Next Article in Journal
Structural Monophyly Analysis Allows Estimation of Self-Sustainability at the Supraspecific Level over 88 Million Years in Mosses
Previous Article in Journal
Knowledge Alliances for Global Change Adaptation: A Relational Approach Based on Traditional Ecological Knowledge, Territorial Management, and Community Practices in the Chilean Context
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Review

Artificial Intelligence as Enabler for Adoption of Sustainable Nuclear-Powered Maritime Ships: Challenges and Opportunities

by
Miltiadis Alamaniotis
1,* and
Konstantinos Ipiotis
2
1
Department of Electrical and Computer Engineering, University of Texas at San Antonio, San Antonio, TX 78249, USA
2
SWECO UK Limited, Leeds LS7 4DN, UK
*
Author to whom correspondence should be addressed.
Sustainability 2025, 17(8), 3654; https://doi.org/10.3390/su17083654
Submission received: 1 March 2025 / Revised: 9 April 2025 / Accepted: 15 April 2025 / Published: 18 April 2025
(This article belongs to the Section Energy Sustainability)

Abstract

:
Decarbonization stands as one of humanity’s most pressing challenges, demanding collective efforts from multiple sectors to meet established goals. The transportation industry plays a pivotal role in this endeavor, with the maritime sector offering significant potential to reduce emissions. As a cornerstone of global goods and commodity transport, the maritime industry is uniquely positioned to contribute meaningfully to the global drive for lower carbon emissions. Artificial intelligence (AI), with its profound influence across diverse domains, is anticipated to play a vital role in supporting the nuclear shipping industry on its path to a decarbonized future. Specifically, AI provides tools to make nuclear power on ships a more economically viable solution while enhancing the safety and security of nuclear systems. This paper explores AI tools as an enabler for adopting nuclear-powered ships, delving into the challenges and opportunities associated with their implementation. Ultimately, it highlights AI’s role in fostering sustainable nuclear-powered maritime solutions, which align with and contribute to achieving global decarbonization goals.

1. Introduction

Nuclear power has been a subject of interest in transportation, particularly maritime ships, since the early days of the nuclear era. However, the high cost of operation eliminated the interest in developing nuclear-powered vessels for many decades [1]. This situation has recently changed due to global decarbonization goals and the advent of innovative reactor technologies such as small modular reactors [2]. As a result, research and development efforts are increasingly focused on leveraging nuclear power for commercial vessels to transport goods [3].
The concept of nuclear-powered commercial (i.e., for propulsion and onboard energy supply) vessels is not new. The first commercial ship equipped with a nuclear reactor was launched in the 1960s, with a few others following in subsequent years [1]. However, for various reasons—primarily financial—these nuclear-powered commercial ships were decommissioned early, and this type of vessel did not gain the market traction initially anticipated. Despite their limited operational lifespan, these ships provided valuable lessons that remain relevant today [4]. Recently, interest in nuclear-powered ships has been rekindled, driven by global decarbonization goals [5]. As a result, the operational insights from those early vessels are once again in the spotlight and may shape the future development of nuclear maritime technology.
In the time between the decommissioning of the first maritime nuclear ships and the present day, advancements in computing have been extraordinary. The world has embraced digitalization, with digital technologies becoming pervasive and an integral part of daily life [6]. Moreover, artificial intelligence has made significant strides, offering a wide range of capabilities for developing automated and autonomous systems. These systems have become ubiquitous in our everyday lives, enhancing safety and security while facilitating unrestricted access to numerous services and processes [7].
Given the widespread adoption of AI, it is anticipated that nuclear-powered ships will also benefit significantly from its applications. Intelligent systems are expected to provide advanced instrumentation for surveillance, monitoring, and decision-making to address the operational needs of these vessels [8]. AI is projected to reduce overall operational costs while enhancing both the safety of the ships and the security of the nuclear materials on board [9]. Notably, such technologies were unavailable during the operation of the first nuclear-powered ships [1]. Their integration now promises to deliver substantial advancements, paving the way for more efficient and secure nuclear maritime operations [4].
AI has long been employed in the nuclear industry at various levels, primarily to enhance operational efficiency and minimize the risk of human error. One of the earliest applications of AI in this field was the development of expert systems, which captured expert knowledge in the form of IF/THEN rules to support decision-making in operation, maintenance, and engineering within nuclear power plants [10]. More specifically, AI has been successfully applied to system monitoring, prognostics, and diagnostics through data-driven approaches [11]. It has also been instrumental in developing intelligent human–machine interfaces, digital twins for nuclear power plant systems, and control and instrumentation systems for nuclear plant components [12,13]. Furthermore, AI-powered safety systems have been designed for forecasting power and heat profiles, identifying two-phase flow regimes, and analyzing thermal behavior [14]. In recent years, AI has played a critical role in cybersecurity within nuclear facilities, particularly in identifying and securing critical digital assets [15]. Additionally, AI has been leveraged for advanced data analytics in radiation spectroscopy, contributing to nuclear nonproliferation [16], radiation protection and shielding [17], and radiation applications in healthcare [18,19].
In addition to its transformative impact on the nuclear industry, artificial intelligence (AI) has also been recognized as a key driver in the digitization of maritime transportation, leading to significant improvements in operational efficiency. Intelligent tools have already been developed and applied across various domains of maritime vessel operations [20]. One critical area where AI has proven valuable is the predictive maintenance of systems and components [21]. Fault detection [22], prognostics, and health management [23] are among the most prominent applications, enabling the early identification of issues and reducing downtime. AI has also revolutionized ship routing, particularly in complex environments such as maneuvering in small and congested ports [24] and optimizing navigation routes [25]. In addition, intelligent methods have enhanced the efficiency of maritime operations through accurate predictions of operational parameters [26], localized weather conditions [27], vessel sailing times [28], and emissions related to fuel consumption [29]. Other notable applications of AI in the maritime sector include enhancing situational awareness [30], enabling autonomous control for collision avoidance [31], and improving cybersecurity in vessel communication systems [32,33].
This paper aims to review nuclear-powered ships, examine the challenges associated with adopting nuclear technology in the commercial maritime sector, and explore the potential opportunities in synergism with artificial intelligence it presents. The methodology we followed is based on existing AI applications in both land-based nuclear energy systems and conventionally powered maritime vessels, using these as a foundation to identify key areas where AI can enable more efficient operation in nuclear-powered maritime vessels. Nuclear-powered ships present a significant opportunity to achieve decarbonization goals by 2050 [34]. This paper examines how AI tools can support these objectives by enhancing the efficient application of nuclear technology in maritime vessels. By addressing key challenges and alleviating concerns surrounding nuclear propulsion, AI could serve as a critical enabler for the adoption of nuclear-powered ships while securing the sustainability of international transportation and trade [35,36].
The current lack of operational experience at the intersection of AI and nuclear maritime systems is also evident in the literature: although AI has been increasingly applied in maritime contexts, there is a noticeable scarcity of studies focused on nuclear-powered ships. This paper seeks to fill that gap by exploring how AI can act as an enabler for the adoption and optimization of nuclear maritime systems.
The roadmap for this paper is as follows: Section 2 presents a brief history of nuclear-powered maritime vessels. Section 3 explores the application of artificial intelligence technologies in supporting the operation of nuclear maritime ships, while it examines future challenges and opportunities in the field. Finally, Section 4 concludes this paper by summarizing its key points.

2. Nuclear-Powered Maritime Ships

The first nuclear-powered ship, the Savannah, was commissioned in 1962 and decommissioned ten years later. It was primarily built as a research vessel—a laboratory for studying the design, operation, and maintenance of nuclear-powered ships—rather than for commercial profit. Its propulsion system was approximately twice as fast as that of a conventional ship, delivering a shaft-line power of 16 MW. The vessel was a mixed cargo/passenger ship, with a cargo capacity of 10,000 tons and accommodations for up to 60 passengers. The reactor was a light-water type, using low-enrichment uranium fuel (approximately 4.4% enrichment). Additionally, the ship featured dedicated onboard facilities for storing nuclear waste for at least 100 days [1]. The Savannah was ultimately decommissioned in 1971 due to financial infeasibility: it incurred costs of USD 90 million while generating only USD 12 million in revenue [37].
The second ship was the Otto Hahn, manufactured and operated by Germany. It was commissioned in the mid-1960s, featuring a pressurized water reactor (PWR) as its propulsion system. The ship’s operation as a nuclear-powered vessel ceased in 1979, when its owner converted it into a conventional ship. Before the conversion, the Otto Hahn had traveled 650,000 nautical miles around the world and had used two reactor cores. The ship’s high operational costs, coupled with regulatory challenges—such as many ports refusing to allow it to dock due to nuclear risks—ultimately led to its decommissioning.
The third nuclear-powered ship was the Mutsu, which was manufactured by two different Japanese vendors. Mitsubishi (Tokai, Japan) provided the core, while the hull was designed by Ishikawajima-Harima Heavy Industries Co., Ltd. (Tokyo, Japan). The ship utilized low-enriched uranium fuel (with an enrichment level of 3.24%) and was of the light-water reactor type. The Mutsu was tested in 1974 in the open sea, far from Japan’s shores, due to protests from anti-nuclear activists. During its first test, the ship experienced neutron leakage. Several repairs were made to ensure the ship’s radiation safety, which delayed its commissioning until 1991. A year later, in 1992, the ship was decommissioned [1]. Overall, the story of the Mutsu underscores management and financial errors, as two different companies were involved in its design, leading to interface complications.
The development of the Soviet-designed nuclear-powered icebreaker Lenin was primarily motivated by the desire to traverse Arctic routes [1]. It began operations in 1959, featuring a 90 MWth reactor core. This design was later upgraded to a 171 MWth core, which was installed in new icebreakers of the Sevmorput class, operational since 1988. The Sevmorput experienced several periods of service, although its entry into several Soviet ports was denied due to fears following the Chernobyl accident. Nuclear icebreakers continue to be used today for transporting cargo and passengers in Russia’s northern regions across the Arctic.
The historical use of nuclear power in maritime vessels demonstrates that their primary weakness lies in financial viability. In other words, the costs associated with technical and human support often exceed the revenue they generate. Naturally, the key challenge in adopting nuclear-powered maritime vessels is how to address this financial deficiency. Other challenges, such as technical and nonproliferation concerns, can be mitigated through engineering solutions, as evidenced by the successful deployment of nuclear submarines and icebreakers. However, AI has the potential to enhance the financial efficiency of these vessels by enabling optimal and more efficient operation. For instance, AI could reduce the need for highly paid onboard nuclear engineers—a major point of contention among crew members (and engineers) in the cases discussed in the previous section [1].
Beyond financial deficiency—an inherent challenge of nuclear maritime vessels—there are additional unique challenges. First, the limited space on board imposes spatial and physical constraints on the deployment of nuclear systems within the vessels. Second, since maritime vessels operate across multiple jurisdictions, they must comply with a variety of national nuclear regulations. To address this, a unified regulatory framework—potentially under the IAEA—needs to be established and universally accepted. Finally, nuclear-powered ships function as mobile reactors, making the tracking and accountability of nuclear fuel a distinct challenge compared to other onboard energy systems. Ensuring the proper monitoring and security of these vessels is therefore crucial.

