Articles

2026

Physics-Aware Gaussian Splat World Models for Place-Based Climate Serious Games

Kumar, K.; Faust, K.; Hsiao, C.-H.; Butcher, D.;
60th Hawaii International Conference on System Sciences (HICSS), 2027 (accepted)

Tags: conference gaussian-splatting world-models

FORM: Robot Manipulation through Direct Material Law Identification

Tretiakov, S.; Zhao, R.; Hsiao, C.-H.; Li, X.; Thorpe, A. J.; Iqbal, H.; Chinchali, S.; Topcu, U.; Kumar, K.;
arXiv preprint arXiv:2609.38105

PDF: https://arxiv.org/abs/2609.38105 Tags: robotics mpm material-identification weak-form

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Li, X.; Kan, K.; Verma, D.; Kumar, K.; Osher, S.; Wu Fung, S.;
arXiv preprint arXiv:2607.20674

PDF: https://arxiv.org/abs/2607.20674 Tags: ml control safety

Path Planning in Physically Viable World Models

Low, S. A.; Hsiao, C.-H.; Li, X.; Thorpe, A. J.; Topcu, U.; Kumar, K.;
arXiv preprint arXiv:2607.00673

PDF: https://arxiv.org/abs/2607.00673 Tags: robotics world-models gaussian-splatting navigation

Damage detection and identification using a differentiable material point method

Cheng, J.; Kumar, K.; DeJong, M. J.;
Computers & Structures 328, 108259

Tags: mpm differentiable inverse-problems

SedNet: A physics-informed operator-learning framework for rapid sedimentation velocity analytical ultracentrifugation analysis

Basalla, A.; Kumar, K.; Cui, Z.; Williams, R. O. III;
International Journal of Pharmaceutics 698, 126972

Tags: ml operator-learning

Physically Viable World Models: A Case for Query-Conditioned Embodied AI

Thorpe, A. J.; Tretiakov, S.; Hsiao, C.-H.; Low, S. A.; Li, X.; Iqbal, H.; Bhatt, N. P.; Topcu, U.; Kumar, K.;
arXiv preprint arXiv:2605.30542

PDF: https://arxiv.org/abs/2605.30542 Tags: robotics world-models ml

Neural Operators for Multi-Task Control and Adaptation

Sewell, D.; Li, X.; Tretiakov, S.; Kumar, K.; Fridovich-Keil, D.;
arXiv preprint arXiv:2604.03449

PDF: https://arxiv.org/abs/2604.03449 Tags: ml control operator-learning

Artificial Intelligence Supporting Infrastructure Decisions

Kumar, K.;
The Handbook of Infrastructure Communication, Wiley, pp. 237-254

Tags: book ai infrastructure

Teaching Geotechnical Engineering through Murder Mystery Problem Solving

Agarwal, R., Kumar, K., Riegle-Crumb, C.;
Journal of Civil Engineering Education

Tags: teaching

Formal verification of tree-based machine learning models for lateral spreading

Kumar, K.;
arXiv preprint arXiv:2603.16983

PDF: https://arxiv.org/abs/2603.16983 Tags: ml xai liquefaction formal-verification

Domain-informed explainable boosting machines for trustworthy lateral spread predictions

Hsiao, C.-H.; Kumar, K.; Rathje, E. M.;
arXiv preprint arXiv:2603.17175

PDF: https://arxiv.org/abs/2603.17175 Tags: ml xai liquefaction

Explainable boosting machine for structural health assessment of reinforced concrete beams using crack width measurements

Shamszadeh, M. M.; Kumar, K.; Ferche, A.-C.; Bayrak, O.; Salamone, S.;
Automation in Construction 181, 106641

Tags: ml xai structural-health-monitoring

Back to Top ↑

2025

A Critical Assessment of PINNs and Operator Learning for Geotechnical Engineering

Kumar, K.;
arXiv preprint arXiv:2512.24365

PDF: https://arxiv.org/abs/2512.24365 Tags: ml sciml operator-learning

Learning Generalizable Neural Operators for Inverse Problems

Thorpe, A. J.; Tretiakov, S.; Sarkar, D. R.; Kumar, K.; Topcu, U.;
arXiv preprint arXiv:2512.18120

PDF: https://arxiv.org/abs/2512.18120 Tags: ml operator-learning inverse-problems

