The Future of Scientific Modelling: Combining Physics with Artificial Intelligence: A Review
DOI:
https://doi.org/10.31033/IJEMR/16.3.2026.1922Keywords:
Artificial Intelligence, Scientific Modelling, Physics-Informed AI, Physics-Informed Neural Networks, Scientific Machine Learning, Computational Physics, Digital Twin, Hybrid IntelligenceAbstract
Science Modelling is a traditional approach to analysing the complicated nature of physical events using mathematical equations, numerical methods, and empirical data. Despite the successful performance of the existing computational algorithms, there remain some problems related to the complexity of systems and data produced by modern scientific experiments, which cannot be solved easily using these methods. The recent development of AI technologies has made it possible to build sophisticated prediction algorithms based on data analysis, but these algorithms often yield results that contradict physical laws. The incorporation of physics in artificial intelligence has proven to be an innovative approach which blends the interpretability of physical theories with the flexibility of machine learning techniques. However, there are some drawbacks associated with such a technique including the high computational cost, optimization problems, non-interpretable nature of predictions, the need for uncertainty quantification, and scaling issues with real-world systems. This paper aims at reviewing the history of scientific modelling, exploring the concepts related to physics-integrated artificial intelligence, identifying the benefits and drawbacks associated with such a technique, and discussing the future research directions.
Downloads
References
Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021). Physics-informed machine learning. Nature Reviews Physics, 3.
Cuomo, S., Di Cola, V. S., Giampaolo, F., Rozza, G., Raissi, M., & Piccialli, F. (2022). Scientific machine learning through physics-informed neural networks. Neural Networks.
Mishra, S., & Molinaro, R. (2021). Estimates on the generalization error of physics-informed neural networks. Journal of Computational Physics.
Cai, S., Wang, Z., & Karniadakis, G. E. (2021). Physics-informed neural networks for turbulence modelling. Physical Review Fluids.
Yang, L., Meng, X., & Karniadakis, G. E. (2021). Bayesian physics-informed neural networks. Journal of Computational Physics.
Karumuri, S., et al. (2022). Scalable PINNs via domain decomposition. Computer Methods in Applied Mechanics and Engineering.
Bastek, J. H., et al. (2023). Physics-informed machine learning for quantum systems. Physical Review Research.
Pfaff, T., et al. (2021). Learning mesh-based simulation with graph networks. ICML Proceedings.
Meng, C., et al. (2025). When physics meets machine learning: A survey of physics-informed machine learning. Machine Learning for Computational Science and Engineering.
Toscano, J. D., et al. (2024). From PINNs to PIKANs: Recent advances in physics-informed machine learning.
Hybrid physics-informed artificial intelligence for high-fidelity modeling and optimization of electrical systems. Frontiers in Artificial Intelligence.
Karniadakis, G. E., et al. (2024). Recent developments in scientific machine learning and PINNs
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Dr. Jyoti Chaudhary
This work is licensed under a Creative Commons Attribution 4.0 International License.
Research Articles in 'International Journal of Engineering and Management Research' are Open Access articles published under the Creative Commons CC BY License Creative Commons Attribution 4.0 International License http://creativecommons.org/licenses/by/4.0/. This license allows you to share – copy and redistribute the material in any medium or format. Adapt – remix, transform, and build upon the material for any purpose, even commercially.
