\`x^2+y_1+z_12^34\`
Advanced Search
Article Contents
Article Contents

Scientific Machine Learning: A Symbiosis

Abstract / Introduction Full Text(HTML) Related Papers Cited by
  • This editorial serves as a preface to the "Scientific Machine Learning" (SciML) special issue of the AIMS Foundations of Data Science journal. In this piece, we contend that SciML exists in a symbiotic relationship with the fields of computational science and engineering (CSE) and machine learning (ML). We highlight the progress (and limitations) of CSE and reflect on the recent successes of ML. While ML creates significant possibilities for advancing simulation techniques, it lacks the mathematical guarantees that are typically found in CSE. We argue that as SciML develops and embraces the remarkable capabilities of ML, it will support, not replace, traditional methods of CSE. We then overview some existing challenges and opportunities in this interdisciplinary field and close by introducing the special issue papers.

    Citation:

    \begin{equation} \\ \end{equation}
  • 加载中
  • [1] A. AbdelfattahV. BarraN. BeamsR. BleileJ. BrownJ.-S. CamierR. CarsonN. ChalmersV. DobrevY. Dudouit and et al., Gpu algorithms for efficient exascale discretizations, Parallel Computing, 108 (2021), 102841.  doi: 10.1016/j.parco.2021.102841.
    [2] J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al., GPT-4 technical report, arXiv preprint, arXiv: 2303.08774, 2023.
    [3] M. Ainsworth and J. T. Oden, A posteriori error estimation in finite element analysis, Computer Methods in Applied Mechanics and Engineering, 142 (1997), 1-88.  doi: 10.1016/S0045-7825(96)01107-3.
    [4] C. Badue, R. Guidolini, R. V. Carneiro, P. Azevedo, V. B. Cardoso, A. Forechi, L. Jesus, R. Berriel, T. M. Paixao, F. Mutz, et al., Self-driving cars: A survey, Expert Systems with Applications, 165 (2021), 113816. doi: 10.1016/j.eswa.2020.113816.
    [5] K. BiL. XieH. ZhangX. ChenX. Gu and Q. Tian, Accurate medium-range global weather forecasting with 3D neural networks, Nature, 619 (2023), 533-538.  doi: 10.1038/s41586-023-06185-3.
    [6] M. P. Brenner and P. Koumoutsakos, Machine learning and physical review fluids: An editorial perspective, Physical Review Fluids, 6 (2021), 070001.  doi: 10.1103/PhysRevFluids.6.070001.
    [7] E. Calvello, N. B. Kovachki, M. E. Levine and A. M. Stuart, Continuum attention for neural operators, arXiv preprint, arXiv: 2406.06486, 2024.
    [8] L. Cao, T. O'Leary-Roseberry and O. Ghattas, Derivative-informed neural operator acceleration of geometric MCMC for infinite-dimensional Bayesian inverse problems, arXiv preprint, arXiv: 2403.08220, 2024.
    [9] L. Cao, T. O'Leary-Roseberry, P. K. Jha, J. T. Oden and O. Ghattas, Residual-based error correction for neural operator accelerated infinite-dimensional bayesian inverse problems, Journal of Computational Physics, 486 (2023), 112104, 33 pp. doi: 10.1016/j.jcp.2023.112104.
    [10] H. Cheng, M. Zhang and J. Q. Shi, A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommendations, IEEE Transactions on Pattern Analysis and Machine Intelligence, 46 (2024). doi: 10.1109/TPAMI.2024.3447085.
    [11] R. Courant, Variational methods for the solution of problems of equilibrium and vibrations, Lecture Notes in Pure and Applied Mathematics, 49 (1943), 1-23.  doi: 10.1201/b16924-2.
    [12] R. CourantK. Friedrichs and H. Lewy, Über die partiellen differenzengleichungen der mathematischen physik, Mathematische Annalen, 100 (1928), 32-74.  doi: 10.1007/BF01448839.
    [13] M. Danilova, P. Dvurechensky, A. Gasnikov, E. Gorbunov, S. Guminov, D. Kamzolov and I. Shibaev, Recent theoretical advances in non-convex optimization, In High-Dimensional Optimization and Probability: With a View Towards Data Science, Springer, 2022, 79-163. doi: 10.1007/978-3-031-00832-0_3.