3. Artificial Intelligence as Enabler for Adoption of Nuclear Maritime Ships

Advances in computing and artificial intelligence emerged during a period when nuclear-powered maritime vessels, aside from Arctic icebreakers, were virtually nonexistent, as stated earlier. Consequently, the application of AI in nuclear maritime ships remains largely unexplored. However, this limited precedent also presents an opportunity to integrate AI into the field. The success of AI in related domains [38], such as civilian nuclear power [39], highlights its potential to enable the adoption of nuclear-powered ships by enhancing their operational efficiency and diminishing cost.
This section identifies the areas in maritime vessels where AI can be utilized while exploring future opportunities for AI in each of the areas. Given the scarcity of current solutions, the focus shifts toward future possibilities driven by advancements in related fields. Notably, nuclear power and AI are distinct domains, but their integration within the maritime industry could significantly contribute to the broader adoption of nuclear-powered ships.
AI has the potential to offer a wide range of solutions for nuclear-powered maritime vessels within the context of the aforementioned unique challenges, significantly impacting environmental sustainability. Specifically, it can help reduce operational costs and minimize the environmental footprint by optimizing the cost-efficient use of various onboard processes. In practice, AI and nuclear power have yet to coexist on ships, resulting in limited practical experience and a highly premature stage of research. Therefore, this paper explores solutions informed by experience from other domains and how they are envisioned to optimize nuclear power utilization. Table 1 provides a summary of the areas where AI may provide significant solutions.
It should be noted that implicitly, the use of AI in the areas provided in Table 1 is related either directly or indirectly to the overcoming of economic, regulatory, and public acceptance barriers. For instance, the monitoring of reactor systems and the transmission of data via satellites to regulatory agencies satisfy regulatory requirements. Another example is the use of AI in radiation protection which enhances the public acceptance of the peaceful use of nuclear power in maritime vessels.

3.1. Monitoring and Maintenance

One of the primary applications of AI is in the development of instrumentation for monitoring nuclear power systems [40]. In general, monitoring instrumentation technologies involve deploying multiple sensors, acquiring and storing data, and analyzing them to assess the state of nuclear systems [41]. From a data analytics perspective, monitoring aims to identify behavioral patterns associated with the system’s normal and safe operation [42].
The identification of behavioral patterns is crucial for developing intelligent monitoring systems. The primary objective of these systems is to process incoming data and determine the system’s current state, enabling short-term predictions of its behavior [43]. Such predictive capability is essential for carrying out maintenance procedures in nuclear systems and is known as “predictive maintenance” [44]. Ensuring the safe operation of a nuclear-powered ship is even more critical, given that these vessels spend most of their lifespan at sea. Consequently, the opportunities for maintenance are strictly limited, and the number of ports equipped to handle nuclear maintenance is expected to be very small.
Therefore, AI will play a significant role in predictive maintenance, a concept that has already been successfully implemented in nuclear power plants and other critical industries [45,46]. Figure 1 provides an overview of predictive maintenance and highlights its main challenge compared to land-based nuclear reactor systems. Unlike other industrial applications, predictive maintenance in large-scale maritime vessels faces unique constraints due to their low operational flexibility. This limitation arises from the nature of the maritime industry: the long voyages these vessels undertake may coincide with the optimal maintenance window identified by predictive maintenance systems. Consequently, decisions must be made regarding whether maintenance should be performed before or after a voyage, carefully weighing the trade and financial implications of each choice.
Beyond maintenance, monitoring also plays a crucial role in the overall health management of nuclear systems [47]. AI can contribute significantly to developing critical systems for managing the health of nuclear-powered ships. Specifically, AI can be leveraged to build prognostic, fault detection, and diagnostic systems [48].
Prognostics refers to tools used to estimate the remaining useful life (RUL) of a component. It is a key aspect of predictive maintenance, enabling maintenance or component replacement to be scheduled just before failure occurs. This approach reduces maintenance costs by minimizing the need for multiple maintenance intervals and maximizing the component’s operational lifespan [49]. Likewise, fault detection systems are designed to identify faults, whether in the form of abnormal operation or complete failure, and trace their origin. Complementary to fault detection, diagnostic systems determine the type of fault and pinpoint its exact location [50].
In sum, AI offers several solutions for implementing the aforementioned processes. In particular, machine learning (ML) models can be trained on historical or simulated data to identify behavioral patterns [51], which can then be used to predict the remaining useful life (RUL) of components or detect deviations from normal operational behavior, such as fault patterns [52].
However, for nuclear systems with limited operational experience and associated datasets, an alternative approach is the adoption of rule-based AI solutions for prognostics and diagnostics [53]. Rule-based systems rely on IF/THEN rules that encode the knowledge and expertise of highly experienced professionals [53]. Given the scarcity of data on nuclear maritime vessels, developing rule-based AI monitoring systems with input from nuclear submarine experts presents a promising solution for ensuring the effective and safe operation of nuclear ships [53]. In addition, explainable AI systems may also be developed that not only perform the task of prognosis or diagnosis but also explain the reasoning behind their output [54], thus enhancing the trust towards AI systems.

3.2. Core Refueling Optimization

One of the key advantages of nuclear-powered ships is their long operational period before requiring refueling. This timescale is measured in decades, and ideally, a vessel may need only one—or even no—refueling throughout its lifetime. However, for the rare occasions when refueling is necessary, AI can offer solutions to optimize scheduling, thereby reducing both downtime and associated costs.
Nuclear-powered maritime ships will need to dock at specialized ports equipped with dedicated refueling facilities. Given the high investment costs required to modify existing ports or construct new nuclear docks—including the expenses for necessary security measures—many host countries may only be able to afford a single refueling dock. As a result, these facilities may be located far from a vessel’s regular routes, requiring additional travel time. Furthermore, the strict schedules of maritime vessels—many of which will play a crucial role in sustaining global trade and supply chains—necessitate that refueling is conducted as efficiently as possible. Optimizing refueling operations not only minimizes docking time but also enhances nonproliferation safeguards.
To that end, AI provides a comprehensive set of tools to ensure the fast and secure refueling of nuclear ships. The existing literature on conventional nuclear power plants has explored intelligent methods for determining optimal refueling patterns. Specifically, a variety of AI-based techniques have been proposed, including commonly used methods such as neural networks, fuzzy logic systems, and rule-based systems [55]. Additionally, advanced optimization techniques have been explored, such as Tabu search, simulated annealing, and particle-based optimization methods, including genetic algorithms, particle swarm optimization, ant colony optimization [56], gravitational search algorithms, and harmony search algorithms [57,58].
The plethora of algorithms and their demonstrated efficiency—particularly that of particle-based optimization methods—suggest that these approaches can also serve as effective solutions for optimizing the refueling of nuclear maritime ships. Notably, these intelligent algorithms must account for the physical space constraints imposed by docking facilities and the challenges of the aqueous environment.

3.3. On-Ship Nuclear Integrated Energy Systems Management

Efficient onboard energy management is a key factor in extending the utilization of nuclear fuel. Compared to conventional large-scale reactors, small modular reactors (SMRs) offer greater operational flexibility [59]. Since SMRs will serve as the primary energy source for nuclear-powered vessels, they present opportunities for enhanced energy management on board.
The core idea is to treat the ship as a nuclear integrated energy system (NIES), where the SMR interacts with other energy sources, storage devices, and industrial processes such as desalination [60,61]. The effective management of such an integrated system is essential to optimizing energy generation and consumption [62], ultimately ensuring prolonged nuclear fuel burnout [63].
Given the complexity of integrated energy systems arising from the interplay between various energy sources and consumption entities, artificial intelligence (AI) can provide effective solutions for optimizing energy management [63]. In such a system, the primary objective is to maximize the utilization of nuclear fuel and extend its burnout period.
The use of AI in managing integrated energy systems is not a new concept. Studies have shown that AI can overcome operational challenges arising from the integration of diverse system components [64]. This challenge becomes even more significant when considering that the propulsion system must also be part of the integrated energy system—an aspect not typically accounted for in a conventional NIES (as shown in Figure 2).
Advanced AI solutions can operate autonomously, efficiently optimizing energy distribution to meet the ship’s objectives. Notably, the integration of renewable energy sources with flexible SMRs has proven to enhance efficiency [65,66], particularly for large commercial maritime vessels that travel long distances across oceans and are exposed to varying environmental conditions, such as extended periods of sunlight or strong winds [67]. Additionally, long-haul voyages subject ships to diverse travel conditions, leading to fluctuating energy demands and shifting onboard priorities. In such cases, AI can dynamically adjust the energy system’s operation in real time to align with the vessel’s needs while maintaining overall efficiency. Notably, improving onboard energy efficiency can significantly reduce operational costs. These savings can be further enhanced by implementing industrial processes such as water desalination [68], which minimizes the need for port stops to replenish water supplies, ultimately making voyages more cost-effective.

