][]

Review

Artiﬁcial Intelligence and its integration in Naval

Operations

La Inteligencia Artiﬁcial y su integración en las

Operaciones Navales

Oscar Alejandro Torres Salcedo ¹

∗

, Ginary Sarmiento Meneses ²and Juan David Vélez Restrepo ³

1

Batallón de Fuerzas Especiales de I.M, Cartagena, 130001, Colombia; oscar.torres.s@armada.mil.co

Estación de Guardacostas Primaria de Tumaco, Tumaco, 528502, Colombia; ginary.meneses@armada.mil.co

Centro de Investigación, Desarrollo e Innovación para Actividades Marítimas, Cartagena, 130001, Colombia;

juan.velez@armada.mil.co

2

3

∗

Correspondence: oscar.torres.s@armada.mil.co

Citation: Torres, O.; Sarmiento, G.; Vélez, J. Artiﬁcial Intelligence and its integration in Naval Operations. OnBoard Knowledge Journal

2026, 2, 2. https://doi.org/10.70554/OBJK2026.v02n01.02

Received: 01/05/2025, Accepted: 05/06/2025, Published: 24/03/2026

DOI: https://doi.org/10.70554/OBJK2026.v02n01.02

Abstract: A literature review was carried out with the objective of analyzing the impact of artiﬁcial intelligence (AI) in

the improvement of surveillance and reconnaissance systems, with emphasis on the early detection of threats in coastal

areas. For this purpose, the parameters of the systematic methodology were followed to identify, select and analyze

the most relevant information on the integration of AI in naval operations, with a particular focus on surveillance and

reconnaissance systems. The search for information was carried out in recognized academic and technical databases,

both in the general ﬁeld and in the defense sector. The main sources used included academic databases such as Scopus,

Google Scholar, Semantic Scholar and JSTOR, 35 studies were selected that met the deﬁned inclusion and exclusion

requirements, for the period between 2020 - 2025. Common patterns and factors were found within the review, which

were organized into 6 topics for further analysis, namely: fundamentals and advances of AI in naval operations. AI

techniques applied in surveillance and reconnaissance. Integration of AI with existing surveillance technology. Early

warning systems and threat prediction. Practical implementation in security and defense strategies. Ethical, legal and

cybersecurity aspects. The relevant results of the review show that the use of advanced algorithms (deep learning, neural

networks, etc.) signiﬁcantly improves the detection and classiﬁcation of threats in maritime environments, optimizing

the accuracy and speed of operational decision making. Likewise, it is evident that AI-based predictive models allow

detecting anomalies and foreseeing threats in coastal areas, facilitating proactive responses and improving operational

safety, depending largely on the quality and availability of data.

Keywords: Artiﬁcial intelligence; Naval operations; Naval security; Coastal security; Technology.

Resumen: Se llevó a cabo una revisión bibliográﬁca con el objetivo de analizar el impacto de la inteligencia artiﬁcial

(IA) en la mejora de los sistemas de vigilancia y reconocimiento, con énfasis en la detección temprana de amenazas en

zonas costeras. Para ello, se siguieron los parámetros de la metodología sistemática que permitió identiﬁcar, seleccionar y

analizar la información más relevante sobre la integración de la IA en las operaciones navales, con un enfoque particular

OnBoard Knowledge Journal 2026, 2, 2.

https://revistasescuelanaval.com/obk/

Licensed by Escuela Naval de Cadetes "Almirante Padilla", COL.

This article is freely accessible and distributed under the terms and conditions

of Creative Commons Attribution (https://creativecommons.org/licenses/by/4.0/).

OnBoard Knowledge Journal 2026, 2, 2

2 of 13

en los sistemas de vigilancia y reconocimiento. La búsqueda de información se llevó a cabo en bases de datos académicas

y técnicas reconocidas, tanto del ámbito general como del sector defensa. Las principales fuentes utilizadas incluyeron

bases de datos académicas como Scopus, Google Scholar, Semantic Scholar y JSTOR, se seleccionaron 35 estudios que

cumplieron con los requisitos de inclusión y exclusión deﬁnidos, para el periodo comprendido entre 2020 - 2025. Se

encontró dentro de la revisión patrones y factores comunes, que fueron organizados en 6 tópicos para su posterior

análisis, esto son: fundamentos y avances de la IA en las operaciones navales. Técnicas de IA aplicadas en la vigilancia y

el reconocimiento. Integración de IA con tecnología de vigilancia existente. Sistemas de alerta temprana y predicción de

amenazas. Implementación práctica en estrategias de seguridad y defensa. Aspectos éticos, legales y de ciberseguridad.

Los resultados relevantes de la revisión permiten reconocer que el uso de algoritmos avanzados (deep learning, redes

neuronales, etc.) mejora notablemente la detección y clasiﬁcación de amenazas en entornos marítimos, optimizando la

precisión y la rapidez en la toma de decisiones operativas. Así mismo, se evidencia que los modelos predictivos basados

en IA permiten detectar anomalías y prever amenazas en zonas costeras, facilitando respuestas proactivas y mejorando la

seguridad operativa, dependiendo en gran medida de la calidad y disponibilidad de datos.