    [14] C. A. Felippa and R. W. Clough, The finite element method in solid mechanics, In SIAM-AMS Proceedings, American Mathematical Society, 2 (1970), 210-252.
    [15] O. Ghattas and K. Willcox, Learning physics-based models from data: Perspectives from inverse problems and model reduction, Acta Numerica, 30 (2021), 445-554.  doi: 10.1017/S0962492921000064.
    [16] A. GholamiZ. YaoS. KimC. HooperM. W. Mahoney and K. Keutzer, AI and memory wall, IEEE Micro, 44 (2024), 33-39.  doi: 10.1109/MM.2024.3373763.
    [17] P. Ghysels and R. Synk, High performance sparse multifrontal solvers on modern gpus, Parallel Computing, 110 (2022), 102897, 11 pp. doi: 10.1016/j.parco.2022.102897.
    [18] D. Gottlieb and S. A. Orszag, Numerical Analysis of Spectral Methods: Theory and Applications, SIAM, 1977.
    [19] L. Greengard and V. Rokhlin, A fast algorithm for particle simulations, Journal of Computational Physics, 73 (1987), 325-348.  doi: 10.1016/0021-9991(87)90140-9.
    [20] J. K. Gupta and J. Brandstetter, Towards multi-spatiotemporal-scale generalized PDE modeling, arXiv preprint, arXiv: 2209.15616, 2022.
    [21] Q. He, M. Perego, A. A. Howard, G. E. Karniadakis and P. Stinis, A hybrid deep neural operator/finite element method for ice-sheet modeling, Journal of Computational Physics, 492 (2023), 112428, 17 pp. doi: 10.1016/j.jcp.2023.112428.
    [22] P. Hohenberg and W. Kohn, Inhomogeneous electron gas, Physical Review, 136 (1964), B864-B871. doi: 10.1103/PhysRev.136.B864.
    [23] P. JiangC. SonneW. LiF. You and S. You, Preventing the immense increase in the life-cycle energy and carbon footprints of llm-powered intelligent chatbots, Engineering, 40 (2024), 202-210.  doi: 10.1016/j.eng.2024.04.002.
    [24] J. Jumper, R. Evans, A. Pritzel, T. Green, M. Figurnov, O. Ronneberger, K. Tunyasuvunakool, R. Bates, A. Žídek, A. Potapenko, et al., Highly accurate protein structure prediction with alphafold, Nature, 596 (2021), 583-589. doi: 10.1038/s41586-021-03819-2.
    [25] G. E. KarniadakisI. G. KevrekidisL. LuP. PerdikarisS. Wang and L. Yang, Physics-informed machine learning, Nature Reviews Physics, 3 (2021), 422-440.  doi: 10.1038/s42254-021-00314-5.
    [26] B. Keith, T. O'Leary-Roseberry, L. Lu, S. Mishra and Z. Mao, Workshop report 23w5129 scientific machine learning, 2023.
    [27] T. Kolev, P. Fischer, M. Min, J. Dongarra, J. Brown, V. Dobrev, T. Warburton, S. Tomov, M. S. Shephard, A. Abdelfattah, et al., Efficient exascale discretizations: High-order finite element methods, The International Journal of High Performance Computing Applications, 35 (2021), 527-552. doi: 10.1177/10943420211020803.
    [28] J. N. Kutz and S. L. Brunton, Parsimony as the ultimate regularizer for physics-informed machine learning, Nonlinear Dynamics, 107 (2022), 1801-1817.  doi: 10.1007/s11071-021-07118-3.
    [29] R. Lam, A. Sanchez-Gonzalez, M. Willson, P. Wirnsberger, M. Fortunato, F. Alet, S. Ravuri, T. Ewalds, Z. Eaton-Rosen, W. Hu, et al., Learning skillful medium-range global weather forecasting, Science, 382 (2023), 1416-1421. doi: 10.1126/science.adi2336.
    [30] P. D. Lax and R. D. Richtmyer, Survey of the stability of linear finite difference equations, Comm. Pure and Appl. Math., 9 (1956), 267-293.  doi: 10.1002/cpa.3160090206.
    [31] E. Lejeune, Mechanical MNIST: A benchmark dataset for mechanical metamodels, Extreme Mechanics Letters, 36 (2020), 100659.  doi: 10.1016/j.eml.2020.100659.
    [32] D. Luo, T. O'Leary-Roseberry, P. Chen and O. Ghattas, Efficient PDE-constrained optimization under high-dimensional uncertainty using derivative-informed neural operators, arXiv preprint, arXiv: 2305.20053, 2023.
    [33] N. McGreivy and A. Hakim, Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations, Nature Machine Intelligence, 6 (2024), 1256-1269.  doi: 10.1038/s42256-024-00897-5.
    [34] R. J. Melosh, Basis for derivation of matrices for the direct stiffness method, AIAA Journal, 1 (1963), 1631-1637.  doi: 10.2514/3.1869.