3.4. Digital Twins for Nuclear-Powered Maritime Vessel Operations

Digital twins (DTs) represent a transformative technology with significant implications for the nuclear sector, particularly in the context of small modular reactors (SMRs) and associated vessels. The creation of a digital twin of a vessel enables stakeholders and nuclear regulatory agencies to leverage real-time data and advanced analytics throughout the entire lifecycle of the asset, from design and construction to operation and decommissioning [69,70].
One of the primary benefits of utilizing digital twins in this context is their potential to enhance sustainability. By providing comprehensive insights into the operational performance and condition of the vessel, digital twins facilitate more efficient resource utilization and minimize waste. This is particularly relevant in the nuclear sector, where the management of radioactive materials and the safety of operations are paramount [71]. The ability to monitor, simulate, analyze, and test various scenarios allows for proactive maintenance and operational adjustments, ultimately leading to improved reliability and reduced environmental impact.
Additionally, digital twins contribute to the transition to green energy by optimizing the performance of small modular reactors. Through continuous monitoring and data analysis, digital twins can identify inefficiencies and opportunities for improvement, supporting the development of more sustainable nuclear energy solutions. Furthermore, the insights gained from digital twins can inform the design of future reactors, ensuring that they are built with sustainability in mind from the outset [72].
Furthermore, digital twins have been introduced to assist in the ship’s asset management, ensuring decision-making is effective, safe, and secure throughout the lifecycle of the subject. The digital representation of a physical asset provides the ability to conduct simulations and tests and monitor assets, reducing risks, eliminating waste, and increasing value. Notably, digital twins equipped with mechanistic models of fuel and materials, implemented using AI tools—such as deep neural network models or rule-based expert systems—can accurately predict reactor states even in high-radiation and harsh environments, including accident scenarios. This will be a significant enhancement in the vessels’ overall resilient operation.
Beyond vessels, the application of digital twins can extend to ports and other facilities associated with the nuclear sector. By creating digital representations of these assets, stakeholders can enhance operational efficiency, improve safety protocols, and reduce environmental impacts. The integration of digital twins across the entire supply chain can lead to a more cohesive and sustainable approach to asset management.
However, while the benefits of digital twins are substantial, there are also challenges and limitations to consider. The implementation of digital twins requires significant investment in technology and infrastructure, as well as ongoing commitment to data management and cybersecurity. Additionally, the complexity of modeling certain aspects of nuclear operations may pose technical challenges that need to be addressed [73].
In sum, the utilization of digital twins in the nuclear sector offers numerous advantages related to sustainability and the transition to green energy. By monitoring, simulating, analyzing, and testing throughout the lifecycle of vessels and other assets, digital twins can enhance operational performance and support the development of more sustainable practices. As the nuclear sector continues to evolve, the strategic application of digital twins will be critical in addressing the challenges and opportunities that lie ahead.
Of particular interest is the integration of digital twins with artificial intelligence, which will pave the way for developing advanced algorithms and methodologies for the operation of nuclear-powered ships. Digital twins can serve as a testbed for refining predictive maintenance algorithms, enhancing their effectiveness and reliability, as discussed in Section 3.1.
One of the key advancements AI can bring to digital twins is the development of autonomous training systems for nuclear reactor operators. Nuclear-powered ships must recruit and retain onboard nuclear reactor operators and engineers who require continuous, high-frequency training to maintain situational awareness and sharpen their skills. However, training poses a significant challenge due to the physical constraints of nuclear ships, which operate in aquatic environments and may remain at sea for months without docking.
Digital twins, enhanced with advanced AI algorithms, offer a solution by enabling onboard intelligent training simulators. This training can be further improved through the adoption of explainable AI (XAI) methods, which not only provide an interactive training interface but also generate detailed assessment reports on trainee performance. Moreover, XAI systems can offer comprehensive explanations of the nuclear system’s behavior in response to trainee actions, helping operators understand the consequences of their inputs. These explanations, derived from digital twins equipped with precise system models, historical and simulated data, and machine learning methods, enhance learning and operational readiness, as illustrated in Figure 3.
Notably, training systems like the one shown in Figure 3 offer several advantages, including modularity, as they are implemented through software modules, making upgrades seamless. Additionally, when new systems are installed on board, the corresponding software modules can be integrated into the digital twin core, ensuring continuous adaptability [74]. Another advantage of digital twin training is that it can be provided remotely before the human operator joins the ship in relevant facilities and conducts operations beforehand through a combination of digital twin and virtual reality technologies.
Furthermore, the use of explainable AI (XAI) eliminates the need for a human instructor, as trainees receive real-time feedback and detailed explanations when incorrect actions are taken [75]. Lastly, XAI systems can continuously learn from their interactions with trainees, enabling them to refine and personalize training sessions without requiring human input [76].

3.5. Radiation Protection

Extensive exposure to radiation generated during nuclear reactor operation necessitates strict measures to ensure the safety of operators and workers. To that end, rigorous protocols have been established to accomplish the following: (i) minimize the risk of accidents that could lead to radiation release and (ii) reduce the likelihood of accidental human exposure. Notably, in the event of an accident, it is crucial to initiate mitigation activities as quickly as possible, ensuring that all actions align with established protocols and designated procedures [77].
The nuclear maritime industry faces the same radiation protection challenges while also considering safety measures both during travel and while docked at a port. Additionally, the maritime sector commonly employs personnel on short-term contracts, leading to frequent staff turnover. As a result, crew members may not have sufficient time to fully absorb and internalize radiation protection procedures.
AI can offer effective solutions for enhancing radiation protection and ensuring human safety. A key application of AI is in the design of optimal physical protection systems, which improve safety while keeping costs low [78]. Unlike land-based reactors, maritime reactors are confined to limited spaces within vessels. As a result, the need for optimized protection systems is further emphasized by spatial constraints.
AI-powered Large Language Models (LLMs) have been widely applied to support decision-making across various domains. Similarly, nuclear maritime vessels can leverage LLMs to efficiently train newly hired personnel while maintaining their situational awareness through personalized training programs.
Additionally, in emergency situations, onboard personnel without nuclear-specific training can use LLMs to quickly identify the necessary procedures to follow [79]. For example, in the event of an accident, a user could query the LLM for appropriate actions based on their current location—since crew members may be in different areas—to minimize radiation exposure. Notably, AI systems remain unaffected by high-stress situations, ensuring they provide clear and accurate guidance to individuals experiencing panic.
Furthermore, LLMs can play a crucial role in maintaining knowledge related to radiation protection aboard a ship. Protection procedures and safety guidelines are documented in extensive physical and digital records, making it time-consuming to retrieve specific information when needed [80]. Additionally, critical details may be dispersed across multiple pages or documents, making their identification and synthesis into a coherent summary challenging. LLM tools can efficiently search, extract, and summarize relevant information into a single, concise text. By doing so, AI helps preserve institutional knowledge, ensuring that valuable information remains accessible and does not get lost or buried within vast volumes of documentation.

3.6. Safeguards and Security of Nuclear Materials

One of the primary concerns in the nuclear industry and mainly of nuclear regulatory commissions and safeguard agencies is ensuring the secure movement, storage, and use of nuclear materials. Specifically, it is crucial to maintain precise knowledge of the location, usage, and quantity of nuclear material—a practice known as material accountability. To achieve this, the whereabouts of nuclear materials must be continuously monitored using advanced tracking and surveillance technologies, a term known as nuclear security [81].
In this context, AI can offer efficient solutions through automated and autonomous systems that enhance material accountability. Specifically, AI enables the development of advanced data analytic methods for analyzing gamma measurements and spectra [82]. It can also be employed to ensure the integrity of onboard nuclear materials by verifying and validating activities associated with their handling. Moreover, intelligent algorithms can detect the illicit movement of radioactive materials, as well as identify and characterize the material when suspicious activity is detected [83]. Figure 4 illustrates the security architecture that AI can facilitate for onboard nuclear material monitoring.
As shown in Figure 4, monitoring activities in a nuclear vessel are primarily focused on two key areas: the reactor core and the vessel’s entry/exit point. The AI system is centralized in a control room, where measurements are transmitted via communication links. This network of detectors functions as a sensor system, continuously collecting radiation data and transmitting them to a central computer for storage and analysis [83].
Given the large volume of collected data, fast and accurate analysis is essential. AI plays a crucial role in performing various data analytic tasks, including data fusion, pattern recognition, inference making, data correlation, and parameter estimation. These processes collectively contribute to verifying scheduled activities and detecting any illicit ones.
Furthermore, AI modules installed on nuclear ships can also function as a virtual agent for the International Atomic Energy Agency (IAEA). Specifically, LLMs with full access to the ship’s digital records can generate summaries of activities upon request. These LLM modules can operate autonomously, directly connecting to the IAEA via satellite communication to transmit the required reports. Since nuclear ships will primarily operate internationally, they are expected to remain under IAEA oversight in addition to national regulatory authorities [84]. The integration of AI-driven reporting systems can enhance transparency, streamline compliance, and facilitate the real-time monitoring of nuclear activities on board.
Overall, the use of AI for nuclear material monitoring will strengthen the trust of the IAEA and the international community in the countries where nuclear ships are docked. Countries lacking this technology may attempt to illicitly remove nuclear material from ships for unauthorized use, making robust AI-driven monitoring systems even more critical. Additionally, LLMs that communicate directly with the IAEA can significantly reduce the agency’s operational costs by minimizing the need for frequent on-site inspections, thereby lowering travel expenses for human agents.