Palabras clave: Inteligencia artiﬁcial; Operaciones navales; Seguridad naval; Seguridad costera; Tecnología.

1. Introduction

Is it possible to identify the presence of threats in real-time through recognition without the presence

of a human being? 25 years ago, a supercomputer defeated a chess champion, Russian Garry Kasparov, a

historic milestone that, however, was just the beginning of a long journey for Artiﬁcial Intelligence (AI) [6].

AI is a technology that has been advancing rapidly worldwide, both in civilian and military ﬁelds, and its

integration into naval operations is no exception. In the military sector, it is driven by the need for evolution,

with the constant search for faster and more powerful weapons or technologies, which is precisely what AI

offers [21]. It positions itself as a key tool to improve operational effectiveness and real-time decision-making.

This review article addresses the question: What are the applications of AI that can be used in current naval

operations, and how do they improve operational effectiveness? To answer this question, the impact of AI on

surveillance and reconnaissance systems is evaluated, with a particular focus on early threat detection in

coastal areas.

As is well known, there are already powerful countries using AI in military activities, many of which

are unknown and remain conﬁdential due to their use in attack or defense. In this context, it is important

to highlight that AI technologies applied to the military ﬁeld pose a huge challenge for countries that do

not have access to these new technologies. In a short time, a huge gap will open between different military

systems, separating those countries with AI-based systems from those without them [1]. The methodology

employed in this review is based on a systematic analysis of recent scientiﬁc and technical literature, using

specialized databases and reliable sources. It includes scientiﬁc articles, technical reports, and case studies

published in the last ﬁve years to ensure the current and relevant information. The methodological approach

combines a narrative review with a critical analysis of AI applications in naval operations, identifying trends,

challenges, and future opportunities.

The main objective of this review is to analyze the impact of AI in improving surveillance and recon-

naissance systems, with an emphasis on early threat detection in coastal areas. To do so, the most relevant

AI applications in this ﬁeld are analyzed, such as the use of machine learning algorithms for satellite image

interpretation, the integration of facial recognition, and the optimization of sensor networks for real-time

data collection. Furthermore, it discusses how these technologies contribute to decision-making, enabling a

quicker and more accurate response to risk situations. In the words of the current president of Russia, "The

future will belong to AI, and the ﬁrst country to master it will be the governor of the world." – Vladimir

Putin.

This article is structured as follows: Section 1 introduces the topic and provides background information

on the integration of AI in naval operations. Section 2 outlines the contributions of the study, summarizing

OnBoard Knowledge Journal 2026, 2, 2

3 of 13

the main ﬁndings from the reviewed literature. Section 3 presents the methodology used in this systematic

review, detailing the criteria and process for selecting and analyzing relevant studies. Section 4 discusses the

key ﬁndings and insights derived from the reviewed literature, emphasizing the impact of AI on surveillance,

reconnaissance, and early threat detection. Section 5 presents the results of the review, highlighting the

signiﬁcant advancements AI has made in improving operational effectiveness in naval operations. Section

6 draws conclusions based on the study’s ﬁndings, underscoring the importance of AI in transforming

naval operational strategies. Section ?? provides directions for future work, focusing on advancements in

AI integration, the development of hybrid models, and the need for improved regulatory frameworks. The

article concludes with a list of references used throughout the review.

2. Contributions

The contributions of this study are focused on providing a comprehensive review of the integration of

AI in naval operations, particularly in the areas of surveillance, reconnaissance, and early threat detection.

The main contributions include:

i.

This study synthesizes 35 relevant studies, published between 2020 and 2025, that investigate AI’s

impact on improving surveillance and reconnaissance systems in naval environments. The review

highlights the technological advancements in AI, such as machine learning algorithms and deep

learning models, that have signiﬁcantly enhanced the detection and classiﬁcation of maritime threats.

The study provides an in-depth examination of AI techniques, including deep learning, convolutional

neural networks (CNN), and machine learning models, that have been applied to object recogni-

tion, anomaly detection, and real-time maritime data analysis. This research contributes to the

understanding of how these AI methods increase the efﬁciency and accuracy of surveillance systems.

One of the study’s contributions is identifying how AI can be integrated with traditional surveillance

technologies like radars, satellites, and UAVs. The synergy between AI and existing technologies

is crucial for improving detection resolution, optimizing resource management, and enabling more

effective decision-making in maritime operations.

ii.

iii.

iv.

v.

Another key contribution is the exploration of AI-based predictive models for early threat detection.

The study demonstrates how AI can be leveraged to predict anomalies and vulnerabilities in coastal

areas, thus enabling proactive responses and enhancing operational security.

The review also identiﬁes challenges in the operational implementation of AI, such as the dependency

on large datasets, the need for real-time data quality, and the adaptation to dynamic operational

environments. These ﬁndings underscore the importance of continued research into improving AI

algorithms and addressing gaps in data collection and management.

vi.

The study also emphasizes the growing importance of ethical, legal, and cybersecurity issues in

the implementation of AI systems within naval operations. It highlights the need for regulatory

frameworks to ensure the responsible and secure use of AI technologies, as well as addressing

concerns related to privacy and data protection.

vii.

