is a widely studied research question [12, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34].”
BackgroundSplines Parameterization of Planar Domains by Physics-Informed Neural Networks
Falini, A., D’Inverno, G. A., Sampoli, M. L., & Mazzia, F. (2023) · Mathematics · doi:10.3390/math11102406 · Cited by 8
“Given different initial W 0 , b 0 , it is observed that PINNs may converge to different solutions, see, e.g., [44,45].”
Wang, K., Hu, T., & Zhao, B. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3307750 · Cited by 8
Sun, S., Tian, S., & Li, B. (2024) · Results in Physics · doi:10.1016/j.rinp.2024.107386 · Cited by 8
Roop, J. P. (2024) · Results in Applied Mathematics · doi:10.1016/j.rinam.2024.100493 · Cited by 8
Jia, J., Ju, L., & Zhang, X. (2024) · International Journal of Numerical Analysis and Modeling · doi:10.4208/ijnam2024-1028 · Cited by 8
MHDnet: Physics-Preserving Learning for Solving Magnetohydrodynamics Problems
Guan, X., Hu, B., Mao, S., Wang, X., & Yang, Z. (2024) · Communications in Computational Physics · doi:10.4208/cicp.oa-2024-0002 · Cited by 8
State of mission: Battery management with neural networks and electrochemical AI
Ozkan, C. S., & Ozkan, M. (2025) · iScience · doi:10.1016/j.isci.2025.113593 · Cited by 7
“37 PINNs incorporate known physical laws— typically formulated as partial or ordinary differential equations (PDEs/ODEs), conservation laws, or boundary and initial condi-tions—into the neural network training by augmenting the loss function with residuals from these equations.”
Exploring prototype-guided strategy for domain decomposition in physics-informed neural network
Wang, Y., Peng, Y., Hu, Z., & Li, Y. (2025) · Nonlinear Dynamics · doi:10.1007/s11071-025-10871-4 · Cited by 9
“For example, Pang et al. [38] developed fractional PINNs (fPINNs) for spatiotemporal fractional ADEs, using automatic differentiation for integer derivatives and numerical methods for fractional derivatives, thus overcoming challenges with fractional derivatives in neural networks.”
Sivalingam, S. M., Govindaraj, V., & Dubey, S. A. (2025) · Engineering Analysis with Boundary Elements · doi:10.1016/j.enganabound.2025.106281 · Cited by 7
Wu, T., Zhao, C., & Liu, X. (2025) · Computers & Mathematics with Applications · doi:10.1016/j.camwa.2025.06.006 · Cited by 7
Yang, X., Wang, L., Cui, J., Xu, J. K., Wu, M., Liu, J., & Zhu, H. (2025) · Physics of Fluids · doi:10.1063/5.0266451 · Cited by 7
Chen, Z., Qiu, C., Li, Z., & Xu, S. (2025) · Physics of Fluids · doi:10.1063/5.0278224 · Cited by 7
Sahoo, A. K., Sahoo, S. K., & Chakraverty, S. (2025) · IEEE Access · doi:10.1109/access.2025.3602179 · Cited by 7
“Their work sparked widespread interest, leading to rapid advancements in PINNs by researchers around the globe [27], [28], [29], [30], [31], [32].”
Kumar, Y., & Vats, R. K. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114379 · Cited by 7
Chen, G., Ju, L., & Qiao, Z. (2026) · Numerical Methods for Partial Differential Equations · doi:10.1002/num.70133 · Cited by 7
“PINN [ 9, 21] and its extensions [ 6 – 8, 10, 11] have become popular deep learning techniques for solving PDEs.”
Yang, Z., Li, D., Nai, W., Liu, L., Sun, J., & Lv, X. (2024) · IEEE Access · doi:10.1109/access.2024.3356173 · Cited by 7
“To be more specific, Pang et al. have proposed the fractional PINN (fPINN) method for solving fractional order PDEs [55], Lu et al. from the same research team have also provided the DeepXDE ML library for solving PDEs based on the PINN method, and this ML library for scientific computing has been…”
MethodSelf-knowledge Distillation Enhanced Universal Framework for Physics-Informed Neural Networks
Li, Y., Yang, J., & Wang, D. (2025) · Nonlinear Dynamics · doi:10.1007/s11071-025-10916-8 · Cited by 7
“PINNs and these variants have achieved remarkable successes in solving both forward and inverse PDE problems, including the Navier-Stokes equation [27,28], stochastic partial differential equations [29], and fractional partial differential equations [30].”
Forward and Backward Problems for Coupled Subdiffusion Systems
Feng, D., Liu, Y., & Lu, S. (2025) · Numerical Functional Analysis and Optimization · doi:10.1080/01630563.2025.2451929 · Cited by 7
“While several studies have explored this field, for instance, the work presented in [7, 22], it is noteworthy that most existing results focused on the single equation, with limited exploration of coupled systems.”
Neural networks optimized by data-driven gradient physics for soliton pulse equation solutions
Rizvi, S. T. R., Abbas, S., Shahid, A., Abdel‐Khalek, S., & SEADAWY, A. R. (2025) · Advances in Complex Systems · doi:10.1142/s1793962325500424 · Cited by 7
Application of PINN to obtain solution of boundary layer problems arising in fluid dynamics
Raina, A., Badireddi, S., & Natesan, S. (2025) · Mathematical Foundations of Computing · doi:10.3934/mfc.2025024 · Cited by 7
Physics-informed neural network approach to quark-antiquark color flux tube
Kou, W., Lin, X., Guo, B., & Chen, X. (2025) · Physical review. D/Physical review. D. · doi:10.1103/z61n-r7gw · Cited by 7
“[61, 62], are highly instructive—particularly the auxiliary PINNs strategy proposed in Ref.”
Zhang, J., Tian, X., & Zhou, C. S. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113907 · Cited by 7
Li, Y., & Zhang, L. (2025) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa65407.2025.11166586 · Cited by 7
“This emergent paradigm represents a fundamentally different approach to numerical simulation, combining the flexibility of machine learning with the rigor of physical principles [18]– [20].”
Eshkofti, K., & Hosseini, S. M. (2022) · Waves in Random and Complex Media · doi:10.1080/17455030.2022.2083264 · Cited by 7
“PINN is widely applicable for solving inverse problems [41], fractional differential equations [42], and stochastic differential equations [33] and [43,44].”
FDM-PINN: Physics-informed neural network based on fictitious domain method
Yang, Q., Yang, Y., Cui, T., & He, Q. (2022) · International Journal of Computer Mathematics · doi:10.1080/00207160.2022.2128674 · Cited by 7
“[29] for solving forward and inverse problems involving nonlinear PDEs has led to some remarkable results for solving a variety of problems, including heat transfer problems [5], finance [2], uncertainty quantification [8,27,37], stochastic partial differential Equations (SPDEs) [19,39], inverse problems [6,18], integ…”
BackgroundMethodA physics-informed learning approach to Bernoulli-type free boundary problems
Cuomo, S., Giampaolo, F., Izzo, S., Nitsch, C., Piccialli, F., & Trombetti, C. (2022) · Computers & Mathematics with Applications · doi:10.1016/j.camwa.2022.10.003 · Cited by 7
MC-Nonlocal-PINNs: Handling Nonlocal Operators in PINNs via Monte Carlo Sampling
Feng, X., Qian, Y., & Shen, W. (2023) · Numerical Mathematics Theory Methods and Applications · doi:10.4208/nmtma.oa-2022-0201 · Cited by 7
A deep learning method for computing mean exit time excited by weak Gaussian noise
Li, Y., Zhao, F., Xu, S., Duan, J., & Liu, X. (2024) · Nonlinear Dynamics · doi:10.1007/s11071-024-09280-w · Cited by 7
“Recent years have witnessed a wide range of applications of PINNs, including Navier–Stokes equations in fluid mechanics [31], fractional equations [32], integro-differential equations [33], and stochastic dynamics [19,34].”
Sun, J., Dong, H., Liu, M., & Fang, Y. H. (2024) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0209068 · Cited by 7
DIFFUSION ON FRACTAL OBJECTS MODELING AND ITS PHYSICS-INFORMED NEURAL NETWORK SOLUTION
Zhao, D., Yu, G., & Li, W. (2020) · Fractals · doi:10.1142/s0218348x21500717 · Cited by 7
On the Prescription of Boundary Conditions for Nonlocal Poisson’s and Peridynamics Models
D’Elia, M., & Yu, Y. (2022) · Association for Women in Mathematics series · doi:10.1007/978-3-031-04496-0_8 · Cited by 7
A New Artificial Neural Network Method for Solving Schrödinger Equations on Unbounded Domains
Wilson, J. P., Dai, W., Bora, A., & Boyt, J. C. (2022) · Communications in Computational Physics · doi:10.4208/cicp.oa-2022-0135 · Cited by 7
A Framework for Physics-Informed Deep Learning Over Freeform DomainsPreprint
Mezzadri, F., Gasick, J., & Qian, X. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4260001 · Cited by 7
A Stabilized Physics Informed Neural Networks Method for Wave Equations
Jiao, Y., Liu, Y., Yang, J. Z. Y. J. Z., & Yuan, C. R. (2024) · Numerical Mathematics Theory Methods and Applications · doi:10.4208/nmtma.oa-2024-0044 · Cited by 6
Multi-benchmark adaptive sampling physics-informed neural network for complex and coupled equations
Zhang, Y., Deng, L.-J., & Feng, M. (2025) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0296969 · Cited by 6
Rahman, J. U., Arshad, M., & Mustafa, N. (2025) · International Journal of Applied and Computational Mathematics · doi:10.1007/s40819-025-02071-w · Cited by 6
“This exponential decay not only guarantees convergence but also quantifies the rate at which the system returns to the DFE.”