3.7. Cybersecurity

Modern ships are fully equipped with digital systems to enhance operational efficiency. However, as in other domains, the digitization of ships also introduces vulnerabilities to cyberattacks [85]. While satellite connectivity provides essential access to the internet and facilitates communication, it also serves as a potential entry point for cyber threats [86].
Furthermore, the use of wireless technologies for data exchange and monitoring on board introduces additional vulnerabilities, as they may attract cybercriminals seeking to compromise nuclear control and monitoring systems for nefarious purposes [87]. Since wireless and digital connections are essential for reducing operational costs and cannot be replaced with analog alternatives, implementing robust cybersecurity measures is imperative [88].
A wide range of cybersecurity solutions has been proposed and tested across various domains. As a well-researched topic, AI-driven cybersecurity solutions can be adapted and tailored to meet the specific needs of nuclear ships. Of particular interest are AI technologies capable of detecting cyberattacks in real-time and performing rapid cyber-forensic analysis [89]. Additionally, intelligent decision-making systems can provide mitigation plans to recover from attacks when detected [90], while LLMs can assist human operators in identifying and following the correct set of security protocols [91].
At this point, it is important to note that before deploying any cybersecurity measures, the ship’s critical digital assets (CDAs) must first be identified [92]. Since there is no prior experience with fully digital nuclear maritime operations, AI foundation models can be trained on data from related fields—such as civilian nuclear power plants and nuclear submarines—to generate a comprehensive list of CDAs tailored to the specific nuclear ship in question, as shown in Figure 5.

3.8. Nuclear Contamination Management

Operational experience from nuclear power plants has shown that both large- and small-scale accidents—or even illegal activities—can result in nuclear contamination, which can gradually spread over time. In the harsh and dynamic environment of the ocean or sea, containment becomes even more challenging, as contamination can disperse rapidly with currents, making mitigation efforts significantly more difficult [93].
Nuclear contamination in aqueous environments is a topic of interest but is only indirectly related to nuclear maritime vessels. Contamination would occur only in the event of an onboard nuclear system accident that leads to the release of nuclear material into the water [94]. In such cases, AI solutions can play a crucial role in managing nuclear contamination by conducting the following:
(i)
Predicting the dispersion of radioactive material in the water;
(ii)
Controlling unmanned aerial vehicles (UAVs) and autonomous underwater vehicles (AUVs) to monitor radiation levels;
(iii)
Operating autonomous vehicles for decontamination efforts in affected ocean areas.
Driven by these cases, maritime nuclear ships should be equipped with a fleet of autonomous vehicles and robots designed to activate when contamination is detected. AI algorithms will enable these systems to operate independently, executing their designated tasks with precision, whether for monitoring radiation levels, containing the spread, or conducting decontamination efforts.

3.9. Onboard Digital Panel Operation

Instrumentation and control systems in the control room provide ship personnel with a comprehensive understanding of the vessel’s current state, enabling them to take appropriate actions. Traditionally, these systems were analog, requiring operators to interact with physical knobs, buttons, and hardware displays. However, a major drawback of analog systems is their space requirements, as every instrument—including those rarely used—occupies physical space on the control panel [95].
The advent of digital systems has transformed this landscape by replacing hardware-based instrumentation with software-driven interfaces. In this setup, instruments and controls are presented as software modules on a glass-based panel, significantly reducing the space required compared to traditional analog control panels [96].
Notably, the vast array of virtual instruments and controls, along with the large volume of sensor data displayed on the panel, makes these interfaces complex and challenging to operate. Such interfaces often incorporate dropdown menus where multiple instruments and measurements are grouped together. Due to limited screen space, operators can display only a select number of instruments at a time, while the rest remain in the background. It is important to highlight that digital panels on nuclear ships will become even more complex, as they must manage a high number of instruments dedicated solely to monitoring nuclear systems [97,98].
AI can offer solutions to enhance the user-friendliness of digital panels. AI algorithms can dynamically adjust the interface layout, ensuring that the most critical information is displayed at any given moment. For instance, AI can assess the ship’s current state and prioritize the information presented to the operator accordingly. Additionally, AI systems can personalize the interface by learning from the operator’s behavioral patterns, such as gestures, reaction speed, and other physical characteristics, to optimize usability and efficiency [99].
Additionally, AI tools can support human operators and mitigate errors related to human factors. Intelligent systems powered by explainable AI can run in the background, continuously assessing the operator’s actions. If a discrepancy is detected between the operator’s actions and the AI’s assessment of the optimal course of action, the system can issue an alert and provide an explanation for the discrepancy [100]. This approach helps operators recognize potential mistakes caused by mistyping, rushed decisions, or confusion due to the complexity of the digital panel interface, ultimately enhancing operational safety and efficiency (and implicitly reducing human error rate).
The use of LLMs can also greatly benefit operators by streamlining access to critical information. The vast number of protocols and extensive documentation generated by nuclear systems often results in valuable insights being buried within lengthy reports and datasets. LLMs can assist operators by quickly retrieving relevant information in response to a prompt, ensuring that crucial details are not overlooked. Additionally, when an operator requires a synthesis or summary of information dispersed across multiple documents, LLMs can efficiently compile and present the necessary data in a clear and comprehensible manner, enhancing decision-making and operational efficiency.

3.10. Electricity Supply at Ports

Onboard nuclear reactors can also serve as a power source for port facilities while docked. This not only generates revenue for the ship owner but also supports decarbonization efforts. By connecting to port infrastructure, the nuclear ship can supply a steady and reliable energy flow directly from its reactor [101].
Notably, even when docked, the ship still requires energy for critical onboard loads, such as refrigeration, lighting, and other essential systems, necessitating a constant power supply [102]. Therefore, balancing the ship’s own energy needs with the electricity supplied to the port requires the intelligent management of nuclear power generation to maximize efficiency. SMRs, expected to be installed on nuclear maritime ships, offer flexible operation, allowing their output to be adjusted in response to demand fluctuations. It is crucial to ensure that generation and consumption are properly aligned to prevent energy waste.
AI systems have been successfully proposed and tested for managing power and energy systems. Tailored algorithms can optimize energy generation and consumption, ensuring efficiency [103]. Similarly, AI can regulate the output of SMRs, dynamically adjusting power production to match both the ship’s and the port’s energy demands. AI becomes even more valuable when the port incorporates renewable energy sources, as it can coordinate all available generation resources to minimize energy waste and enhance overall efficiency.
Additionally, intelligent algorithms can be employed to forecast energy demand in advance [104]. Accurate forecasting is crucial for developing an effective management strategy, as it enables the pre-scheduling of SMR-based electricity supply. By integrating AI-driven forecasting with intelligent management algorithms, energy supply to ports can be optimized, ensuring efficiency and reliability. The use of AI as an enabler for utilizing nuclear ships as electricity suppliers to the port where they are docked is illustrated in Figure 6. From a wider point of view, AI is an enabler that further assists the creation of the so-called Positive Energy in collaboration with the district’s and the vessel’s digital twins for optimization and decision support systems.

3.11. Secure Informative Navigation Systems

The presence of a nuclear reactor on board a ship makes it a potential target for various groups, such as maritime pirates, who may attempt to capture the vessel for its nuclear materials or onboard technologies. These groups are often concentrated in specific regions, posing significant risks of hijacking or trespassing from certain areas [105]. One possible solution is to restrict nuclear ships to routes considered safe, but this severely limits their operational flexibility and marketability. Consequently, unrestricted travel is often the only viable option for such vessels. or the vessel can contain armor and become a hybrid war/commercial ship, subject to appropriate training and equipment.
In the case of hybrid war/commercial ships AI can play a crucial role recognizing threats and eliminating them, having the captain as the final decision-maker. In addition, it may provide very short-term navigation driven actions in the form of battle maneuvers, which can be implemented via the methods of reinforcement learning.
AI can enhance navigation systems by incorporating security considerations alongside other navigational factors. These intelligent systems would assess the risks of potential attacks from groups such as paramilitary or terrorist organizations before determining or adjusting a ship’s route [106]. By integrating real-time security information, the system can reroute the vessel as new threats or risks are detected [107]. As a result, nuclear ships could drive the development of a new class of secure, information-driven navigation systems [108], specifically tailored to meet the unique security needs of these vessels [109,110,111,112].

4. Conclusions

Even though the vast majority of currently operating reactors are naval, the use of nuclear reactors in maritime vessels has been extremely limited. However, decarbonization goals have prompted the maritime industry to explore alternative energy sources that can be used to reduce greenhouse gas emissions. Among these alternatives is the revitalization of nuclear ships, where the reactor is used for both propulsion and electricity supply.
The history of maritime nuclear vessels reveals that most efforts were abandoned, primarily due to high operational costs. Notably, nuclear maritime ships were developed during eras when artificial intelligence was still in its early stages, and as a result, AI was not utilized in these vessels at the time.
This paper explored the role of AI as an enabler for achieving sustainable nuclear ships, discussing both the challenges and opportunities associated with its use. Notably, nine distinct areas were identified where AI could provide solutions to enhance operational efficiency and, consequently, reduce operational costs. These areas were selected based on the successful application of AI in civilian nuclear power plants and its proven effectiveness in those settings [113,114].
By reviewing the list of areas and the AI solutions discussed in this paper, one key point stands out. The recent advancements in AI, particularly in the form of Large Language Models (LLMs), offer a powerful tool that can be used to address several challenges and significantly reduce operational costs. It should be noted that LLMs will play a crucial role in supporting human operators and onboard staff in making informed decisions.
In summary, with this paper, we aimed to demonstrate that the future of nuclear reactors in ships is closely tied to AI tools, which play a pivotal role in developing and sustaining a fleet of nuclear maritime ships with zero greenhouse gas emissions.

