- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes KF-SPINN, a physics-informed neural network method for solving the BGK equation in the low-Knudsen-number regime. The method builds on SPINN-BGK and introduces three main modifications: a Chapman–Enskog-based representation with an initial-layer correction (CE-ramp), multiscale shock-aligned lifting features, and a training loss combining conservation and entropy-transport residuals with a Charbonnier penalty. The authors test the method on smooth problems and 1D3V and 2D3V Riemann problems.
Critical strengths
- The improvement on the 1D shock problem is substantial. The improvement becomes more pronounced as Kn decreases, which is particularly relevant since resolving sharp shocks at small Kn is the main difficulty addressed by the paper.
- The method makes good use of the structure of the BGK equation, and the ablations are informative. The CE-ramp representation accounts for rapid relaxation toward the hydrodynamic manifold, reducing what the remainder network needs to learn.
- The method achieves high accuracy without a large increase in computational cost.
Critical weaknesses
- The main methodological contributions could be clarified. The proposed method combines several ideas from existing work, including Chapman–Enskog expansions, shock-aligned lifting, and conservation-based training. While the combination is effective, it would be helpful if the authors could explain more clearly which components are new and how they differ from the closest related methods.
- The method relies on shock information whose accuracy and availability are not fully examined. In 1D, the shock speed is prescribed from the Euler Riemann solution, while in 2D, the shock surface is estimated from a preliminary PINN and then fixed for the second stage. Table 3 shows that shock alignment is essential for accuracy, but the paper does not test how sensitive the results are to errors in the prescribed shock location. The random-speed experiments in Table 15 do not address this issue because the correct shock speed is always retained. It would be useful to test the 1D problem using a predicted shock speed, as in the 2D approach, rather than the Euler Riemann speed. A small perturbation study of the shock speed and a quantitative assessment of the extracted 2D shock surface would also help clarify this dependence.
- The numerical results need more direct comparisons of the predicted solutions. Most results are presented as averaged relative errors, with relatively few solution profiles. I would like to see more comparisons of density, velocity, and temperature at different times and Kn values, especially near the shock and contact discontinuity. This would make it easier to judge whether the method captures the shock position, thickness, and surrounding flow correctly.
- The advantage over conventional BGK solvers is not clear. The paper only compares against other neural network methods. A comparison with the conservative semi-Lagrangian solver in terms of accuracy, runtime, and memory would help assess the practical value of KF-SPINN. The computational cost of obtaining the shock information should also be reported separately.
- The tests are limited to simple shock geometries. The 1D shock tube and radially symmetric 2D problem do not fully test the method’s ability to handle more complicated shock structures. How well would the shock extraction and lifting work for interacting shocks or irregular shock fronts?
Questions for authors
Please refer to the concerns in the weaknesses section.
6 comments
Response to EvJc (2/3)
W3. More prediction profiles
We added profile plots for the 1D3V Riemann problem: , , and at five times for (Figure 17), and close-ups of the contact and the shock at for and in the format of Figure 1 (Figure 18). They show the three aspects you asked about:
- Shock position. KF-SPINN places the shock at the reference position at both Kn. NSR matches the reference at but shifts the shock by about 0.006 at .
- Shock thickness. KF-SPINN reproduces the reference thickness, whereas SPINN-BGK, Ko et al., and NSR at smear the shock.
- Surrounding flow. KF-SPINN matches the contact and the post-shock state; SPINN-BGK and Ko et al. overshoot the temperature behind the shock.
Revision location: Appendix G.3 (“Prediction profiles”), Figures 17 and 18.
W4. Comparison with the conservative semi-Lagrangian solver and cost of shock extraction.
Comparison with the conservative semi-Lagrangian solver. We compared KF-SPINN with the conservative semi-Lagrangian (CSL) solver [8] on the 1D3V and 2D3V Riemann problems at . Errors are with respect to the reference in 1D3V and to a new axisymmetric reference in 2D3V (see our response to Reviewers ZTjJ and SEHq). KF-SPINN runtime and memory are from Table 1 (one A100; the 2D3V time includes both stages and level-set fitting).