The research proposes practical applications of AI in naval defense, such as the use of AI-driven

systems for coastal surveillance, route optimization, and strategic decision-making in naval operations.

Notably, the study discusses the potential of technologies like the Black Hornet nanodrone and laser

weapon systems integrated with AI, which can enhance the operational capacity of naval forces and

improve national security.

3. Methodology

To conduct this review, a systematic methodology was followed that allowed for the identiﬁcation,

selection, and analysis of the most relevant information on the integration of AI in naval operations, with a

particular focus on surveillance and reconnaissance systems. The following outlines the steps and criteria

used in the research process.

The information search was carried out in recognized academic and technical databases, both general

and defense-related. The main sources used included academic databases such as Scopus, Google Scholar,

OnBoard Knowledge Journal 2026, 2, 2

4 of 13

Semantic Scholar, and JSTOR. Additionally, defense-speciﬁc databases such as the Defense Technical Informa-

tion Center (DTIC) and the Naval Research Laboratory (NRL) were utilized. These sources were selected for

their relevance, reliability, and thematic coverage, ensuring an approach that encompassed both technological

and operational aspects. Clear criteria were established for selecting the studies and documents included in

the review:

Inclusion Criteria:

•

Scientiﬁc articles, technical reports, and case studies published between 2020 and 2025.

Documents addressing AI applications in naval operations, particularly in surveillance, reconnaissance,

and early threat detection.

•

Studies providing empirical evidence or theoretical analysis on the operational effectiveness of AI.

Publications in English and Spanish.

Exclusion Criteria:

•

Documents not directly related to naval operations or AI.

Studies lacking methodological rigor or not supported by reliable sources.

Publications prior to 2020, except those deemed essential for historical context.

Articles not available in full text.

Search Strategies:

The search was conducted using a combination of keywords to optimize the results. The keywords

included terms such as: artiﬁcial intelligence, naval operations, maritime surveillance, early threat detection,

autonomous systems, machine learning, Deep learning. The keywords were combined using Boolean operators:

•

AND: To combine terms and narrow the search (e.g., "artiﬁcial intelligence" AND "naval operations").

OR: To include synonyms or related terms (e.g., "maritime surveillance" OR "coastal monitoring").

NOT: To exclude irrelevant topics (e.g., "artiﬁcial intelligence" NOT "medicine").

Additionally, ﬁlters were applied for temporal range (2020-2025) and language (English and Spanish) to

ensure the timeliness and accessibility of the information.

The initial search yielded a total of 2,430 documents. After removing duplicates and applying the

inclusion and exclusion criteria, 35 studies were selected for detailed review. These documents were analyzed

based on their thematic relevance, methodological quality, and contribution to the research objective.

The analysis focused on identifying AI applications in naval operations, evaluating their impact on

operational effectiveness, and highlighting the associated challenges and opportunities. The literature search

was completed on February 11, 2025, ensuring that the review included the most recent and relevant studies

on the topic.

4. Discussion

Once the suggested review was developed, a series of contributions from academia on the research

topic were found, and to better manage them, they were grouped into a series of subtopics that help establish

the impact of AI in naval operations, speciﬁcally in the areas of reconnaissance and surveillance.

Initially, the identiﬁcation of the foundations and advances of AI in naval operations is presented. In this

regard, it is important to consider technological evolution. A series of studies highlight the transition from

traditional methods to AI-based approaches [10]. Both the theoretical foundations of AI applied to maritime

environments and the evolution of its algorithms to improve pattern recognition and the identiﬁcation of

anomalous behaviors are discussed [9].

There is evidence of a trend in improvements in operational efﬁciency and the ability to process large

volumes of data [28]. However, the need to overcome challenges such as environmental variability and the

lack of labeled data in certain maritime scenarios is also noted. All of this points to process optimization,

although gaps remain in achieving proper adaptation to real and complex conditions. The development of

hybrid models and multimodal data may help bridge these gaps [11].

OnBoard Knowledge Journal 2026, 2, 2

5 of 13

These studies agree that AI’s ability to integrate and analyze data from multiple sources (satellite images,

remote sensors, historical records) is fundamental to improving surveillance and security in coastal areas.

However, they emphasize that the success of these applications largely depends on the quality and quantity

of available data, which implies an investment in information collection and management infrastructures.

This is why many of the leading powerhouse countries invest large amounts in advancing these technologies

(Figure 1).

Figure 1. Countries with the largest private investment in artiﬁcial intelligence from 2013 to 2022 (USD).

Note: Chart showing the countries with the highest private investment in AI during the period from 2013 to 2022,

expressed in billions of U.S. dollars (USD). The data reﬂects the growth and geographical distribution of resources

allocated to the development of AI technologies globally. Taken from [19].

The reviewed studies emphasize the transformative potential of AI in maritime surveillance and security,

while highlighting the importance of addressing the challenges inherent to its operational implementation.

While modern algorithms can outperform traditional methods in accuracy, challenges such as managing

false results, adapting to changing conditions, and the need for continuous model training still persist. The

theoretical review suggests that the future of AI in naval operations will be marked by the development

of hybrid models that combine different machine learning techniques to achieve greater robustness and

adaptability [26].

Another relevant topic in the review pertains to AI techniques applied to surveillance and recognition.