Author Contributions

Conceptualization, M.A. and K.I.; investigation, M.A.; resources, K.I.; writing—original draft preparation, M.A. and K.I.; writing—review and editing, M.A. and K.I. All authors have read and agreed to the published version of the manuscript.

Funding

This research received no funding.

Institutional Review Board Statement

Not applicable.

Data Availability Statement

No new data were used or generated in this work.

Conflicts of Interest

Author Konstantinos Ipiotis was employed by the company SWECO UK Limited. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

References

  1. Freire, L.O.; de Andrade, D.A. Historic survey on nuclear merchant ships. Nucl. Eng. Des. 2015, 293, 176–186. [Google Scholar] [CrossRef]
  2. Hidayatullah, H.; Susyadi, S.; Subki, M.H. Design and technology development for small modular reactors–Safety expectations, prospects and impediments of their deployment. Prog. Nucl. Energy 2015, 79, 127–135. [Google Scholar] [CrossRef]
  3. Schøyen, H.; Steger-Jensen, K. Nuclear propulsion in ocean merchant shipping: The role of historical experiments to gain insight into possible future applications. J. Clean. Prod. 2017, 169, 152–160. [Google Scholar] [CrossRef]
  4. Wróbel, K. A tale of two disruptive maritime technologies: Nuclear propulsion and autonomy. TransNav Int. J. Mar. Navig. Saf. Sea Transp. 2022, 16, 733–741. [Google Scholar] [CrossRef]
  5. Wang, Q.; Zhang, H.; Zhu, P. Using nuclear energy for maritime decarbonization and related environmental challenges: Existing regulatory shortcomings and improvements. Int. J. Environ. Res. Public Health 2023, 20, 2993. [Google Scholar] [CrossRef]
  6. Virvou, M.; Tsihrintzis, G.A.; Bourbakis, N.G.; Jain, L.C. Introduction to Handbook on Artificial Intelligence-Empowered Applied Software Engineering—Vol. 2: Smart Software Applications in Cyber-Physical Systems; Springer International Publishing: New York, NY, USA, 2022; pp. 1–7. [Google Scholar]
  7. Alamaniotis, M. Challenges and AI-based solutions for smart energy consumption in smart cities. In Advances in Artificial Intelligence-Based Technologies: Selected Papers in Honour of Professor Nikolaos G. Bourbakis—Vol. 1; Springer: Berlin/Heidelberg, Germany, 2022; pp. 111–124. [Google Scholar]
  8. Durlik, I.; Miller, T.; Kostecka, E.; Tuński, T. Artificial Intelligence in Maritime Transportation: A Comprehensive Review of Safety and Risk Management Applications. Appl. Sci. 2024, 14, 8420. [Google Scholar] [CrossRef]
  9. Alamaniotis, M.; Heifetz, A. Survey of Machine Learning Approaches in Radiation Data Analytics Pertained to Nuclear Security. In Advances in Machine Learning/Deep Learning-Based Technologies: Selected Papers in Honour of Professor Nikolaos, G. Bourbakis–Vol. 2; Springer International Publishing: Cham, Switzerland, 2022; pp. 97–115. [Google Scholar]
  10. Uhrig, R.E. Use of Expert Systems in Nuclear Power Plants; No. CONF-890899-1; Oak Ridge National Lab.: Oak Ridge, TN, USA, 1989. [Google Scholar]
  11. Upadhyaya, B.R.; Zhao, K.; Lu, B. Fault monitoring of nuclear power plant sensors and field devices. Prog. Nucl. Energy 2003, 43, 337–342. [Google Scholar] [CrossRef]
  12. Sethu, M.; Kotla, B.; Russell, D.; Madadi, M.; Titu, N.A.; Coble, J.B.; Boring, R.L.; Blache, K.; Agarwal, V.; Yadav, V.; et al. Application of artificial intelligence in detection and mitigation of human factor errors in nuclear power plants: A review. Nucl. Technol. 2023, 209, 276–294. [Google Scholar] [CrossRef]
  13. Zhou, G.; Tan, D. Review of nuclear power plant control research: Neural network-based methods. Ann. Nucl. Energy 2023, 181, 109513. [Google Scholar] [CrossRef]
  14. Radaideh, M.I.; Pigg, C.; Kozlowski, T.; Deng, Y.; Qu, A. Neural-based time series forecasting of loss of coolant accidents in nuclear power plants. Expert Syst. Appl. 2020, 160, 113699. [Google Scholar] [CrossRef]
  15. Son, J.; Choi, J.; Yoon, H. New complementary points of cyber security schemes for critical digital assets at nuclear power plants. IEEE Access 2019, 7, 78379–78390. [Google Scholar] [CrossRef]
  16. Wu, J.; Ma, Y.; Yu, C.; Zou, C.; Cai, X.; Chen, J. Nuclear non-proliferation review and improving proliferation resistance assessment in the future. Int. J. Energy Res. 2021, 45, 11399–11422. [Google Scholar] [CrossRef]
  17. Boahen, J.K.; Elsagheer Mohamed, S.A.; Khalil, A.S.; Hassan, M.A. Application of artificial intelligence techniques in modeling attenuation behavior of ionization radiation: A review. Radiat. Detect. Technol. Methods 2023, 7, 56–83. [Google Scholar] [CrossRef]
  18. Fu, Y.; Zhang, H.; Morris, E.D.; Glide-Hurst, C.K.; Pai, S.; Traverso, A.; Wee, L.; Hadzic, I.; Lønne, P.I.; Shen, C.; et al. Artificial intelligence in radiation therapy. IEEE Trans. Radiat. Plasma Med. Sci. 2021, 6, 158–181. [Google Scholar] [CrossRef]
  19. Seah, J.; Brady, Z.; Ewert, K.; Law, M. Artificial intelligence in medical imaging: Implications for patient radiation safety. Br. J. Radiol. 2021, 94, 20210406. [Google Scholar] [CrossRef]
  20. Assani, N.; Matić, P.; Kaštelan, N.; Čavka, I.R. A review of artificial neural networks applications in maritime industry. IEEE Access 2023, 11, 139823–139848. [Google Scholar] [CrossRef]
  21. Simion, D.; Postolache, F.; Fleacă, B.; Fleacă, E. Ai-driven predictive maintenance in modern maritime transport—Enhancing operational efficiency and reliability. Appl. Sci. 2024, 14, 9439. [Google Scholar] [CrossRef]
  22. Theodoropoulos, P.; Spandonidis, C.C.; Giannopoulos, F.; Fassois, S. A deep learning-based fault detection model for optimization of shipping operations and enhancement of maritime safety. Sensors 2021, 21, 5658. [Google Scholar] [CrossRef]
  23. Tang, W.; Roman, D.; Dickie, R.; Robu, V.; Flynn, D. Prognostics and health management for the optimization of marine hybrid energy systems. Energies 2020, 13, 4676. [Google Scholar] [CrossRef]
  24. Pérez-Canosa, J.M.; Lama-Carballo, F.J.; Salgado-Don, A.; Cao-Feijóo, G.; Pacheco, E.A.; Orosa, J.A. Novel Modeling for the Calculation of the Center of Lateral Resistance Position of Different Ships Making Use of a Full Mission Bridge Simulator and AI Tools. J. Mar. Sci. Eng. 2024, 12, 1381. [Google Scholar] [CrossRef]
  25. Kim, M.K.; Kim, J.H.; Yang, H. Optimal route generation and route-following control for autonomous vessel. J. Mar. Sci. Eng. 2023, 11, 970. [Google Scholar] [CrossRef]
  26. Alexiou, K.; Pariotis, E.G.; Zannis, T.C.; Leligou, H.C. Prediction of a ship’s operational parameters using artificial intelligence techniques. J. Mar. Sci. Eng. 2021, 9, 681. [Google Scholar] [CrossRef]
  27. Jian, J.; Sun, Z.; Sun, K. An intelligent automatic sea forecasting system targeting specific areas on sailing routes. Sustainability 2024, 16, 1117. [Google Scholar] [CrossRef]
  28. Martínez, R.; García, J.A.; Felis, I. AI-Driven Estimation of Vessel Sailing Times and Underwater Acoustic Pressure for Optimizing Maritime Logistics. Eng. Proc. 2023, 58, 26. [Google Scholar] [CrossRef]
  29. Lee, J.; Eom, J.; Park, J.; Jo, J.; Kim, S. The development of a machine learning-based carbon emission prediction method for a multi-fuel-propelled smart ship by using onboard measurement data. Sustainability 2024, 16, 2381. [Google Scholar] [CrossRef]
  30. Qiao, D.; Liu, G.; Lv, T.; Li, W.; Zhang, J. Marine vision-based situational awareness using discriminative deep learning: A survey. J. Mar. Sci. Eng. 2021, 9, 397. [Google Scholar] [CrossRef]
  31. Zhang, Y.; Zhang, D.; Jiang, H. A review of artificial intelligence-based optimization applications in traditional active maritime collision avoidance. Sustainability 2023, 15, 13384. [Google Scholar] [CrossRef]
  32. Haruna, M.; Gebremeskel, K.G.; Troscia, M.; Tardo, A.; Pagano, P. Mechanisms for Securing Autonomous Shipping Services and Machine Learning Algorithms for Misbehaviour Detection. Telecom 2024, 5, 1031–1050. [Google Scholar] [CrossRef]
  33. Valero, C.I.; Ivancos Pla, E.; Vaño, R.; Garro, E.; Boronat, F.; Palau, C.E. Design and development of an aiot architecture for introducing a vessel eta cognitive service in a legacy port management solution. Sensors 2021, 21, 8133. [Google Scholar] [CrossRef]