| Problem | Method | Grid | Error | Time (s) | Peak memory (GiB) | GPU |
|---|---|---|---|---|---|---|
| 1D3V Riemann | CSL (DIRK2) | , | 1.63e-4 | 930 | 11.67 | RTX PRO 6000 ×1 |
| CSL (DIRK2) | , | 2.68e-5 | 3731 | 32.74 | RTX PRO 6000 ×1 | |
| CSL (DIRK2) | , | 3.30e-6 | 6769 | 64.80 (total) | RTX PRO 6000 ×2 | |
| KF-SPINN | – | 6.35e-4 | 1550 | 0.94 | A100 ×1 | |
| 2D3V Riemann | CSL (BDF3) | , | 2.19e-2 | 71 | 153.99 (total) | RTX PRO 6000 ×2 |
| CSL (BDF3) | , | 1.45e-2 | 461 | 258.14 (total) | RTX PRO 6000 ×3 | |
| KF-SPINN | – | 1.81e-2 | 863 (total) | 1.75 | A100 ×1 |
In 2D3V, the error of KF-SPINN lies between those of the two CSL grids. The solver is faster (71 s and 461 s versus 863 s, on different GPUs) but needs 88 and 148 times the memory of KF-SPINN and two to three powerful GPUs; memory limits the solver to spatial cells. The memory of the grid-based solver grows with the product of the spatial and velocity grid sizes, which is where the separable representation pays off. In 1D3V, the solver is more accurate even on the coarsest grid at lower cost, and we do not claim an advantage there. KF-SPINN also gives a continuous solution that can be evaluated at any .
Revision location: Appendix H.3, Table 27.
Shock extraction cost. We report the runtime of each stage of the 2D3V pipeline separately (one seed):
| Component | Budget | Time |
|---|---|---|
| Preliminary prediction | 50k training iterations | 413.85 s |
| Shock detection and level-set fitting | Detection + 20k IGR iterations | 20.47 s |
| Stage-2 training | 100k training iterations | 452.99 s |
Shock detection and level-set fitting account for about 2% of the total runtime.
Revision location: Appendix G.2 (“Training time and sampling strategies” and “Accuracy and wall-clock time”), Table 21 and Figure 13.
W5. More complex shock structures.
1D3V shock–density-wave interaction problem. We add a 1D3V problem in which the shock interacts with a density wave, as in the Shu–Osher problem [9] but at the length scale of our 1D problems. The right state of the Sod problem is replaced by a stationary entropy wave:
Domain, final time, boundary conditions, and training budget follow the 1D3V Sod problem, and the reference is a Chu-reduced solution at (refinement error ). The shock speed varies over time as the shock passes through the density wave, so the shock geometry is not known in advance. The two-stage variant is therefore useful even in 1D3V: it extracts this time-varying shock from its stage-1 prediction and lifts along it. Mean macroscopic relative errors at are (Table 31):
| SPINN-BGK | Ko et al. | NSR | KF-SPINN (constant speed) | KF-SPINN (two-stage) | |
|---|---|---|---|---|---|
| 1.38e-01 | 1.06e-01 | 4.01e-02 | 1.22e-02 | 1.07e-02 |
Both the two-stage variant and constant Sod speed stay well below the baselines. In Figure 20, KF-SPINN follows the reference through the shock and the density wave, whereas SPINN-BGK and Ko et al. smear them.
Revision location: Appendix H.4 (“1D3V shock–density-wave interaction problem”), Eq. (55), Table 31, and Figure 20.
Response to EvJc (3/3)
2D3V elliptic problem. We add a non-axisymmetric 2D3V problem in which the circular interface is replaced by a -rotated ellipse with axis ratio and the same area. As in the circular case, the two-stage pipeline learns the evolving shock geometry from its stage-1 prediction. Mean macroscopic relative errors at are:
| SPINN-BGK | Ko et al. | NSR | KF-SPINN | |
|---|---|---|---|---|
| 5.91e-02 | 8.97e-02 | 2.83e-02 | 1.80e-02 | |
| 5.02e-02 | 7.83e-02 | 4.48e-03 | 4.80e-03 |
KF-SPINN attains the lowest error at and the second lowest at , extending the evidence to asymmetric shock propagation.
Shock intersection, reflection, and splitting remain future work. We will release the code upon acceptance to support further development of neural gas-kinetic solvers.
Revision location: Appendix H.4 (“2D3V elliptic problem”), Eq. (54) and Table 30.
