Jun 2026· International Journal of Education, Modern Management, Applied Science & Social Science· Vol 08, pp. 223-229· 0 citations
TL;DR
This review provides a comprehensive overview of AI methodologies applied to physics, highlighting the growing importance of hybrid AI-physics models, explainable artificial intelligence, quantum machine learning, scientific foundation models, and autonomous laboratories as the next generation of intelligent scientific research systems.
Abstract
Artificial Intelligence (AI) has emerged as a transformative paradigm in modern physics, fundamentally changing the way researchers model complex systems, analyze experimental data, and discover new physical laws. The convergence of machine learning (ML), deep learning (DL), and physics-informed computational methods has significantly accelerated research across theoretical and applied physics (Karniadakis et al., 2021; Zhang et al., 2023). Unlike traditional computational techniques that often require extensive numerical simulations and handcrafted models, AI-based approaches learn complex relationships directly from data while increasingly incorporating physical constraints to improve accuracy and interpretability (Willard et al., 2022). Recent advances in Physics-Informed Neural Networks (PINNs), neural differential equations, graph neural networks, symbolic regression, and generative AI have enabled efficient solutions to challenging problems in quantum mechanics, high-energy physics, cosmology, materials science, climate modeling, and computational physics (Raissi et al., 2019; Chen et al., 2018; Bronstein et al., 2021; Cranmer et al., 2020). AI has also enhanced experimental automation by optimizing instrument control, accelerating data processing, and supporting autonomous scientific discovery (King et al., 2009). Despite these remarkable achievements, several challenges remain, including limited data availability, model interpretability, physical consistency, computational cost, and the generalization of AI models beyond training datasets (Rudin, 2019; Willard et al., 2022). This review provides a comprehensive overview of AI methodologies applied to physics, highlighting their theoretical foundations, practical applications, current limitations, and emerging research directions. The paper concludes by emphasizing the growing importance of hybrid AI-physics models, explainable artificial intelligence, quantum machine learning, scientific foundation models, and autonomous laboratories as the next generation of intelligent scientific research systems.
This review examines the evolution of physical modelling from classical first-principles approaches to contemporary data-driven and physics-informed learning frameworks. It begins with the historical foundations of scientific modelling, including classical mechanics, field equations, computational simulation, and statistical mechanics, and shows how these traditions established differential equations and numerical methods as core tools in science and engineering. The review then discusses the rise of data-driven modelling, covering statistical learning, machine learning, deep learning, and Gaussian processes, with attention to their strengths in handling complex nonlinear systems and their limitations in interpretability, data requirements, and physical consistency. A central focus is placed on Physics-Informed Neural Networks (PINNs) and related hybrid methods that integrate governing laws into learning algorithms to improve prediction, generalization, and physical plausibility. Applications across fluid dynamics, structural engineering, climate science, biomedicine, materials discovery, and energy systems are highlighted. Finally, the review identifies key challenges related to scalability, uncertainty quantification, robustness, and benchmarking, and outlines future directions such as active learning, operator learning, and scientific foundation models.
Eshit Dhiman· International journal of mul...· 0 citations
Artificial Intelligence (AI) is reshaping the field of physics by offering researchers more efficient ways to analyze data, simulate occurrences, and make scientific discoveries. Through machine learning and deep learning, physicists can now handle enormous datasets, both from labs and observations, much faster and with fewer errors than with conventional techniques. AI has touched various areas of physics like particle physics astrophysics quantum physics, and material sciences. Besides helping with particle recognition, it is also used for analyzing gravitational waves, looking for dark matter, and even designing new materials that exhibit extraordinary physical properties. This work firstly focuses on how AI can be leveraged in modern physics and at the same time identifies the key challenges and the possible directions that the AI-physics tandem could take in the future. It details how AI methods dramatically increase research productivity, make it possible to perform intricate simulations at a much faster pace, and help uncover even the subtle patterns and correlations in complex physical systems. The paper enlightened us about new tools being developed like Physics-Informed Neural Networks (PINNs) and generative AI models - these are hybrid approaches that integrate the fundamentals of physics and state-of-the-art computation techniques. As advantageous as AI is, it is not without shortcomings like the dependence on very good quality data, the difficulty in understanding how models make their decisions, the huge computational power they require, and the need to always comply with the laws of physics. Continuing to merge AI and physics could very well lead to a complete transformation of the way we do science, resulting in quicker discovery and deeper understanding of the universe at its core.
Sangi Bhanu Prasad, Kandela Ruchitha, Umme Habeeba et al.· International Research Journ...· 0 citations
Physics-informed neural networks (PINNs) have emerged as a powerful paradigm in scientific machine learning by embedding governing physical laws into neural network training through loss functions. They have demonstrated remarkable success in solving various forward and inverse problems governed by partial differential equations (PDEs). However, in practical applications, purely physics-constrained PINNs that rely solely on PDE residuals often suffer from slow or non-convergence and limited prediction accuracy, particularly when modeling high-order dynamical systems (e.g., second-order and above). Moreover, conventional PINNs struggle to effectively capture high-frequency components in complex physical fields, which further limits their generalization and representational capability.