  34. Camarasa, C.; Mata, É.; Navarro, J.P.J.; Reyna, J.; Bezerra, P.; Angelkorte, G.B.; Feng, W.; Filippidou, F.; Forthuber, S.; Harris, C.; et al. A global comparison of building decarbonization scenarios by 2050 towards 1.5–2 C targets. Nat. Commun. 2022, 13, 3077. [Google Scholar] [CrossRef]
  35. Edgerton, M. Port and maritime security and sustainability. In Sustainability in the Maritime Domain: Towards Ocean Governance and Beyond; Springer International Publishing: New York, NY, USA, 2021; pp. 155–167. [Google Scholar]
  36. Carlton, J.; Aldwinkle, J.; Anderson, J. Future ship powering options: Exploring alternative methods of ship propulsion. Lond R. Acad. Eng. 2013, 1–95. Available online: https://www.semanticscholar.org/paper/FUTURE-SHIP-POWERING-OPTIONS-Exploring-alternative/2d4294d734371e2c957e2e249a492e655c9a1ed0 (accessed on 15 February 2025).
  37. Lange, R.S. Theme Study–Large Vessel NS Savannah; US Department of the Interior, History Division: Washington, DC, USA, 1990; Volume 32.
  38. Alamaniotis, M. Intelligent Scheduling of Floating Nuclear Reactor Operation for Implementation of Distributed Smart Energy Systems in Remote Coastal Locations. In Proceedings of the IEEE 36th International Conference on Tools with Artificial Intelligence, Herndon, VA, USA, 28–30 October 2024. [Google Scholar]
  39. Lu, C.; Lyu, J.; Zhang, L.; Gong, A.; Fan, Y.; Yan, J.; Li, X. Nuclear power plants with artificial intelligence in industry 4.0 era: Top-level design and current applications—A systemic review. IEEE Access 2020, 8, 194315–194332. [Google Scholar] [CrossRef]
  40. Cappelli, M. (Ed.) Instrumentation and Control Systems for Nuclear Power Plants; Woodhead Publishing: Cambridge, UK, 2023. [Google Scholar]
  41. Alamaniotis, M.; Cappelli, M. Intelligent identification of boiling water reactor state utilizing relevance vector regression models. J. Nucl. Eng. Radiat. Sci. 2018, 4, 020904. [Google Scholar] [CrossRef]
  42. Xu, B.; Kumar, S.A. Big data analytics framework for system health monitoring. In 2015 IEEE International Congress on Big Data; IEEE: Piscataway, NJ, USA, 2015; pp. 401–408. [Google Scholar]
  43. Alamaniotis, M.; Cappelli, M. Real-Time State Identification of Boiling Water Reactors Using Relevance Vector Machines. In International Conference on Nuclear Engineering; American Society of Mechanical Engineers: New York, NY, USA, 2016; Volume 50015, p. V001T04A001. [Google Scholar]
  44. Gohel, H.A.; Upadhyay, H.; Lagos, L.; Cooper, K.; Sanzetenea, A. Predictive maintenance architecture development for nuclear infrastructure using machine learning. Nucl. Eng. Technol. 2020, 52, 1436–1442. [Google Scholar] [CrossRef]
  45. Saley, A.M.; Marchand, J.; Sekhari, A.; Cheutet, V.; Danielou, J.B. State-of-art and maturity overview of the nuclear industry on predictive maintenance. In Proceedings of the IFIP International Conference on Product Lifecycle Management, Grenoble, France, 10–13 July 2022; Springer Nature: Cham, Switzerland, 2022; pp. 337–346. [Google Scholar]
  46. Achouch, M.; Dimitrova, M.; Ziane, K.; Sattarpanah Karganroudi, S.; Dhouib, R.; Ibrahim, H.; Adda, M. On predictive maintenance in industry 4.0: Overview, models, and challenges. Appl. Sci. 2022, 12, 8081. [Google Scholar] [CrossRef]
  47. Zhao, X.; Kim, J.; Warns, K.; Wang, X.; Ramuhalli, P.; Cetiner, S.; Kang, H.G.; Golay, M. Prognostics and health management in nuclear power plants: An updated method-centric review with special focus on data-driven methods. Front. Energy Res. 2021, 9, 696785. [Google Scholar] [CrossRef]
  48. Agarwal, V.; Lybeck, N.J.; Bickford, R.; Rusaw, R. Development of asset fault signatures for prognostic and health management in the nuclear industry. In Proceedings of the 2014 International Conference on Prognostics and Health Management, Cheney, DC, USA, 22–25 June 2014; IEEE: Piscataway, NJ, USA; pp. 1–7. [Google Scholar]
  49. Liao, L.; Köttig, F. Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems, and an application to battery life prediction. IEEE Trans. Reliab. 2014, 63, 191–207. [Google Scholar] [CrossRef]
  50. Maitlo, A.A.; Liu, Y.K.; Lakhan, M.N.; Raza, W.; Shar, A.H.; Ali, A.; Hanan, A.; Ahmed, M. Recent advances in nuclear power plant for fault detection diagnosis-a review. J. Crit. Rev. 2020, 7, 4340–4349. [Google Scholar]
  51. Elshenawy, L.M.; Halawa, M.A.; Mahmoud, T.A.; Awad, H.A.; Abdo, M.I. Unsupervised machine learning techniques for fault detection and diagnosis in nuclear power plants. Prog. Nucl. Energy 2021, 142, 103990. [Google Scholar] [CrossRef]
  52. Qi, B.; Liang, J.; Tong, J. Fault diagnosis techniques for nuclear power plants: A review from the artificial intelligence perspective. Energies 2023, 16, 1850. [Google Scholar] [CrossRef]
  53. Adumene, S.; Islam, R.; Amin, M.T.; Nitonye, S.; Yazdi, M.; Johnson, K.T. Advances in nuclear power system design and fault-based condition monitoring towards safety of nuclear-powered ships. Ocean. Eng. 2022, 251, 111156. [Google Scholar] [CrossRef]
  54. Reyes, A.M.; Chengu, A.; Gatsis, N.; Ahmed, S.; Alamaniotis, M. Model Explainable AI Method for Fault Detection in Inverter-Based Distribution Systems. In Proceedings of the 2024 IEEE Texas Power and Energy Conference (TPEC), College Station, TX, USA, 13–14 February 2024; IEEE: Piscataway, NJ, USA; pp. 1–6. [Google Scholar]
  55. Nissan, E. An overview of AI methods for in-core fuel management: Tools for the automatic design of nuclear reactor core configurations for fuel reload, (re)arranging new and partly spent fuel. Designs 2019, 3, 37. [Google Scholar] [CrossRef]
  56. Ortiz, J.J.; Castillo, A.; Montes, J.L.; Perusquía, R. A new system to fuel loading and control rod pattern optimization in boiling water reactors. Nucl. Sci. Eng. 2007, 157, 236–244. [Google Scholar] [CrossRef]
  57. Sobolev, A.V.; Gazetdinov, A.S.; Samokhin, D.S. Genetic algorithms for nuclear reactor fuel load and reload optimization problems. Nucl. Energy Technol. 2017, 3, 231–235. [Google Scholar] [CrossRef]
  58. Li, Z.; Wang, J.; Ding, M. A review on optimization methods for nuclear reactor fuel reloading analysis. Nucl. Eng. Des. 2022, 397, 111950. [Google Scholar] [CrossRef]
  59. Rowinski, M.K.; White, T.J.; Zhao, J. Small and Medium sized Reactors (SMR): A review of technology. Renew. Sustain. Energy Rev. 2015, 44, 643–656. [Google Scholar] [CrossRef]
  60. Arvanitidis, A.I.; Agarwal, V.; Alamaniotis, M. Nuclear-driven integrated energy systems: A state-of-the-art review. Energies 2023, 16, 4293. [Google Scholar] [CrossRef]
  61. Ali, M.S.; Sharma, A.; Joy, T.A.; Halim, M.A. A Comprehensive Review of Integrated Energy Management for Future Smart Energy System. Control Syst. Optim. Lett. 2024, 2, 43–51. [Google Scholar] [CrossRef]
  62. Bragg-Sitton, S.M.; Boardman, R.; Rabiti, C.; O’Brien, J. Reimagining future energy systems: Overview of the US program to maximize energy utilization via integrated nuclear-renewable energy systems. Int. J. Energy Res. 2020, 44, 8156–8169. [Google Scholar] [CrossRef]
  63. Azman, M.A.N.; Ali, N.S.M.; Sarkawi, M.S.; Sazali, M.A.; Basri, N.A. Nuclear fuel materials and its sustainability for low carbon energy system: A review. In IOP Conference Series: Materials Science and Engineering; IOP Publishing: Bristol, UK, 2022; Volume 1231, p. 012016. [Google Scholar]
  64. Kumbhar, A.; Dhawale, P.G.; Kumbhar, S.; Patil, U.; Magdum, P. A comprehensive review: Machine learning and its application in integrated power system. Energy Rep. 2021, 7, 5467–5474. [Google Scholar] [CrossRef]
  65. Gabbar, H.A.; Adham, M.I.; Abdussami, M.R. Optimal planning of integrated nuclear-renewable energy system for marine ships using artificial intelligence algorithm. Energies 2021, 14, 3188. [Google Scholar] [CrossRef]
  66. Arvanitidis, A.I.; Alamaniotis, M. Integrating an Ensemble Reward System into an Off-Policy Reinforcement Learning Algorithm for the Economic Dispatch of Small Modular Reactor-Based Energy Systems. Energies 2024, 17, 2056. [Google Scholar] [CrossRef]
  67. Gabbar, H.A.; Adham, M.I.; Abdussami, M.R. Analysis of nuclear-renewable hybrid energy system for marine ships. Energy Rep. 2021, 7, 2398–2417. [Google Scholar] [CrossRef]