We hope these responses address your concerns. Thank you again for your constructive feedback, which has substantially improved the clarity and completeness of our work.
Best regards,
Submission #23105 Author Team
References:
[1] Qin Lou, Xuhui Meng, and George Em Karniadakis. Physics-informed neural networks for solving forward and inverse flow problems via the Boltzmann-BGK formulation. Journal of Computational Physics, 447:110676, 2021.
[2] Qi Sun, Zhenjiang Liu, Lili Ju, and Xuejun Xu. Lift-and-embed learning method for solving scalar hyperbolic equations with discontinuous solutions. Journal of Scientific Computing, 107(3):87, 2026.
[3] Yameng Zhu, Weibing Deng, and Ran Bi. A two-stage adaptive lifting PINN framework for solving viscous approximations to hyperbolic conservation laws. arXiv preprint arXiv:2511.04490, 2025.
[4] Takeshi R. Fujimoto, Taro Kawasaki, and Keiichi Kitamura. Canny-Edge-Detection/Rankine-Hugoniot-conditions unified shock sensor for inviscid and viscous flows. Journal of Computational Physics, 396:264–279, 2019.
[5] Amos Gropp, Lior Yariv, Niv Haim, Matan Atzmon, and Yaron Lipman. Implicit geometric regularization for learning shapes. In Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pp. 3789–3799. PMLR, 2020.
[6] Shi Jin, Zheng Ma, and Keke Wu. Asymptotic-preserving neural networks for multiscale kinetic equations. Communications in Computational Physics, 35(3):693–723, 2024.
[7] Pierre Charbonnier, Laure Blanc-Feraud, Gilles Aubert, and Michel Barlaud. Two deterministic half-quadratic regularization algorithms for computed imaging. In Proceedings of 1st International Conference on Image Processing, volume 2, pp. 168–172. IEEE, 1994.
[8] Seung Yeon Cho, Sebastiano Boscarino, Giovanni Russo, and Seok-Bae Yun. Conservative semi-Lagrangian schemes for kinetic equations Part II: Applications. Journal of Computational Physics, 436:110281, 2021.
[9] Chi-Wang Shu and Stanley Osher. Efficient implementation of essentially non-oscillatory shock-capturing schemes, II. Journal of Computational Physics, 83(1):32–78, 1989.
Response to EvJc (1/3)
Dear Reviewer EvJc,
We thank you for the positive and constructive feedback, and are glad that the reviewer found the gains on 1D shock problems substantial, especially at small Kn, CE-ramp a good use of the BGK structure, the ablations informative, and the computational overhead modest. We address each comment below; revisions are marked in blue in the manuscript.
W1. Clarification of novelty.
We agree that KF-SPINN builds on existing ideas; our contributions are BGK-specific extensions of them:
Section 5.2 and Appendix G.2 ablate the representation, lifting features, and objective separately.
W2. Two-stage method for the 1D3V Riemann problem and shock sensitivity.
Two-stage method for 1D3V Riemann. As suggested, we replace the prescribed Euler shock speed with a space–time shock level set learned from the stage-1 prediction. We follow the 2D3V schedule (50k stage-1 iterations, 20k IGR iterations, and 100k stage-2 iterations) with 384 random space–time collocation points in stage 2, retaining the original 1D3V domains, velocity quadrature, and optimizer settings:
The learned geometry removes the need for a prescribed speed, keeping errors below 6.5×10−4 for Kn≥3×10−4. Accuracy degrades at Kn=10−4, consistent with the sensitivity analysis below.
Shock sensitivity. In 1D, we replace the shock speed c=1.84447 with c∈{1.5,1.7,1.8,2.0,2.2}; unlike Table 15, the correct speed is not retained. In 2D, we perturb the learned shock geometry. At Kn=10−4:
The 1D results reveal sensitivity in the thinnest-shock case, which diminishes as Kn increases (Table 18). In 2D, the error remains stable: auxiliary networks recovered the unperturbed shock surface and reduced the error for seeds 1–4, whereas recovery failed for seed 0, whose error increased for A=−0.02 (Table 20). Thank you for suggesting this test; it revealed a useful compensating role of the auxiliary features.
To assess the extracted 2D shock surface, we note that the BGK shock is a layer of finite thickness, so its location is not uniquely defined. We therefore overlay the extracted surface on the reference fields (Figures 15 and 16).