Zero-Shot Function Encoder-Based Differentiable Predictive Control

Iqbal, H.; Li, X.; Ingebrand, T.; Thorpe, A.; Kumar, K.; Topcu, U.; Drgoňa, J.;
Learning for Dynamics and Control (L4DC) 2026, Oral

PDF: https://arxiv.org/abs/2511.05757 Tags: conference ml control neural-ode

Parameter-Efficient Conditioning for Material Generalization in Graph-Based Simulators

Manoharan, N. R.; Iqbal, H.; Kumar, K.;
arXiv preprint arXiv:2511.05456

PDF: https://arxiv.org/abs/2511.05456 Tags: ml gns graph-neural-networks

Stability of Transformers under Layer Normalization

Kan, K.; Li, X.; Zhang, B. J.; Sahai, T.; Osher, S.; Kumar, K.; Katsoulakis, M. A.;
arXiv preprint arXiv:2510.09904

PDF: https://arxiv.org/abs/2510.09904 Tags: ml transformers deep-learning

Zero-Shot Transferable Solution Method for Parametric Optimal Control Problems

Li, X.; Kan, K.; Verma, D.; Kumar, K.; Osher, S.; Drgoňa, J.;
American Control Conference (ACC) 2026

PDF: https://arxiv.org/abs/2509.18404 Tags: conference ml control operator-learning

Structural identification of material properties and load parameters using a differentiable material point method

Cheng, J.; Kumar, K.; DeJong, M. J.;
Computer-Aided Civil and Infrastructure Engineering 40 (24), 3856-3874

Tags: mpm differentiable inverse-problems

A Decade of DesignSafe: Enabling Open Science in Natural Hazards

Rathje, E. M.; Kumar, K.; Esteva, M.; Brandenberg, S. J.; Cockerill, T.; Dawson, C.; Padgett, J. E.; Pinelli, J.-P.; Stanzione, D.;
Frontiers in Built Environment 11, 1594375

Tags: designsafe natural-hazards open-science

From images to properties: a NeRF-driven framework for granular material parameter inversion

Hsiao, C. H.; Kumar, K.;
Powders and Grains 2025

PDF: https://arxiv.org/abs/2507.09005 Tags: conference ml nerf mpm inverse-problems

SetONet: A Deep Set-based Operator Network for Solving PDEs with permutation invariant variable input sampling

Tretiakov, S., Li, X., Kumar, K.;

PDF: https://arxiv.org/abs/2505.04738 Tags: operator-learning ml

MLPs and KANs for data-driven learning in physical problems: A performance comparison

Pant, R., Li, S., Li, X., Iqbal, H., Kumar, K.;

PDF: https://arxiv.org/abs/2504.11397 Tags: kan

Towards scientific machine learning for granular material simulations – challenges and opportunities

Fransen, M., Fürst, A., Tunuguntla, D., Wilke, D.N., Alkin, B., Barreto, D., Brandstetter, J., Cabrera, M.A., Fan, X., Guo, M., Kieskamp, B., Kumar, K., Morrissey, J., Nuttall, J., Ooi, J., Orozco, L., Papanicolopulos, S.-A., Qu, T., Schott, D., Shuku, T., Sun, W.C., Weinhart, T., Ye, D., Cheng, H.;
Archives of Computational Methods in Engineering 33, 789-821

PDF: https://arxiv.org/abs/2504.08766 Tags: ml

Runout of liquefaction-induced tailings dam failure: Influence of earthquake motions and residual strength

Sordo, B.; Rathje, E.; Kumar, K.;
Soil Dynamics and Earthquake Engineering 194, 109371

PDF: https://arxiv.org/abs/2503.12727 Tags: mpm liquefaction tailings-dam earthquake

Runout of liquefaction-induced tailings dam failure: Influence of earthquake motions and residual strength

Sordo, B., Rathje, E., Kumar, K.;

PDF: https://arxiv.org/abs/2503.12727 Tags: mpm fem

Investigating the Effect of CPT in Lateral Spreading Prediction Using Explainable AI

Hsiao, C. H., Rathje, E., Kumar, K.;

PDF: https://arxiv.org/abs/2503.13389 Tags: conference xai

Back to Top ↑

2024

Micromechanical evaluation of the effective stress parameter using the multiphase lattice Boltzmann method and investigation of its hysteresis

Hosseini, R.; Kumar, K.;
Computers and Geotechnics 188, 107564

PDF: https://arxiv.org/abs/2501.00661 Tags: lbm multiphase

Measuring the effective stress parameter using the multiphase lattice Boltzmann method and investigating the source of its hysteresis

Hosseini, R., Kumar, K.;

PDF: https://arxiv.org/abs/2501.00661 Tags: lbm unsaturated

Hybrid Finite-Element and Material Point Method for Modeling Liquefaction-Induced Tailings Dam Failures

Sordo, B.; Rathje, E.; Kumar, K.;
Journal of Geotechnical and Geoenvironmental Engineering 151 (8), 04025086

PDF: https://arxiv.org/abs/2412.08040 Tags: mpm fem liquefaction tailings-dam

A hybrid Finite Element and Material Point Method for modeling liquefaction-induced tailings dam failures

Sordo, B., Rathje, E., Kumar, K.;

PDF: https://arxiv.org/abs/2412.08040 Tags: mpm fem

Machine Learning Aided Modeling of Granular Materials: A Review

Wang, M., Kumar, K., Feng, Y. T., Qu, T., Wang, M.;

PDF: https://arxiv.org/abs/2410.14767 Tags: ml

Basis-to-Basis Operator Learning using Function Encoders

Ingebrand, T., Thorpe, A. J., Goswami, S., Kumar, K., Topcu, U.;
Computer Methods in Applied Mechanics and Engineering 435, 117646

PDF: https://arxiv.org/abs/2410.00171 Tags: operator-learning

Sequential Hybrid Finite Element and Material Point Method to Simulate Slope Failures

Sordo, B., Rathje, E., Kumar, K.;

PDF: https://arxiv.org/abs/2404.15860 Tags: mpm fem

Explainable AI models for predicting liquefaction-induced lateral spreading

Hsiao, C. H, Kumar, K., Rathje, E.;

PDF: https://arxiv.org/abs/2404.15959 Dataset: https://doi.org/10.17603/ds2-6avc-1s73 Tags: xai

Modeling liquefaction-induced runout of a tailings dam using a hybrid finite element and material point method approach

Sordo, B., Rathje, E., Kumar, K.;

PDF: https://arxiv.org/abs/2404.15860 Tags: conference mpm fem

Inverse analysis of granular flows using differentiable graph neural network simulator

Choi, Y.J, Kumar, K.;

PDF: https://arxiv.org/abs/2401.13695 Dataset: https://doi.org/10.17603/ds2-0wjq-0j84 Tags: ml gns

Back to Top ↑

2023

Three-dimensional granular flow simulation using graph neural network-based learned simulator

Choi, Y.J, Kumar, K.;

PDF: https://arxiv.org/abs/2311.07416 Dataset: https://doi.org/10.17603/ds2-h3zz-gq43 Tags: ml gns

Differentiable programming for inverse estimation of soil permeability and design of duct banks

Vajapeyajula, A., Kumar, K.;

PDF: http://arxiv.org/abs/2312.15293 Tags: ml diffsim

An inverse analysis of fluid flow through granular media using differentiable lattice Boltzmann method

Wang, Q., Kumar, K.;

PDF: https://arxiv.org/pdf/2310.00810.pdf Tags: ml sciml diff-programming

Accelerating particulate and fluid simulations with graph neural networks for solving forward and inverse problems

Kumar, K., Choi, Y.J.;

PDF: https://arxiv.org/abs/2309.13348 Tags: ml gns

Reflections on teaching engineering through murder mysteries

Kumar, K.;
Journal of Technology and Science Education

PDF: https://www.jotse.org/index.php/jotse/article/view/2014/742 Tags: teaching

Graph Neural Network-based surrogate model for granular flows

Choi, Y.J, Kumar, K.;
Computers and Geotechnics

PDF: https://arxiv.org/abs/2305.05218 Tags: ml gns

Enabling knowledge discovery in natural hazard engineering datasets on DesignSafe

Mehta, C., Kumar, K.;

PDF: https://arxiv.org/abs/2304.11273 Tags: ml llm

Geotechnical Parrot Tales (GPT): Harnessing Large Language Models in geotechnical engineering

Kumar, K.;

PDF: https://arxiv.org/abs/2304.02138 Tags: ml llm

Back to Top ↑

2022

GNS: A generalizable Graph Neural Network-based simulator for particulate and fluid modeling

Kumar, K., Vantassel, J.;

PDF: https://arxiv.org/abs/2211.10228 Tags: ml gns mpm

Using explainability to design physics-aware CNNs for solving subsurface inverse problems

Crocker, J., Kumar, K., Cox, B.;

PDF: https://arxiv.org/abs/2211.08651 Tags: fwi ml cnn

Evaluation of particle motions in stabilized specimens of transparent sand using deep learning segmentation

Marx, D., Kumar, K., Zornberg, J.;

PDF: https://arxiv.org/abs/2212.02939 Tags: ml cnn porescale experiments

Multiphase lattice Boltzmann modeling of cyclic water retention behavior in unsaturated sand based on X-ray Computed Tomography

Wang, Q., Milatz, M., Hosseini, R., Kumar, K;

PDF: https://arxiv.org/abs/2209.11393 Tags: swcc lbm porescale

A frequency-velocity CNN for developing near-surface 2D Vs images from linear-array, active-source wavefield measurements

Abbas, A, Vantassel, J., Cox, B. R., Kumar, J., Crocker, J;

PDF: https://arxiv.org/abs/2207.09580 Tags: ml fwi cnn

Minority Report: A graph network oracle for in situ visualization

Kumar, K., Navratil, P., Solis, A., Vantassel, J;

PDF: https://arxiv.org/abs/2206.12683 Tags: conference ml gns insitu viz

A machine learning approach to predicting pore pressure response in liquefiable sands under cyclic loading

Choi, Y., Kumar, K.;

PDF: https://arxiv.org/abs/2206.07780 Tags: conference ml liquefaction

Hybrid Finite Element and Material Point Method to simulate granular column collapse from failure initiation to runout

Sordo, B., Rathje, E., Kumar, K.;

PDF: https://arxiv.org/abs/2206.07169 Tags: conference mpm fem

Investigating the source of hysteresis in the Soil-Water Characteristic Curve using the multiphase lattice Boltzmann method

Hosseini, R., Kumar, K., Delenne, J.Y.;

PDF: https://arxiv.org/abs/2204.07174 Tags: swcc multiphase lbm porescale

Back to Top ↑

2021

Conductive and convective heat transfer in inductive heating of subsea buried pipelines

Kumar, K., El Mohtar, C., and Gilbert, R.;
ASCE Journal of Pipeline Systems Engineering and Practice

PDF: https://arxiv.org/pdf/2112.11826.pdf Tags: heat-transfer

In-situ visualization of natural hazards with Galaxy and Material Point Method

Abram, G., Solis, A., Liang, Y., and Kumar, K.;
IEEE Computing in Science & Engineering

PDF: https://arxiv.org/pdf/2109.02754 Tags: mpm insitu viz

Effect Of Slope Angle On The Runout Evolution of Granular Column Collapse for Varying Initial Volumes

Wang, Q., Hosseini, R., Kumar, K.;
Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney 2021

PDF: https://arxiv.org/abs/2108.12866 Tags: conference granular-flow dem lbm

Power electronics packaging for in-road wireless charging installations

Ridge, A., Konaklieva, S., Bradley, S., McMahon, R. A., Kumar, K.;
IEEE Workshop on Emerging Technologies - Wireless Power (WoW), San Diego, USA, 1-4 June 2021

PDF: http://wrap.warwick.ac.uk/152746/1/WRAP-Power-electronics-packaging-in-road-wireless-charging-2021.pdf Tags: conference wireless-charging heat-transfer

Effect of Initial Volume on the Run-Out Behavior of Submerged Granular Columns

Wang, Q., Hosseini, R., Kumar, K.;
GeoCongress 2021, Dallas, USA

PDF: https://arxiv.org/abs/2011.03129 Tags: conference granular-flow dem lbm

Investigating the effect of porosity on the soil water retention curve using the multiphase Lattice Boltzmann Method

Hosseini, R., Kumar, K., Delenne, J.Y.;
Powders and Grains 2021, Buenos Aires, Argentina

PDF: https://arxiv.org/abs/2102.08420 Tags: conference lbm porescale swcc hpc

Biomechanical trade‑offs in the pelvic floor constrain the evolution of the human birth canal

Stansfield, E.; Kumar, K.; Mitteroecker, P.; Grunstra, N. D. S.;
Proceedings of the National Academy of Sciences of the United States of America (PNAS)

PDF: https://doi.org/10.5281/zenodo.4723996 Tags: fem biology