  68. Ghazi, Z.M.; Rizvi, S.W.F.; Shahid, W.M.; Abdulhameed, A.M.; Saleem, H.; Zaidi, S.J. An overview of water desalination systems integrated with renewable energy sources. Desalination 2022, 542, 116063. [Google Scholar] [CrossRef]
  69. Peakman, A.; Owen, H.; Abram, T. The core design of a Small Modular Pressurised Water Reactor for commercial marine propulsion. Prog. Nucl. Energy 2019, 113, 175–185. [Google Scholar] [CrossRef]
  70. Jones, D.; Snider, C.; Nassehi, A.; Yon, J.; Hicks, B. Characterising the Digital Twin: A systematic literature review. CIRP J. Manuf. Sci. Technol. 2020, 29, 36–52. [Google Scholar] [CrossRef]
  71. Stewart, R.; Treviño, E.; Shields, A.; Heaps, K.; Darrington, J.; Williams, Q.; Pope, C.; Scott, J.; Baker, B.; Palmer, J.; et al. The AGN-201 Digital Twin: A test bed for remotely monitoring nuclear reactors. Ann. Nucl. Energy 2025, 213, 111041. [Google Scholar] [CrossRef]
  72. Mengyan, H.; Xueyan, Z.; Cuiting, P.; Yixuan, Z.; Jun, Y. Current status of digital twin architecture and application in nuclear energy field. Ann. Nucl. Energy 2024, 202, 110491. [Google Scholar] [CrossRef]
  73. Daniell, J.; Kobayashi, K.; Alajo, A.; Alam, S.B. Digital twin-centered hybrid data-driven multi-stage deep learning framework for enhanced nuclear reactor power prediction. Energy AI 2025, 19, 100450. [Google Scholar] [CrossRef]
  74. Satu, P.; Jari, L.; Hanna, K.; Tomi, P.; Marja, L.; Tuisku-Tuuli, S. Virtual-Reality training solutions for nuclear power plant field operators: A scoping review. Prog. Nucl. Energy 2024, 169, 105104. [Google Scholar] [CrossRef]
  75. Hall, A.; Murray, P.; Boring, R.L.; Agarwal, V. Human-centered and explainable artificial intelligence in nuclear operations. In Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Online, 8–13 September 2024; SAGE Publications: Sage, CA, USA; Los Angeles, CA, USA; Volume 68, pp. 1563–1568. [Google Scholar]
  76. Carvalho, P.V.; dos Santos, I.L.; Gomes, J.O.; Borges, M.R.; Guerlain, S. Human factors approach for evaluation and redesign of human–system interfaces of a nuclear power plant simulator. Displays 2008, 29, 273–284. [Google Scholar] [CrossRef]
  77. Martin, A.; Harbison, S.; Beach, K.; Cole, P. An Introduction to Radiation Protection; Crc Press: Boca Raton, FL, USA, 2018. [Google Scholar]
  78. Fei, T.; Zhong, Z.; Bays, S.E.; Heidet, F. Radiation Protection and Shielding Analysis of the Versatile Test Reactor. Nucl. Sci. Eng. 2022, 196 (Suppl. S1), 98–109. [Google Scholar] [CrossRef]
  79. Chandra, A.; Chakraborty, A. Exploring the role of large language models in radiation emergency response. J. Radiol. Prot. 2024, 44, 011510. [Google Scholar] [CrossRef]
  80. Zhang, K.; Li, L.; Xu, X.; Xin, R.; Xu, X.; Zhang, P. Intelligent Q&A System for Power Dispatching Based on Retrieval Augmented Generation. In Proceedings of the 2024 6th International Conference on Energy, Power and Grid (ICEPG), Guangzhou, China, 27–29 September 2024; IEEE: Piscataway, NJ, USA; pp. 1604–1608. [Google Scholar]
  81. Miles, P.R.; Cook, J.A.; Angers, Z.V.; Swenson, C.J.; Kiedrowski, B.C.; Mattingly, J.; Smith, R.C. Radiation source localization using surrogate models constructed from 3-D Monte Carlo transport physics simulations. Nucl. Technol. 2021, 207, 37–53. [Google Scholar] [CrossRef]
  82. Alamaniotis, M.; Heifetz, A.; Raptis, A.C.; Tsoukalas, L.H. Fuzzy-logic radioisotope identifier for gamma spectroscopy in source search. IEEE Trans. Nucl. Sci. 2013, 60, 3014–3024. [Google Scholar] [CrossRef]
  83. Gharibshahi, E.; Alamaniotis, M. Artificial Intelligence Detection System of Radioactive Nanocomposites in Liquid-Filled Containers for Nuclear Security. Nucl. Technol. 2024, 210, 868–883. [Google Scholar] [CrossRef]
  84. Ştefănescu, R.; Hite, J.; Cook, J.; Smith, R.C.; Mattingly, J. Surrogate-based robust design for a non-smooth radiation source detection problem. Algorithms 2019, 12, 113. [Google Scholar] [CrossRef]
  85. Maglaras, L.; Kantzavelou, I.; Ferrag, M.A. Digital transformation and cybersecurity of critical infrastructures. Appl. Sci. 2021, 11, 8357. [Google Scholar] [CrossRef]
  86. Wilson, C. Cyber threats to critical information infrastructure. In Cyberterrorism: Understanding, Assessment, and Response; Springer: New York, NY, USA, 2014; pp. 123–136. [Google Scholar]
  87. Ayodeji, A.; Mohamed, M.; Li, L.; Di Buono, A.; Pierce, I.; Ahmed, H. Cyber security in the nuclear industry: A closer look at digital control systems, networks and human factors. Prog. Nucl. Energy 2023, 161, 104738. [Google Scholar] [CrossRef]
  88. Salem, A.H.; Azzam, S.M.; Emam, O.E.; Abohany, A.A. Advancing cybersecurity: A comprehensive review of AI-driven detection techniques. J. Big Data 2024, 11, 105. [Google Scholar] [CrossRef]
  89. Campos, B.M.; Alamaniotis, M. Review of internal cyber attacks in nuclear facilities and an artificial neural network model for implementing internal cyberforensics. Nucl. Technol. Radiat. Prot. 2021, 36, 128–138. [Google Scholar] [CrossRef]
  90. Kaur, R.; Gabrijelčič, D.; Klobučar, T. Artificial intelligence for cybersecurity: Literature review and future research directions. Inf. Fusion 2023, 97, 101804. [Google Scholar] [CrossRef]
  91. Bokkena, B. Enhancing IT Security with LLM-Powered Predictive Threat Intelligence. In Proceedings of the 2024 5th International Conference on Smart Electronics and Communication (ICOSEC), Trichy, India, 18–20 September 2024; IEEE: Piscataway, NJ, USA; pp. 751–756. [Google Scholar]
  92. Kim, S.; Kim, S.; Nam, K.H.; Kim, S.; Kwon, K.H. Cyber security strategy for nuclear power plant through vital digital assets. In Proceedings of the 2019 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, 5–7 December 2019; IEEE: Piscataway, NJ, USA; pp. 224–226. [Google Scholar]
  93. Mertzimekis, T.J.; Nomikou, P.; Petra, E.; Batista, P.; Cabecinhas, D.; Pascoal, A.; Sebastiño, L.; Escartín, J.; Kebkal, K.; Karantzalos, K.; et al. Radioactivity monitoring in ocean ecosystems (RAMONES). In Proceedings of the Conference on Information Technology for Social Good, Rome, Italy, 9–11 September 2021; pp. 216–220. [Google Scholar]
  94. Chen, M.; Qi, C.; Wu, X. Applications of Artificial Intelligence in Oceanic Nuclear Contamination Management. In Proceedings of the 2024 IEEE Conference on Artificial Intelligence (CAI), Singapore, 25–27 June 2024; IEEE: Piscataway, NJ, USA; pp. 210–215. [Google Scholar]
  95. Simonsen, E.; Osvalder, A.L. Aspects of the nuclear power plant control room system contributing to safe operation. Procedia Manuf. 2015, 3, 1248–1255. [Google Scholar] [CrossRef]
  96. Lagari, P.L.; Nasiakou, A.; Alamaniotis, M. Evaluation of human machine interface (HMI) on a digital analog control room in nuclear power plants using a fuzzy logic approach. Int. J. Monit. Surveill. Technol. Res. 2016, 4, 50–68. [Google Scholar] [CrossRef]
  97. Porthin, M.; Liinasuo, M.; Kling, T. Effects of digitalization of nuclear power plant control rooms on human reliability analysis–A review. Reliab. Eng. Syst. Saf. 2020, 194, 106415. [Google Scholar] [CrossRef]
  98. Liao, J.; Ou, X.; Zhao, W.; Li, X.; Yu, Q. Research on Intelligent Operation Support Technology for 5G Nuclear-Powered Ships. In Proceedings of the 2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture (AIAM), Manchester, UK, 23–25 October 2021; IEEE: Piscataway, NJ, USA; pp. 500–504. [Google Scholar]
  99. Sethu, M.; Titu, N.A.; Hu, D.; Madadi, M.; Coble, J.; Boring, R.; Blache, K.; Agarwal, V.; Yadav, V.; Khojandi, A. Using artificial intelligence to mitigate human factor errors in nuclear power plants: A review. In Proceedings of the 12th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies, Online, 14–17 June 2021; pp. 129–141. [Google Scholar]
  100. Shorthill, T.H.; Chen, E.; Kim, J.; Wang, C.; Athe, P.; Bao, H.; Dinh, N.; Lawrence, S. An Integrated Framework for Risk Assessment of Safety-Related Digital Instrumentation and Control Systems in Nuclear Power Plants: Methodology Advancement and Application; No. INL/RPT-24-80888-Rev000; Idaho National Laboratory (INL): Idaho Falls, ID, USA, 2024. [Google Scholar]
  101. Alamaniotis, M.; Fevgas, A. Intelligent Management of Integrated Energy Systems in Remote Maritime Environments utilizing Fuzzy Modes. In Proceedings of the Mediterranean Conference on Power Generation, Transmission, Distribution, and Energy Conversion (MEDPOWER 2024), Athens, Greece, 3–6 November 2024; pp. 1–6. [Google Scholar]