Fourteen contributions were found in the literature reviewed, providing a general overview of the techniques

that have been developed and their usefulness. Deep learning, convolutional neural networks (CNN),

and other machine learning models for object recognition, anomaly detection, and real-time maritime data

analysis are part of the offering [16]. Among the issues addressed are the more precise identiﬁcation of illegal

vessels, the development of illicit activities, and atypical behaviors that may occur. This points to an increase

in the effectiveness of surveillance and control.

The use of advanced algorithms has enhanced the ability of systems to process satellite images, sensor

data, and real-time videos. However, the effectiveness of these methods largely depends on the quality

and quantity of available data, as well as the capacity to adapt to different operational environments. It is

recommended to continue investigating the optimization of these models and their validation in real-world

scenarios [5].

On the other hand, a high effectiveness of AI was found when integrated with existing surveillance

technologies such as radars, satellites, remote sensors, and autonomous vehicles (UAVs), etc. At this point,

the combination of data from different mechanisms helps to deﬁne a more complete and detailed image of

the situation in real time, reducing the margin of error in decision-making [18]).

OnBoard Knowledge Journal 2026, 2, 2

6 of 13

In general, the contributions studied reinforce the premise that the integration of AI with existing

technologies not only improves the resolution and speed of detection but also optimizes resource management.

The synergy between various technological platforms is crucial for developing robust surveillance systems,

although standardized protocols are needed to ensure interoperability between disparate systems.

The review also highlighted the importance of early warning systems and threat prediction. Seven

contributions found show how AI-based models allow for predicting vulnerabilities and special behaviors in

real time, facilitating early threat detection, from illicit activities to adverse environmental events [4]. The

application of big data techniques and predictive analytics contributes to the development of early warning

systems that can prevent critical incidents in coastal areas [11] (Figure 2).

Figure 2. Explorer, a Saildrone (autonomous sailboat) that operates without a crew.

Note: Explorer a Saildrone (unmanned autonomous sailboat), during tests conducted in the Persian Gulf on June 26,

2022. This vehicle is part of the United States Navy’s technological push to strengthen its strategic presence in the face of

growing global competition, particularly against China [14;17].

Another approach found in the reviewed contributions relates to the use and practical applications in

naval forces, where AI is used to optimize routes, improve incident response, and increase security at ports

and maritime borders [3]. A positive impact on the efﬁciency of naval operations is observed, thanks to the

integration of AI systems that facilitate real-time decision-making.

The practical application of AI in coastal defense and security demonstrates improvements in operability

and response capability to threats. However, the transition from experimental models to robust operational

systems requires overcoming technical and logistical challenges, as well as adapting existing military proto-

cols. Evidence suggests that the success of these implementations depends both on technological innovation

and on the training and updating of operatives [23].

A ﬁnal approach found is characterized by the treatment of ethical, legal, and cybersecurity aspects. A

growing trend is evident in addressing challenges such as the use of AI in terms of privacy, data protection,

and legal compliance. In terms of national security, the issue becomes more delicate, making this topic one of

great importance for the naval context.

In general, it was identiﬁed that the evolution of AI has allowed the development of models and

algorithms that, when applied to the maritime environment, open new possibilities for coastal surveillance

and security. Studies like "Artiﬁcial intelligence applications in coastal and marine environments" and "The

challenge of artiﬁcial intelligence for sea security" emphasize the transition from traditional methods to

AI-based approaches, highlighting both technological advancements and inherent challenges (Figure 3).

OnBoard Knowledge Journal 2026, 2, 2

7 of 13

Figure 3. Approximate size comparison with the US Navy’s USV Sea Hunter.

Note: The image shows an approximate comparison between the USV Sea Hunter (USA) and the JARI-USV-A (China)

[20].

These ﬁndings indicate that the theoretical foundation and technological advances in AI are enabling

the resolution of complex problems in the naval domain. Following the research question, it is demonstrated

that fundamental AI applications (such as image processing, data analysis, and pattern recognition) lay the

groundwork for developing systems that enhance operational effectiveness in maritime surveillance and

security.

Other reviewed studies, such as those by [10], agree that technological evolution is a key factor, though

they emphasize the need to adapt these advances to real operational environments. There is a convergence

in the literature regarding the importance of data quality and model scalability, aspects that are similarly

addressed across multiple articles.

As theoretical implications, emphasis is placed on the need to develop hybrid models and integrate

various AI techniques to optimize decision-making in complex contexts. From a practical perspective,

technological advancements can translate into signiﬁcant improvements in surveillance and the ability to

respond to threats, although implementation requires adaptation to environmental and operational variables.

An important limitation is the challenge of managing large volumes of data, adapting to dynamic conditions,

and the need for robust infrastructures.

The use of deep learning algorithms, convolutional neural networks, and machine learning models

for image processing, anomaly detection, and pattern recognition in maritime environments is highlighted.

Articles such as "Automatized marine vessel monitoring from Sentinel-1 Data Using CNN" and "Deep

Learning Models for Real-Time Threat Detection in Coastal Waters" demonstrate the effectiveness of these

methods.

The ﬁndings show that the application of advanced AI techniques signiﬁcantly improves accuracy in

identifying suspicious activities and object recognition, which is crucial for surveillance and reconnaissance

in naval operations. This answers the research question by demonstrating that, by improving detection

accuracy, AI enhances operational effectiveness and security.

Coherence is observed in the literature, as studies, including [3], highlight the ability of these techniques

to process real-time data and reduce errors in detection. The comparison indicates that, although there are

differences in the implementation and performance of algorithms, the consensus is that these techniques

form the core of AI applications in the naval domain.

Regarding theoretical implications, there is an opportunity to integrate supervised and unsupervised

learning models to improve the robustness of systems. The implementation of these models can also translate

into smarter and more proactive surveillance systems, optimizing resources and reducing response times.

The challenges include dependence on large volumes of labeled data, variability in data quality, and the need

to validate models in real-world scenarios.

OnBoard Knowledge Journal 2026, 2, 2

8 of 13

The importance of merging AI with traditional surveillance technologies, such as radars, sensors,

satellites, and UAVs, was identiﬁed. Studies such as "Leveraging AI/ML for Enhanced Maritime Domain

Awareness" and "AI-enhanced Satellite Imaging for Coastal Surveillance" demonstrate the beneﬁts of this

integration.

This leads to the premise that combining technologies allows for leveraging information from various

sources, improving the ability to detect and respond to threats in real time. In relation to the research question,

technological integration translates into greater operational effectiveness, as it allows for a more complete

and accurate view of the maritime environment.

On the other hand, the literature shows consistency in the importance of interoperability between

systems; several studies highlight that the fusion of data from different sensors increases reliability and

reduces uncertainty in detection. The comparison shows that, although implementation varies, the consensus

is that the synergy between AI and traditional technologies is an essential component in modernizing naval

surveillance [15].

One theoretical implication points to the need to develop data fusion frameworks and communication

protocols between heterogeneous systems [29]. Integration facilitates a more coordinated and efﬁcient

response, which can lead to a reduction in response times to incidents. Barriers include compatibility issues,

high implementation costs, and the need for continuous updates to technological infrastructure.

Studies were also identiﬁed that point to the use of predictive models and real-time analytics techniques

for early detection of threats and vulnerabilities in coastal areas. Examples such as "AI-Based Anomaly

Detection in Maritime Trafﬁc" and "Predictive Analytics for Coastal Security Using AI" demonstrate the

ability to anticipate critical situations.

The ﬁndings indicate that the application of AI-based early warning systems allows for the identiﬁca-

tion of anomalous behaviors and the prediction of potential threats, facilitating preventive interventions.

This answers the research question by showing that prediction and prevention are key applications of AI,

improving operational effectiveness by anticipating incidents.

The review shows that various studies have obtained promising results in reducing false results and

improving predictive accuracy. There is a consensus that the integration of big data and advanced detection

algorithms is fundamental for establishing robust early warning systems [25].

A theoretical implication identiﬁed is the need to improve predictive models by incorporating contextual

variables and continuous learning. Notable restrictions include dependence on the quality and availability of

real-time data, as well as the possibility of false results that could generate unnecessary alarms.

On the other hand, practical applications of AI in naval operations were found, such as route optimiza-

tion, maritime trafﬁc prediction, and improvement in strategic decision-making. Studies such as "Smart Ports

and AI-Based Security Measures" and "Maritime Trafﬁc Prediction using AI Algorithms" illustrate real use

cases and the integration of AI in operational environments.

The ﬁndings indicate that the incorporation of AI in the daily operations of naval forces and ports not

only improves security but also optimizes resources and processes, increasing effectiveness in responding

to threats. In the context of the research, it is demonstrated that the practical application of AI is crucial for

transforming security and defense strategies in the maritime domain.

The reviewed literature shows consistent results regarding the improvement of operational efﬁciency

[8], although some studies highlight challenges in the integration and scalability of solutions. It is observed

that, while certain case studies report success in implementation, others indicate the need for operational

adjustments to adapt to dynamic contexts.

The ﬁndings support the formulation of theoretical models (theoretical implication) that explain the

relationship between intelligent automation and improved operational decision-making. In practice, this leads

to the adoption of AI-based solutions, which could translate into safer and more efﬁcient naval operations,

optimizing resource allocation and improving real-time coordination. Challenges such as resistance to change,

the need for specialized training, and the adaptation of pre-existing infrastructures to new technologies are

highlighted.

OnBoard Knowledge Journal 2026, 2, 2

9 of 13

In terms of ethical, legal, and cybersecurity aspects, the studies emphasize the importance of addressing

ethical, legal, and cybersecurity issues in the implementation of AI systems in naval operations. Articles such

as "Enhancing Port and Maritime Cybersecurity Through AI" and "Legal and Ethical Challenges of AI in

Naval Operations" highlight the need for regulatory frameworks and risk mitigation strategies.

These ﬁndings indicate that, although AI offers signiﬁcant operational advantages, its adoption in

the naval domain must be accompanied by policies that ensure ethical, safe, and legally compliant use.

Regarding the research question, it is evident that the development of intelligent systems must be balanced

with safeguards that protect both the integrity of operations and the rights and safety of users.

The literature shows a consensus on the need to integrate cybersecurity measures and establish speciﬁc

regulations for the use of AI in sensitive contexts. Some studies emphasize the risks associated with the

vulnerability of these systems, while others propose integrated solutions combining advanced technology

and robust regulations [29].

From a theoretical perspective, the results call for the development of theoretical frameworks that

integrate technological aspects with ethical and legal considerations, contributing to the creation of evidence-

based policies. The implementation of AI systems in naval operations should be accompanied by cybersecu-

rity strategies and updates to legal regulations, ensuring responsible and secure deployment.

Gaps in current legislation and challenges in implementing uniﬁed protocols are identiﬁed, which may

limit widespread adoption and interoperability of solutions [23].

At this point, it is pertinent for the research to list successful cases of AI use in naval operations

worldwide:

•

USV Sea Hunter (USA). [12]

Laser weapons against drones. [13]

Chinese unmanned vessel JARI-USV-A. [27]

Mini reconnaissance drone with FLIR system. [22]

Explorer - Unmanned Saildrone. [24]

Unmanned marine drone. [2]

DARPA Submarine Drone Project. [7]

All of these cases are subjects of study, and while they have already shown efﬁcient and promising

results for operations, it is important to note that each one has particular characteristics. Based on these,

adjustments are being made to achieve the required productivity.

5. Results

The review of the 35 articles presents a promising outlook on the application of AI in naval operations.

Each of the topics covered contributes integrally to answering the research question, highlighting both

technological advancements and the ongoing challenges in this ﬁeld. In summary, the ﬁndings indicate

that AI has far-reaching applications, ranging from detection and recognition of threats to the integration

of advanced technologies and predictive systems that signiﬁcantly improve operational effectiveness in

maritime surveillance and defense.

The results reveal that AI is fundamental in transforming traditional operational processes. Through

the use of advanced algorithms and machine learning, there has been an optimization in real-time decision-

making, allowing for quicker and more accurate responses to risk situations. This progress has led to

substantial improvements in the safety and efﬁciency of naval operations, facilitating the identiﬁcation and

classiﬁcation of threats on a large scale, such as unauthorized vessels, illicit activities, or adverse conditions

at sea.

Additionally, the review shows that the integration of AI with traditional technologies, such as radars,

satellites, and autonomous vehicles (UAVs), has enhanced detection resolution and speed, reducing the

margin of error in decision-making. This not only improves monitoring capabilities but also optimizes

resource management, enabling naval forces to operate more efﬁciently and with reduced human and

material resource use.

OnBoard Knowledge Journal 2026, 2, 2

10 of 13

The application of predictive models based on AI has emerged as a crucial tool for predicting threats and

early identiﬁcation of anomalies, such as suspicious maritime trafﬁc patterns or sudden changes in coastal

environments. This has facilitated the implementation of early warning systems, enabling prevention of

critical incidents and planning of proactive responses, thereby improving operational security in vulnerable

coastal areas.

Despite these advancements, the studies also conﬁrm that the quality and quantity of available data

remain determining factors for the success of AI applications. Many of the reviewed studies emphasize that

the lack of labeled data, variable environmental conditions, and the diversity in operational settings are

persistent challenges that limit the effectiveness of AI systems in real-world scenarios. This highlights the

need for signiﬁcant investment in infrastructure for data collection and management, as well as improving

the quality of the data.

Regarding theoretical and practical implications, the review shows that there is general consensus on the

potential of AI, but its current limitations are also recognized, such as the management of large data volumes,

the adaptability to changing conditions, and the need for continuous model training. The results suggest that

overcoming these challenges will require the development of hybrid models that combine various techniques

of supervised and unsupervised learning to enhance the robustness and adaptability of the systems.

The review also highlights that, while AI has enormous potential to improve naval operations, there

is a need to continue with interdisciplinary research, focusing on the integration of new technologies and

the development of robust regulatory frameworks to ensure the ethical and safe implementation of AI. This

approach will contribute to solving current issues related to resistance to change and the lack of standardized

protocols, which limit system interoperability.

6. Conclusions

Once the review of the 35 articles was completed, the task of identifying patterns in the results they

had yielded was carried out, organizing them into topics that could be found in common. This led to the

following questions: foundations and advancements of AI in naval operations; AI techniques applied in

surveillance and reconnaissance; integration of AI with existing surveillance technology; early warning

systems and threat prediction; practical implementation in security and defense strategies; ethical, legal, and

cybersecurity aspects.

Each of these topics contributes to the study, showing the real state of AI in naval operations. The

evolution of AI has laid the theoretical and technological foundations for transforming naval operations,

opening the door to more sophisticated surveillance systems, although challenges in adapting to real

conditions still persist.

The use of advanced algorithms (deep learning, neural networks, etc.) also signiﬁcantly improves

the detection and classiﬁcation of threats in maritime environments, optimizing accuracy and speed in

operational decision-making. It is important to note that the fusion of AI with traditional technologies such as

radars, satellites, and UAVs enhances surveillance by integrating multiple data sources in real time, although

it requires overcoming challenges in interoperability and technological updates.

On the other hand, AI-based predictive models enable the detection of anomalies and the prediction

of threats in coastal areas, facilitating proactive responses and improving operational security, largely

depending on the quality and availability of data. Consequently, the direct application of AI in route

optimization, maritime trafﬁc prediction, and strategic decision-making demonstrates improvements in

operational efﬁciency and security, although its full integration still faces operational and adaptation barriers.

Making a more speciﬁc landing in consideration of technologies that could be efﬁcient for national

operations, it is important to add that the implementation of the Black Hornet system in the Colombian Navy

would represent a signiﬁcant advancement in naval surveillance, reconnaissance, and maritime security

operations. This exploration nanodrone, developed by Teledyne FLIR, is a key tool for improving terrain

analysis in maritime and coastal environments, allowing naval units to gather real-time intelligence without

exposing personnel to unnecessary risks.

OnBoard Knowledge Journal 2026, 2, 2

11 of 13

Its compact size, silent ﬂight capability, and live video transmission make it ideal for maritime inter-

diction operations, patrolling hard-to-reach areas, and supporting special forces units in boardings and

amphibious reconnaissance missions. Additionally, the Black Hornet can be integrated with other AI systems

for automated image processing and analysis, facilitating threat identiﬁcation and decision-making in opera-

tions against drug trafﬁcking, piracy, and other illicit activities in the Caribbean Sea and the Paciﬁc Ocean.

With this technology, the Colombian Navy strengthens its operational capacity and its adaptation to modern

warfare based on autonomous systems and real-time data analysis.

Along the same lines, it is also relevant to consider the implementation of laser weapon systems with AI

in the Colombian Navy, which represents a key advancement in defense against drones and unmanned aerial

threats. Inspired by technology used by the U.S. Navy, this innovation enables faster and more accurate

neutralization of hostile targets, optimizing security in naval operations.

These systems can detect, track, and eliminate reconnaissance or attack drones, protecting naval bases,

surface units, and strategic maritime zones in Colombian territory. In a scenario where Organized Armed

Groups (GAOs) and drug trafﬁcking networks are seeking to modernize their tactics with drones for espionage

or attacks, the integration of laser weapons with AI would provide a crucial advantage in protecting ships,

maritime and riverine lines. Its implementation would enhance security in Colombia’s rivers, where these

vessels play a key role in the ﬁght against drug trafﬁcking, illegal mining, and armed groups. With this

technology, the Colombian Navy would consolidate the development of an intelligent, modern naval and

river defense system, aligned with new maritime and territorial security trends.

All of the above leads to a ﬁnal point: the adoption of AI in the naval domain presents critical challenges

in terms of ethics, legality, and cybersecurity, highlighting the need to develop regulatory frameworks and

robust strategies to ensure responsible and safe use of the technology.

The development of this review exercise allows for a synthesized presentation of the state of AI regarding

its usefulness in naval operations, with a particular focus on the utility of AI-based technology for recognition

within naval prevention and security. Through a systematic reading, it provides insight into the technologies,

their usefulness, and the challenges that arise as we enter the AI era, maximizing its beneﬁts to optimize the

performance of naval operations.

While this study has contributed to the understanding of the integration of AI in naval operations, there

are several areas that warrant further exploration. Future research should focus on enhancing the robustness

and scalability of AI models used in naval environments. Speciﬁcally, the development of hybrid models

that combine both supervised and unsupervised learning techniques can offer improved adaptability to

dynamic maritime conditions and more accurate predictions in real-time scenarios. Additionally, more work

is needed to explore the integration of multi-modal data (e.g., satellite images, sensor data, historical records)

to improve the reliability and precision of AI systems in coastal surveillance and reconnaissance.

Another promising avenue for future research is the development of standardized protocols for interop-

erability between AI-driven systems and traditional surveillance technologies like radars, UAVs, and satellite

networks. Addressing these integration challenges will be critical in ensuring that disparate systems can work

together seamlessly, reducing the margin for error and improving operational effectiveness. Furthermore, the

ethical, legal, and cybersecurity concerns associated with the deployment of AI in sensitive military opera-

tions should be thoroughly examined. Researchers must work towards creating comprehensive regulatory

frameworks that balance technological advancements with responsible and secure usage, safeguarding both

national security and individual rights. Exploring these areas will be crucial in shaping the future of AI in

naval operations, ensuring it is both effective and ethically implemented.

Author Contributions: Torres, O.: Conceptualization, Methodology, Investigation, Resources, Funding acquisition.

Meneses, G.: Software, Visualization, Validation, Formal analysis, Writing – original draft. Vélez, J.: Data curation,

Writing – review & editing, Supervision, Project administration.

All authors have read and agreed to the published version of the manuscript. Please refer to the CRediT taxonomy for the

deﬁnitions of the terms. Authorship should be limited to those who have made substantial contributions to the reported

work.

Funding: This study did not receive external funding.

OnBoard Knowledge Journal 2026, 2, 2

12 of 13

Institutional Review Board Statement: Not applicable, since the present study does not involve human personnel or

animals.

Informed Consent Statement: This study is limited to the use of technological resources, so no human personnel or

animals are involved.

Conﬂicts of Interest: Under the authorship of this research, it is declared that there is no conﬂict of interest with the

present research.