An accurate and robust numerical method for solving distributed-order space–time fractional PDEs
Ghoreyshi, A., Abbaszadeh, M., Zaky, M. A., & Dehghan, M. (2025) · Zeitschrift für angewandte Mathematik und Physik · doi:10.1007/s00033-025-02627-2 · Cited by 6
“Recently, an increasing number of studies across various areas have focused on dynamical systems modeled by fractional differential”
Su, M., Zhang, Z., Liu, M., Qi, F., Jiang, Y., & Liu, W. (2026) · Nonlinear Dynamics · doi:10.1007/s11071-025-12034-x · Cited by 6
“…studies have demonstrated the successful application of PINNs in diverse domains, including modeling threshold curves [26], fractional-order PINNs [27], nonlinear convection–reaction–diffusion equations [28], computational solid mechanics [29], heat transfer problems [30], and metal additive…”
Physics-informed time series analysis with Kolmogorov-Arnold networks under Ehrenfest constraints
Sen, A., Lukin, I. V., Jacobs, K. A., Kaplan, L., Sotnikov, A., & Bondar, D. I. (2026) · Physical Review Research · doi:10.1103/84vm-tvzm · Cited by 6
A nonlocal mechanics-informed neural network homogenization for variable-density lattice structures
Zhang, R., Li, S., Wu, Z., Wu, D., & Li, L. (2026) · Thin-Walled Structures · doi:10.1016/j.tws.2026.114957 · Cited by 6
Aich, R., & Bhargavi, D. N. (2026) · International Communications in Heat and Mass Transfer · doi:10.1016/j.icheatmasstransfer.2026.111293 · Cited by 6
A physics-informed kernel approach to learning the operator for parametric PDEs
Kurz, J., Bowman, B., Seman, M., Oian, C. A., & Khan, T. R. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10460-3 · Cited by 6
“…research tailored this concept to specific frameworks such as developments in PINNs targeting problems in fluid mechanics [9] and broadened the versatility of PINNs to handle other classes of PDEs as in [10, 11], which solve instances of fractional and time-dependent stochastic PDEs, respectively.”
Fazal, F., Sulaiman, M., Bassir, D., Alshammari, F. S., & Laouini, G. (2024) · Fractal and Fractional · doi:10.3390/fractalfract8110671 · Cited by 6
Meng, R., Chen, J., & Xu, Z. H. (2025) · Physics of Fluids · doi:10.1063/5.0255323 · Cited by 6
Regularity-conforming neural networks (ReCoNNs) for solving partial differential equations
Taylor, J. M., Pardo, D., & Muñoz‐Matute, J. (2025) · Journal of Computational Physics · doi:10.1016/j.jcp.2025.113954 · Cited by 6
Xu, H., Yu, X., Liu, J., & Gao, X. Y. (2025) · Computational Materials Science · doi:10.1016/j.commatsci.2025.113887 · Cited by 6
Wang, L., Qiu, C., Wang, Y., & Wang, M. (2025) · International Journal of Computer Mathematics · doi:10.1080/00207160.2025.2531523 · Cited by 6
“To address this, we adopt the classical L 1 finite difference method [29] for approximating the Caputo derivative.”
InfluentialR-PINN: Recovery-type a-posteriori estimator enhanced adaptive PINN
Lu, R., Jia, J., Lee, Y. J., Lu, Z. C., & Zhang, C.-S. (2026) · Journal of Computational Physics · doi:10.1016/j.jcp.2026.114684 · Cited by 6
Javadi, R., Mesgarani, H., Nikan, O., & Avazzadeh, Z. (2023) · Symmetry · doi:10.3390/sym15061275 · Cited by 6
“[29] presented fractional physics-informed neural networks to solve space-time fractional advection-diffusion equations.”
BackgroundA learned conservative semi-Lagrangian finite volume scheme for transport simulations
Chen, Y., Guo, W., & Zhong, X. (2023) · Journal of Computational Physics · doi:10.1016/j.jcp.2023.112329 · Cited by 6
“As an e ff ective alternative to the traditional numerical algorithms, PINNs have been widely deployed to solve complex problems in various fields, see [18, 33–36, 42, 53].”
MethodModeling of Near-and Far-Field Diffraction from EUV Absorbers Using Physics-Informed Neural Networks
Medvedev, V., Erdmann, A. A., & Roßkopf, A. (2023) · Photonics & Electromagnetics Research Symposium (PIERS) · doi:10.1109/piers59004.2023.10221390 · Cited by 6
“The 91800 training points {(x, z)} were distributed across the computational domain using the Sobol sampling sequence [20] to improve the prediction accuracy.”