  102. Narula, K. Ships as workhorses of energy trade. The Maritime Dimension of Sustainable Energy Security; Springer: Berlin/Heidelberg, Germany, 2019; pp. 95–115. [Google Scholar]
  103. Mischos, S.; Dalagdi, E.; Vrakas, D. Intelligent energy management systems: A review. Artif. Intell. Rev. 2023, 56, 11635–11674. [Google Scholar] [CrossRef]
  104. Nti, I.K.; Teimeh, M.; Nyarko-Boateng, O.; Adekoya, A.F. Electricity load forecasting: A systematic review. J. Electr. Syst. Inf. Technol. 2020, 7, 13. [Google Scholar] [CrossRef]
  105. Winn, J.I.; Govern, K.H. Maritime pirates, sea robbers, and terrorists: New approaches to emerging threats. Homel. Secur. Rev. 2008, 2, 131. [Google Scholar]
  106. Helmick, J.S. Maritime piracy and the supply chain. In Global Supply Chain Security: Emerging Topics in Research, Practice and Policy; Springer: Berlin/Heidelberg, Germany, 2015; pp. 17–34. [Google Scholar]
  107. Li, H.; Yang, Z. Towards safe navigation environment: The imminent role of spatio-temporal pattern mining in maritime piracy incidents analysis. Reliab. Eng. Syst. Saf. 2023, 238, 109422. [Google Scholar] [CrossRef]
  108. Vaněk, O.; Jakob, M.; Hrstka, O.; Pěchouček, M. Agent-based model of maritime traffic in piracy-affected waters. Transp. Res. Part C: Emerg. Technol. 2013, 36, 157–176. [Google Scholar] [CrossRef]
  109. Carlton, J.S.; Smart, R.; Jenkins, V. The nuclear propulsion of merchant ships: Aspects of engineering, science and technology. J. Mar. Eng. Technol. 2011, 10, 47–59. [Google Scholar] [CrossRef]
  110. Reistad, O.; Soerlie, A. Non-proliferation and Other Security-related Issues Associated with the Dismantling of Nuclear Vessels in North-West Russia. In Remaining Issues in the Decommissioning of Nuclear Powered Vessels: Including Issues Related to the Environmental Remediation of the Supporting Infrastructure; Springer: Dordrecht, The Netherlands, 2003; pp. 79–90. [Google Scholar]
  111. Okochi, M.; Haberfield, M.; Hemmi, S.; Takemoto, T. Safety and Security Measures for the Maritime Transport of Nuclear Material: Technical Standards and Physical Protection. Trans. Navig. 2021, 6, 97–107. [Google Scholar]
  112. Earle, O.K. Options for the handling and storage of nuclear vessel spent fuel. In Remaining Issues in the Decommissioning of Nuclear Powered Vessels: Including Issues Related to the Environmental Remediation of the Supporting Infrastructure; Springer: Dordrecht, The Netherlands, 2002; pp. 285–295. [Google Scholar]
  113. Jendoubi, C.; Asad, A. A Survey of Artificial Intelligence Applications in Nuclear Power Plants. IoT 2024, 5, 666–691. [Google Scholar] [CrossRef]
  114. Tambouratzis, T.; Giannatsis, J.; Kyriazis, A.; Siotropos, P. Applying the computational intelligence paradigm to nuclear power plant operation: A review (1990–2015). In Research Anthology on Artificial Intelligence Applications in Security; IGI Global: Hershey, PA, USA, 2021; pp. 1507–1578. [Google Scholar]
Figure 1. Predictive maintenance concept in nuclear industry (upper path) and nuclear maritime vessels (lower path), where latter illustrates extra challenges needed to be taken into consideration.
Figure 1. Predictive maintenance concept in nuclear industry (upper path) and nuclear maritime vessels (lower path), where latter illustrates extra challenges needed to be taken into consideration.
Sustainability 17 03654 g001
Figure 2. General architecture for ship onboard integrated energy systems, and use of artificial intelligence for management of its operation.
Figure 2. General architecture for ship onboard integrated energy systems, and use of artificial intelligence for management of its operation.
Sustainability 17 03654 g002
Figure 3. Architecture of intelligent nuclear reactor training system for nuclear ships that combines explainable artificial intelligence and digital twins.
Figure 3. Architecture of intelligent nuclear reactor training system for nuclear ships that combines explainable artificial intelligence and digital twins.
Sustainability 17 03654 g003
Figure 4. Security architecture for nuclear material accountability, where AI analyzes data to make inferences concerning onboard activities associated with nuclear materials.
Figure 4. Security architecture for nuclear material accountability, where AI analyzes data to make inferences concerning onboard activities associated with nuclear materials.
Sustainability 17 03654 g004
Figure 5. Block diagram of potential use of foundation model for identifying critical digital assets (CDAs) in nuclear maritime ships.
Figure 5. Block diagram of potential use of foundation model for identifying critical digital assets (CDAs) in nuclear maritime ships.
Sustainability 17 03654 g005
Figure 6. AI solutions for supplying electricity to ports from docked nuclear ships include advanced forecasting and efficient management.
Figure 6. AI solutions for supplying electricity to ports from docked nuclear ships include advanced forecasting and efficient management.
Sustainability 17 03654 g006
Table 1. Application areas of artificial intelligence in nuclear-powered ships.
Table 1. Application areas of artificial intelligence in nuclear-powered ships.
Application AreaAI Solutions
Monitoring and Maintenance
  • Fault detection
  • Predictive maintenance
  • Failure prognosis and diagnosis
Core Refueling Optimization
  • Fuel rod loading sequence
On-Ship Nuclear Integrated Energy Systems Management
  • Optimize management of generated energy
  • Forecast of onboard load demand
  • Integration of nuclear with renewable energy
  • Control nuclear propulsion
  • Decision-making about water desalination
  • Decision-making about heat production
Digital Twins for Nuclear-Powered Maritime Vessel Operations
  • Simulation and prediction of ships’ system behavior and operation, maintenance simulation
  • Asset management and hazard risk assessment
  • Training of human operators
Radiation Protection
  • Design optimal radiation physical protection systems
  • Provide real-time information in case of emergency
  • Knowledge maintenance regarding safety protocols
Safeguarding and Security of
Nuclear Materials
  • Monitoring of integrity of onboard nuclear materials
  • Detecting illicit activities pertaining to nuclear materials
  • Report activity summaries to IAEA
Cybersecurity
  • Use foundation models for identifying critical digital assets
  • Ensure secure operation of onboard critical digital assets related to nuclear reactors
  • Take mitigation measures and perform digital forensics
Nuclear Contamination
Management
  • Control robots in cleaning up radioactive pollutants
  • Detection of contamination
  • Nuclear waste handling
Onboard Digital Panel Operation
  • User-friendly software interfaces
  • Summarizing operational procedures
  • Human errors: risk mitigation, root cause analysis
Electricity Supply at Ports
  • Decisions regarding supply of electricity at ports
Secure Informative
Navigation Systems
  • Very short-term battle maneuvering
  • Route and rerouting decisions to ensure secure and safe traveling of ship
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Alamaniotis, M.; Ipiotis, K. Artificial Intelligence as Enabler for Adoption of Sustainable Nuclear-Powered Maritime Ships: Challenges and Opportunities. Sustainability 2025, 17, 3654. https://doi.org/10.3390/su17083654

AMA Style

Alamaniotis M, Ipiotis K. Artificial Intelligence as Enabler for Adoption of Sustainable Nuclear-Powered Maritime Ships: Challenges and Opportunities. Sustainability. 2025; 17(8):3654. https://doi.org/10.3390/su17083654

Chicago/Turabian Style

Alamaniotis, Miltiadis, and Konstantinos Ipiotis. 2025. "Artificial Intelligence as Enabler for Adoption of Sustainable Nuclear-Powered Maritime Ships: Challenges and Opportunities" Sustainability 17, no. 8: 3654. https://doi.org/10.3390/su17083654

APA Style

Alamaniotis, M., & Ipiotis, K. (2025). Artificial Intelligence as Enabler for Adoption of Sustainable Nuclear-Powered Maritime Ships: Challenges and Opportunities. Sustainability, 17(8), 3654. https://doi.org/10.3390/su17083654

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop