Citation:

Susmit Sen, Kabita Paul, Sujit Murumkar, 2026. "AI in the Use of Nuclear Energy: Explainable Artificial Intelligence for Transparent, Safe, and Regulatory-Compliant Nuclear Operations", ESP Journal of Engineering & Technology Advancements  6(1): 124-130.

Abstract:

Nuclear energy is an important zero-carbon energy source as global energy needs increase. Artificial Intelligence (AI) is being used to manage the nuclear industry and optimize operations while maximizing safety. But deploying opaque “black-box” algorithms in safety-critical environments presents profound challenges. In this manuscript where we will discuss how Explainable Artificial Intelligence (XAI) aims to reconcile the powerful predictive capability of these models with a need for transparency, accountability and human alignment. We review XAI applications in fault detection, predictive maintenance, severe accident prediction, small modular reactor optimization, and nuclear nonproliferation. The outcomes demonstrate that combining XAI with digital twins and uncertainty-aware models meets the demanding regulatory requirements triggered by international agencies. All in all, XAI is the key to leaving human operators really inside the loop (Human-Centered AI-HCAI) and deploying next-gen intelligent systems by keeping their full potential safely.

References:

[1] A. Hall, P. Murray, R. L. Boring, and V. Agarwal, “Human-Centered and Explainable Artificial Intelligence in Nuclear Operations,” Proc. Human Factors Ergonomics Soc. Annu. Meeting, vol. 68, no. 1, pp. 1563–1568, 2024.

[2] Q. Huang et al., “A review of the application of artificial intelligence to nuclear reactors: Where we are and what’s next,” Heliyon, vol. 9, no. 3, p. e13883, 2023.

[3] International Atomic Energy Agency, “Enhancing Nuclear Power Production with Artificial Intelligence,” IAEA Bulletin, vol. 64, no. 3, Sep. 2023.

[4] A. Ayodeji, M. A. Amidu, S. A. Olatubosun, and Y. Addad, “Deep learning for safety assessment of nuclear power reactors: Reliability, explainability, and research opportunities,” Prog. Nucl. Energy, vol. 153, p. 104432, 2022.

[5] R. Machlev et al., “Explainable Artificial Intelligence (XAI) techniques for energy and power systems: Review, challenges and opportunities,” Energy AI, vol. 9, p. 100169, 2022.

[6] B. Shneiderman, “Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy,” Int. J. Hum.–Comput. Interact., vol. 36, no. 6, pp. 495–504, 2020.

[7] M. Najar and H. Wang, “From black box to glass box: Explainable AI for enhancing operator decision making in reactor accident scenarios,” Prog. Nucl. Energy, vol. 185, p. 105101, 2023.

[8] M. Najar and H. Wang, “Explainable AI models for enhancing operator reliability during reactor design-based accidents using radionuclide data,” Nucl. Technol., vol. 209, no. 4, pp. 512–528, 2023.

[9] Nuclear Regulatory Commission, “Regulatory Framework Gap Assessment for the Use of Artificial Intelligence in Nuclear Applications,” Oct. 2024.

[10] N. Ngoy Kubelwa, “Enhancing Nuclear Power Production with Artificial Intelligence,” IAEA Bulletin, Sep. 2023.

[11] N. R. Amaliah et al., “Human-in-the-Loop XAI for Predictive Maintenance,” Electronics, vol. 12, no. 8, p. 1891, 2023.

[12] C. O. Retzlaff et al., “Post-hoc vs ante-hoc explanations: xAI design guidelines,” Artif. Intell. Med., vol. 145, p. 102654, 2023.

[13] J. Liu et al., “Enhancing interpretability in neural networks for nuclear power plant fault diagnosis,” Prog. Nucl. Energy, vol. 174, p. 104856, 2024.

[14] F. Haseeb et al., “Uncertainty aware unsupervised fault diagnosis of PWR nuclear power plant using KNN and SHAP method,” Prog. Nucl. Energy, vol. 168, p. 105050, 2024.

[15] A. M. Salih et al., “A Perspective on Explainable Artificial Intelligence Methods,” Adv. Intell. Syst., vol. 5, no. 6, p. 2200326, 2023.

[16] B. Reddy et al., “Uncertainty-aware and Explainable Human Error Detection in Nuclear Power Plants,” National Laboratory (INL), INL/RPT-24-77890, 2024.

[17] B. Kotipalli, “The Role of Attention Mechanisms in Enhancing Transparency and Interpretability of Neural Network Models in Explainable AI,” Harrisburg University, 2024.

[18] C. Chen et al., “Combination of deep neural network with attention mechanism enhances the explainability of protein contact prediction,” Proteins, vol. 89, pp. 697–707, 2021.

[19] National Laboratory, “Nuclear energy becomes smarter and safer with AI,” National Laboratory News, Mar. 2024.

[20] National Laboratory, “Explainable Artificial Intelligence Technology for Predictive Maintenance,” INL/RPT-23-74159, Aug. 2023.

[21] Y. Fu et al., “An Interpretable Time Series Data Prediction Framework for Severe Accidents in Nuclear Power Plants,” Entropy, vol. 25, no. 8, p. 1160, 2023.

[22] I. P. A. S. et al., “Leveraging explainable AI for reliable prediction of nuclear power plant severe accident progression,” Reliab. Eng. Syst. Saf., vol. 241, p. 109682, 2024.

[23] D. B. Sholademi, “Emerging Technologies in Nuclear Non-Proliferation Verification,” Int. J. Res., vol. 11, no. 2, pp. 45–58, 2024.

[24] M. Adeoye, “AI-driven real-time diagnostics and self-correcting control schemes for next-generation nuclear energy systems,” Ann. Nucl. Energy, vol. 198, p. 110342, 2024.

[25] S. Sen, “Quantum Computing: Back to the Future,” Int. J. Emerg. Res. Eng. Technol. (IJERET), vol. 6, no. 4, pp. 218–221, Dec. 2025. [Online]. Available: https://ijeret.org/index.php/ijeret/article/view/519

[26] S. Sen, “Artificial Intelligence in Mining, Petroleum and Natural Gas Extraction Process Optimization,” Int. J. Emerg. Res. Eng. Technol. (IJERET), vol. 6, no. 1, pp. 121–125, Mar. 2025. [Online]. Available: https://ijeret.org/index.php/ijeret/article/view/518

[27] S. Sen, “AI-Enabled Substation Architectures for Autonomous Power Systems: Reliability, Asset Intelligence, and Grid-Edge Analytics,” Int. J. Comput. Trends Technol. (IJCTT), vol. 74, no. 2, pp. 11–15, 2026. doi: 10.14445/22312803/IJCTT-V74I2P103

Keywords:

Explainable AI, Fault Diagnosis, Human-Centered AI, Machine Learning, Nuclear Energy, Predictive Maintenance, Regulatory Compliance, Small Modular Reactors.