Physics-Informed Neural Networks for High-Fidelity Electromagnetic Field Approximation in VLSI and RF EDA Applications

Haijian Zhang

doi:10.54097/5eqd7y93

Authors

Haijian Zhang

DOI:

https://doi.org/10.54097/5eqd7y93

Keywords:

Physics-Informed Neural Networks, VLSI Design, RF EDA, Electromagnetic Simulation, Circuit Modeling, Interconnect Analysis, Substrate Coupling, Neural Network Architecture

Abstract

The increasing complexity of Very Large Scale Integration (VLSI) circuits and Radio Frequency (RF) systems demands sophisticated electromagnetic field analysis capabilities that traditional Electronic Design Automation (EDA) tools struggle to provide efficiently. This research presents a novel Physics-Informed Neural Network (PINN) framework specifically tailored for high-fidelity electromagnetic field approximation in VLSI and RF Electronic Design Automation applications. The proposed methodology integrates Maxwell's equations with advanced neural network architectures to enable accurate field prediction across diverse frequency ranges from DC to millimeter-wave operations while maintaining computational efficiency suitable for interactive design workflows. Through comprehensive validation across representative VLSI interconnect structures, RF passive components, and millimeter-wave integrated circuits, our PINN framework demonstrates superior accuracy compared to conventional moment-based methods while achieving computational speedup factors of 45-150× for typical design scenarios. The framework successfully captures complex electromagnetic phenomena including substrate coupling, crosstalk mechanisms, and frequency-dependent losses with mean absolute errors below 3.8% across frequency ranges spanning DC to 300 GHz. The adaptive mesh-free formulation eliminates geometric discretization constraints that limit traditional EDA tools, enabling seamless analysis of irregular conductor geometries and multi-layer dielectric stackups common in advanced semiconductor processes. Real-time field visualization capabilities facilitate intuitive understanding of electromagnetic coupling mechanisms, supporting design optimization workflows that were previously computationally prohibitive. The framework incorporates specialized handling of conductor loss mechanisms, dielectric dispersion effects, and substrate characteristics specific to semiconductor manufacturing processes, ensuring practical relevance for modern VLSI and RF design challenges. Validation against commercial EDA software demonstrates comparable accuracy for standard benchmarks while providing substantial performance advantages for parametric analysis and optimization applications critical to contemporary circuit design methodologies.

Downloads

Download data is not yet available.

References

[1] Božanić, M., & Sinha, S. (2020). Millimeter-wave integrated circuits. Cham, Switzerland: Springer.

[2] Taur, Y., & Ning, T. H. (2021). Fundamentals of modern VLSI devices. Cambridge university press.

[3] Tong, C. (2022). Pcb materials and design requirements for 5g systems. In Advanced Materials and Components for 5G and Beyond (pp. 77-108). Cham: Springer Nature Switzerland.

[4] Bucolo, M., Buscarino, A., Fortuna, L., Famoso, C., Frasca, M., Cucuccio, A., ... & Vinci, G. (2021). A comparative analysis of computer-aided design tools for complex power electronics systems. Energies, 14(22), 7729.

[5] Areias, C. (2025). Advanced Design, Simulation, and Fabrication of Additively Manufactured Microwave Electronics With Novel Shielding and High-Power Integration Techniques (Doctoral dissertation, University of Massachusetts Lowell).

[6] Jung, I., Peng, Z., & Rahmat-Samii, Y. (2024). Recent advances in reconfigurable electromagnetic surfaces: Engineering design, full-wave analysis, and large-scale optimization. Electromagnetic Science, 2(3), 1-25.

[7] Hao, Z., Liu, S., Zhang, Y., Ying, C., Feng, Y., Su, H., & Zhu, J. (2022). Physics-informed machine learning: A survey on problems, methods and applications. arXiv preprint arXiv:2211.08064.

[8] Rahman, M. M. (2023). A Deep Learning Approach for Computational Electromagnetics. McGill University (Canada).

[9] Bi, J., Hanke, F., Ji, H., McLendon, R., Todd, S., Dalrymple, T., ... & Oancea, V. (2021). Multiscale modeling for the science and engineering of materials. International Journal for Multiscale Computational Engineering, 19(3).

[10] Kim, S., Xu, J., Shang, W., Xu, Z., Lee, E., & Luo, T. (2024). A review on machine learning-guided design of energy materials. Progress in Energy, 6(4), 042005.

[11] Ibrahim, H. H., Singh, M. J., Al-Bawri, S. S., Ibrahim, S. K., Islam, M. T., Alzamil, A., & Islam, M. S. (2022). Radio frequency energy harvesting technologies: A comprehensive review on designing, methodologies, and potential applications. Sensors, 22(11), 4144.

[12] Abdelraouf, O. A., Ahmed, A., Eldele, E., & Omar, A. A. (2025). Physics-Informed Neural Networks in Electromagnetic and Nanophotonic Design. arXiv preprint arXiv:2505.03354.

[13] Sarma, M. P., & Sarma, K. K. (2025). Optimization Techniques in VLSI Circuits: An Analytical Perspective of the Current State of the Art. In Exploring the Intricacies of Digital and Analog VLSI (pp. 143-182). IGI Global Scientific Publishing.

[14] Seo, J. (2024). Solving real-world optimization tasks using physics-informed neural computing. Scientific Reports, 14(1), 202.

[15] Raut, P., Panda, D. K., & Goyal, A. K. (2025). A Comprehensive Review on Next-Generation Modelling and Optimization for Semiconductor Devices. IEEE Access.

[16] Chen, L., Chen, Y., Chu, Z., Fang, W., Ho, T. Y., Huang, R., ... & Zou, S. (2024). The dawn of ai-native eda: Opportunities and challenges of large circuit models. arXiv preprint arXiv:2403.07257.

[17] Klapa Antonion, X. W., Raissi, M., & Joshie, L. (2024). Machine learning through physics–informed neural networks: Progress and challenges. Academic Journal of Science and Technology, 9(1), 2024.

[18] Ren, Z., Zhou, S., Liu, D., & Liu, Q. (2025). Physics-Informed Neural Networks: A Review of Methodological Evolution, Theoretical Foundations, and Interdisciplinary Frontiers Toward Next-Generation Scientific Computing. Applied Sciences, 15(14), 8092.

[19] Deng, Y., Fan, K., Jin, B., Malof, J., & Padilla, W. J. (2025). Physics-informed learning in artificial electromagnetic materials. Applied Physics Reviews, 12(1).

[20] Sharma, S. (2022). Advanced Boundary Element Techniques for Multiregion and Multiscale Electromagnetic Modelling (Doctoral dissertation, University of Toronto (Canada)).

[21] Yang, W. T. (2020). An integrated physics-informed process control framework and its applications to semiconductor manufacturing (Doctoral dissertation, Université de Lyon).

[22] Abouelyazid, M. S., Hammouda, S., & Ismail, Y. (2022). Accuracy-based hybrid parasitic capacitance extraction using rule-based, neural-networks, and field-solver methods. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 41(12), 5681-5694.

[23] Khetarpal, V., Gupta, L., Dhand, R., & Sharma, P. (2023, December). Machine Learning Techniques for VLSI Circuit Design: A Review. In International Conference on Intelligent Systems Design and Applications (pp. 191-199). Cham: Springer Nature Switzerland.

[24] Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021). Physics-informed machine learning. Nature Reviews Physics, 3(6), 422-440.

[25] Santra, A., Wang, P., Shaker, G., Mysore, B. S., Dolmans, G., Chen, Y., ... & Pandharipande, A. (2025). Machine Learning-Powered Radio Frequency Sensing: A Review. IEEE Sensors Journal.

[26] Kiarashinejad, Y., Abdollahramezani, S., & Adibi, A. (2020). Deep learning approach based on dimensionality reduction for designing electromagnetic nanostructures. npj Computational Materials, 6(1), 12.

[27] Ma, W., Liu, Z., Kudyshev, Z. A., Boltasseva, A., Cai, W., & Liu, Y. (2021). Deep learning for the design of photonic structures. Nature photonics, 15(2), 77-90.

[28] Liu, X., Wang, Z., Ji, H., & Gong, H. (2024). Application and comparison of several adaptive sampling algorithms in reduced order modeling. Heliyon, 10(15).

[29] Wu, Y. (2023). Local Resonance-Based Rail Neutral Temperature Estimation (Doctoral dissertation, The University of Utah).

[30] Katkevičius, A., Plonis, D., Damaševičius, R., & Maskeliūnas, R. (2022). Trends of microwave devices design based on artificial neural networks: A review. Electronics, 11(15), 2360.

[31] Taj, R. (2024). Physics-Informed Neural Networks for Electrical Circuit Analysis: Applications in Dielectric Material Modeling. arXiv preprint arXiv:2411.10483.

[32] Ayari, M., Gharbi, A., El Touati, Y., Klai, Z., & Elsayed, M. S. (2024). Advanced Numerical Methods in Electromagnetics: Techniques and Applications. Letters in High Energy Physics, 791-803.

[33] Feng, T., Zhou, H., Cheng, Z., Larkin, L. S., & Neupane, M. R. (2023). A critical review of thermal boundary conductance across wide and ultrawide bandgap semiconductor interfaces. ACS applied materials & interfaces, 15(25), 29655-29673.

[34] Rech, P. (2024). Artificial neural networks for space and safety-critical applications: Reliability issues and potential solutions. IEEE Transactions on Nuclear Science, 71(4), 377-404.

[35] Wang, J., Wu, Y., Cao, H., Wang, Y., & Zhang, A. (2025). First-principles calculations innovation in wide bandgap semiconductors: Multiphysics field coupling and functional device design. CHAIN.

[36] Ahn, W. (2019). Multi-scale, multi-physics reliability modeling of modern electronic devices and system (Doctoral dissertation, Purdue University).

[37] Zhang, K., Zorba, D., Meda, A., Beerens, L., & Higham, D. J. Adversarial Attacks on Convolutional Neural Networks with General Purpose Optimization Software. Modelling, Data Analytics and AI in Engineering.