To address these challenges, this study proposes a data-guided physics-informed neural network with Fourier feature enhancement. In the proposed framework, a small amount of high-fidelity measurement or simulation data is incorporated to guide the training process, providing explicit guidance that complement the physics-based constraints. Meanwhile, Fourier feature embeddings are introduced into the input layer of the network to enhance its ability to represent high-frequency variations and multi-scale solution structures. This synergistic integration of data guidance and Fourier-enhanced representations accelerates convergence, improves robustness, and enhances the accuracy of PDE solutions.
The effectiveness of the proposed PINN model is validated through numerical and simulation studies on Euler-Bernoulli beam vibration problems, which serve as representative examples of high-order mechanical systems. The results demonstrate that PINN achieves more accurate and stable full-field vibration reconstructions than conventional PINNs, particularly under conditions involving high-frequency modes. These findings highlight the potential of hybrid data-physics neural frameworks as an efficient and reliable approach for solving complex PDE-governed dynamical systems.
Hailong Liu, S. Hedayatrasa, Yunpeng Zhu et al.· e-Journal of Nondestructive...· 0 citations
Mechanistic simulation and machine learning are powerful but complementary tools: physics-based simulation is interpretable yet computationally expensive and blind to real-world context, whereas machine learning is fast but data-hungry and opaque. Biological systems resolve this tension elegantly, coupling physically grounded mechanoreceptor sensing with higher-level neural interpretation that places those signals in context. Inspired by this layered architecture, we present Mechanics-AI, an open-source framework that mirrors the same sensing-then-interpretation logic computationally. A first learning layer (ML1) emulates expensive finite-element, computational fluid dynamics and multiphysics simulations to produce interpretable physical metrics such as stress, strain, shear, and thermal and moisture fields, while a second layer (ML2) fuses these metrics with heterogeneous real-world metadata to predict categorical outcomes and design recommendations. Eight algorithms are benchmarked automatically, the most accurate is selected for each task, and Shapley additive explanations expose the dominant physical drivers to preserve interpretability. The framework is demonstrated across three independent domains using a single unchanged pipeline: forensic traumatic brain injury prediction, optimisation of a bio-inspired humanoid bioreactor for tissue engineering, and a zero-emission building (ZEBAI) framework that couples thermo-hygro-mechanical simulation with Sobol-sampled surrogate modelling to design sustainable, low-carbon envelopes from recycled aggregate concrete by balancing structural safety, energy and embodied carbon. Despite entirely different physics, data and objectives, the same architecture generalises across all three, showing that bio-inspired, layered coupling of mechanistic simulation and contextual learning offers a reusable, interpretable route to cross-domain engineering prediction and sustainable design.
Yuyang Wei, Weijie Fei, Jiarong Wang et al.· Biomimetics· 0 citations
Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance heavily relies on the manual, trial-and-error engineering of neural representations, loss formulations, and optimization dynamics. While Large Language Models (LLMs) offer a promising avenue for automated design, unconstrained code generation often yields mathematically invalid or numerically unstable solutions under strict scientific computing constraints. To bridge this gap, we propose \textbf{EvoPINN}, an agentic framework that reformulates PINN development from labor-intensive manual design into a rigorous, execution-grounded algorithm discovery problem. EvoPINN navigates a modular search space by decoupling neural representations from training programs, utilizing an LLM agent to iteratively propose memory-conditioned programmatic modifications. To ensure scientific validity, all candidates undergo strict structural verification and budget-matched PDE evaluation. Extensive experiments across diverse PDE regimes (oscillatory, elliptic, dissipative, and nonlinear transport) demonstrate that EvoPINN discovers PDE-specialized learning algorithms that significantly reduce relative $L_{2}$ error compared to baselines. Crucially, EvoPINN autonomously invented SLRC-PINN, a novel architecture whose performance gains persist under rigorous parameter-matched comparisons, establishing the viability of execution-grounded agents for discovering genuinely new scientific computing mechanisms.
Physics-informed machine learning incorporates physical principles --often expressed via differential operators-- into data-driven models. While physics-informed neural networks (PINNs) dominate empirical applications, the complexity of neural network architectures and optimization landscapes hinders the development of a corresponding learning theory. In turn, kernel methods offer an appealing alternative with closed-form solutions and analytical tractability, yet existing guarantees primarily cover the well-specified setting where the target belongs to the native Reproducing Kernel Hilbert Space (RKHS). This imposes unrealistic regularity assumptions that physical targets often fail to satisfy. In this paper, we introduce and analyze Physics-Informed Kernel methodS (PIKS). We establish the universal consistency of PIKS for linear differential constraints, proving that for universal kernels (such as Gaussian or Mat\'ern), the estimator asymptotically learns the target while satisfying physical constraints. We further derive finite-sample bounds under suitable source conditions. Our analysis is based on extending classical operator-theoretic analysis of kernel methods to physics-informed machine learning. Numerical experiments demonstrate that PIKS can be competitive with PINNs and traditional finite element methods.
Joachim Bona-Pellissier, Giacomo Meanti, Matteo Santacesaria et al.· 0 citations