MethodChang, N., Huai, Y., Liu, T., Chen, X., & Jin, Y. (2023) · Physics of Fluids · doi:10.1063/5.0167744 · Cited by 6
Vats, Y., Mehra, M., Oelz, D., & Singh, A. K. (2024) · Journal of Computational and Nonlinear Dynamics · doi:10.1115/1.4066330 · Cited by 9
Gaire, P., & Bhardwaj, S. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128936 · Cited by 6
Lorin, E., & Yang, X. (2024) · Computer Physics Communications · doi:10.1016/j.cpc.2024.109129 · Cited by 6
Neural PDE Solvers for Irregular Domains
Khara, B., Herron, E., Balu, A., Gamdha, D., Yang, C.-H., Saurabh, K., Jignasu, A., Jiang, Z., Sarkar, S., Hegde, C., et al. (2024) · Computer-Aided Design · doi:10.1016/j.cad.2024.103709 · Cited by 6
Fractional Order System Identification with Occupation Kernel Regression
Li, X., & Rosenfeld, J. A. (2021) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc50511.2021.9483209 · Cited by 6
Alzahrani, H., Turkiyyah, G. M., Knio, O., & Keyes, D. E. (2022) · Communications on Applied Mathematics and Computation · doi:10.1007/s42967-021-00184-9 · Cited by 6
“Beyond anomalous diffusion, diverse problems in physics-informed neural networks [32], image denoising [18,9], and sampling from random gaussian fields in spatial statistics [4] also benefit from the ability of fractional operators to capture nonlocal effects and control solution regularity.”
BackgroundLearning To Solve Differential Equations Across Initial ConditionsPreprint
Malik, S., Anwar, U., Ahmed, A. M., & Aghasi, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12159 · Cited by 6
Sandia National Laboratories (SNL-CA), L., Capodaglio, G., USDOE National Nuclear Security Administration (NNSA). Office of Defense Programs (DP), Sandia National Laboratories (SNL), A., D’Elia, M., Günzburger, M., Bochev, P., Klar, M., & Vollmann, C. (2020) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.2172/1656938 · Cited by 6
Model-Constrained Deep Learning Approaches for Inverse Problems.Preprint
Nguyen, H. V., & Bui–Thanh, T. (2021) · arXiv (Cornell University) · Cited by 6
Wu, G.-Z., Fang, Y., Wang, Y., & Dai, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.13192 · Cited by 7
“In addition, many other improved PINNs have emerged, such as variational PINN (Kharazmi et al., 2021) and fractional PINN (Mehta et al., 2019; Pang et al., 2019) methods.”
D’Elia, M., Littlewood, D., Trageser, J. E., Perego, M., & Bochev, P. (2021) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.2172/1825041 · Cited by 6
Dong, L., Qilong, C., Zhixin, P., Maokang, L., & Shouming, Z. (2024) · Scientia Sinica Mathematica · doi:10.1360/ssm-2024-0040 · Cited by 5
Dabiri, D., DaRosa, J. J., Saadat, M., Mangal, D., & Jamali, S. (2026) · Artificial Intelligence for Engineering · doi:10.1049/aie2.70024 · Cited by 5
“Seminal work of Pang and coworkers introduced application of PINNs to fractional derivatives, referred to as fPINNs, for solving forward and inverse advection-diffusion equations with the GL method [39].”
Li, P., & Chen, J. (2026) · Journal of Computational Physics · doi:10.1016/j.jcp.2026.114938 · Cited by 5
Wu, Q., Ma, F., & Wo, W. (2025) · Mathematical Methods in the Applied Sciences · doi:10.1002/mma.11149 · Cited by 5
“The fPINN algorithm [23] is at the leading level in solving fPDEs, which combines PINNs with finite difference schemes, so we compare the numerical results of the proposed method with those of fPINN. and 𝑓 ( 𝑢 ) = 0 (28) In this example, the basis function 𝑖 ( 𝑥 ) is chosen as Chebyshev…”
PINN-DTC: Adaptive partitioning of physics-informed neural network for designing thermal cloak
Gan, Z., & Yu, B. (2025) · Computers & Mathematics with Applications · doi:10.1016/j.camwa.2025.07.037 · Cited by 5
Ma, S., Li, B. Q., & Li, H. (2025) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2025.117106 · Cited by 5
Chebyshev-Sobolev Physics-Informed Neural Networks for General PDE Solutions
Chen, S., Xiong, S., & Liu, Y. (2025) · International Journal of Applied and Computational Mathematics · doi:10.1007/s40819-025-01988-6 · Cited by 5
“Beyond just solving equations, PINNs also help with uncertainty quantification, allowing scientists to assess how reliable their predictions are through techniques like Bayesian methods and dropout, which has proven valuable for real-world applications [26, 36, 37].”
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.