    [35] P. Messina, The exascale computing project, Computing in Science & Engineering, 19 (2017), 63-67.  doi: 10.1109/MCSE.2017.57.
    [36] S. MohammadzadehP. Prachaseree and E. Lejeune, Investigating deep learning model calibration for classification problems in mechanics, Mechanics of Materials, 184 (2023), 104749.  doi: 10.1016/j.mechmat.2023.104749.
    [37] R. S. Nicholson, Some examples of the numerical solution of nonlinear integral equations, Analytical Chemistry, 37 (1965), 667-671.  doi: 10.1021/ac60225a009.
    [38] J. T. Oden, Finite Elements of Nonlinear Continua, Courier Corporation, 2006.
    [39] J. T. Oden, The Third Pillar: The Computational Revolution of Science and Engineering, Commemorative Lecture at the 34th Honda Prize Award Ceremony on the 18th November 2013, 2013.
    [40] V. OommenK. ShuklaS. DesaiR. Dingreville and G. E. Karniadakis, Rethinking materials simulations: Blending direct numerical simulations with neural operators, npj Computational Materials, 10 (2024), 145.  doi: 10.1038/s41524-024-01319-1.
    [41] R. G. ParrD. P. Craig and I. G. Ross, Molecular orbital calculations of the lower excited electronic levels of benzene, configuration interaction included, The Journal of Chemical Physics, 18 (1950), 1561-1563.  doi: 10.1063/1.1747540.
    [42] J. Pathak, S. Subramanian, P. Harrington, S. Raja, A. Chattopadhyay, M. Mardani, T. Kurth, D. Hall, Z. Li, K. Azizzadenesheli, P. Hassanzadeh, K. Kashinath and A. Anandkumar, FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators, Feb. 2022.
    [43] D. A. Reed, R. Bajcsy, M. A. Fernandez, J.-M. Griffiths, R. D. Mott, J. Dongarra, C. R. Johnson, A. S. Inouye, W. Miner, M. K. Matzke, et al., Computational science: Ensuring america's competitiveness, United States. President's Information Technology Advisory Committee. National Coordination Office for Information Technology Research & Development, 2005.
    [44] R. D. Ruth, A canonical integration technique, IEEE Trans. Nucl. Sci., 30 (1983), 2669-2671.  doi: 10.1109/TNS.1983.4332919.
    [45] B. Sanderse, P. Stinis, R. Maulik and S. E. Ahmed, Scientific machine learning for closure models in multiscale problems: A review, Foundations of Data Science, 2024. doi: 10.3934/fods.2024043.
    [46] D. Silver, J. Schrittwieser, K. Simonyan, I. Antonoglou, A. Huang, A. Guez, T. Hubert, L. Baker, M. Lai, A. Bolton, et al., Mastering the game of Go without human knowledge, Nature, 550 (2017), 354-359. doi: 10.1038/nature24270.
    [47] M. TakamotoT. PraditiaR. LeiteritzD. MacKinlayF. AlesianiD. Pflüger and M. Niepert, PDEBench: An extensive benchmark for scientific machine learning, Advances in Neural Information Processing Systems, 35 (2022), 1596-1611. 
    [48] M. D. Wilkinson, M. Dumontier, I. J. Aalbersberg, G. Appleton, M. Axton, A. Baak, N. Blomberg, J.-W. Boiten, L. B. da Silva Santos, P. E. Bourne, et al., The FAIR guiding principles for scientific data management and stewardship, Scientific Data, 3 (2016), 1-9. doi: 10.1038/sdata.2016.18.
    [49] K. E. WillcoxO. Ghattas and P. Heimbach, The imperative of physics-based modeling and inverse theory in computational science, Nature Computational Science, 1 (2021), 166-168.  doi: 10.1038/s43588-021-00040-z.
    [50] A. Yesypenko and P.-G. Martinsson, GPU optimizations for the hierarchical Poincaré-Steklov scheme, In International Conference on Domain Decomposition Methods, Springer, 2022,519-528. doi: 10.1007/978-3-031-50769-4_62.
    [51] A. Yesypenko and P.-G. Martinsson, SlabLU: A two-level sparse direct solver for elliptic PDEs, Advances in Computational Mathematics, 50 (2024), 90, 28 pp. doi: 10.1007/s10444-024-10176-x.
  • 加载中
SHARE

Article Metrics

HTML views(547) PDF downloads(252) Cited by(0)

Access History

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return