References

1. Corchado, M. (2022). La brecha tecnológica en inteligencia artiﬁcial: Implicaciones para la seguridad nacional.

2. Debate, E. (2023). Sead 23: Así funciona la embarcación española no tripulada, un dron marino que examina la armada

con torpedos ligeros. Accedido: 18 de abril de 2023.

3. Dimitrov, T. (2024). Applying artiﬁcial intelligence for improving situational awareness and threat monitoring at sea

as key factor for success in naval operation. In Proceedings of the International Scientiﬁc and Practical Conference, volume 4,

pages 49–55.

4. Fannassi, Y., Ennouali, Z., Hakkou, M., Benmohammadi, A., Al-Mutiry, M., Elbisy, M. S., and Masria, A. (2023).

Prediction of coastal vulnerability with machine learning techniques, mediterranean coast of tangier-tetouan, morocco.

Estuarine, Coastal and Shelf Science, 291:108422.

5. Green, C. (2025). Determining safety risks for artiﬁcial intelligence/ machine learning (ai/ml) enabled systems.

Accedido: 26 de febrero de 2025.

6. Heras, J. (2023). La evolución de la inteligencia artiﬁcial: De deep blue a la autonomía militar. Revista de Tecnología y

Defensa, 15(3):45–58.

7. Infobae (2024). Drones submarinos equipados con inteligencia artiﬁcial ayudan a la marina de ee.uu. a buscar

amenazas. Accedido: 21 de junio de 2024.

8. Intelligence, I. (2022). Detección de pesca ilegal mediante aprendizaje automático: ¿automatización para el beneﬁcio

de empresas privadas o beneﬁcio genuino en el rastreo de embarcaciones oscuras? Accedido: 15 de septiembre de

2022.

9. las Heras, P. (2023). El reto de la inteligencia artiﬁcial para la seguridad y defensa. Global Affairs and Strategic Studies.

Accedido: 2025-06-09.

10. Masria, A. and Abouelsaad, O. (2025). Artiﬁcial intelligence applications in coastal engineering and its challenges – a

review. Continental Shelf Research, 286:105425.

11. Matiz-Rojas, A. H. and Fernández-Camargo, J. A. (2023). Del uso de la inteligencia artiﬁcial como medio y método en

los conﬂictos armados. Revista Cientíﬁca General José María Córdova, 21(42):525–549.

12. Navy, U. S. (2022). Sea hunter unmanned surface vessel: Advancements and operational highlights. Accedido:

2025-06-09.

13. News, C. (2025). La marina de ee. uu. utiliza inteligencia artiﬁcial para optimizar armas láser contra drones.

Accedido: 26 de febrero de 2025.

14. Post, T. D. (2022). Us navy expediting drone ship development to keep up with china. Accedido: 2025-06-09.

15. Queirolo Pellerano, F. (2019). Sistemas de armas autónomos letales (laws): Reﬂexiones para un debate. Revista Política

y Estrategia, 134:147–170.

16. Reis, F., Silva, M., and Costa, P. (2024). Aplicaciones de la inteligencia artiﬁcial en la vigilancia y reconocimiento

marítimo: Un análisis de las técnicas actuales. Revista Internacional de Tecnología Naval, 32(4):215–229. Accedido:

2025-06-09.

17. Sharp, D. (2022). Armada de ee.uu. apuesta a la tecnología ante amenaza china. Los Angeles Times en Español.

Accedido: 2025-06-09.

18. Solutions, T. (2023). Leveraging ai/ml for enhanced maritime domain awareness. Accedido: 2 de octubre de 2023.

19. Statista (2025). Países con más inversión privada en inteligencia artiﬁcial. Accedido: 2025-06-09.

20. Sutton, H. I. (2022). China builds world’s largest uncrewed warship. Accedido: 2025-06-09.

21. Sweet, A. (2023). La inteligencia artiﬁcial como herramienta estratégica en operaciones militares. Journal of Military

Technology, 12(4):67–79.

22. Systems, F. (2025). Black hornet 4. Accedido: 26 de febrero de 2025.

23. Thorne, G. (2020). The legal and ethical challenges the royal navy may face when deploying lethal autonomous

surface vessels into the maritime battlespace. Accedido: 26 de febrero de 2025.

24. Times, L. A. (2022). Armada de ee.uu. apuesta a la tecnología ante amenaza china. Accedido: 2 de agosto de 2022.

OnBoard Knowledge Journal 2026, 2, 2

13 of 13

25. Tiwari, S. P., Chaturvedi, S. K., Adhikary, S., Banerjee, S., and Basu, S. (2021). Automatized marine vessel monitoring

from sentinel-1 data using convolution neural network. In 2021 IEEE International Geoscience and Remote Sensing

Symposium (IGARSS), pages 1311–1314.

26. UNESCO (2023). Global education monitoring report summary 2023: Technology in education: A tool on whose

terms? Accedido: 2025-06-09.

27. Xataka (2024). Jari-usv-a: El nuevo buque de guerra autónomo de china. Accedido: 2025-06-09.

28. Xataka (2025). Así es «orca», el nuevo barco militar chino sin tripulación y hasta arriba de armamento. Accedido: 15

de marzo de 2025.

29. Yu, J. (2024). Las implicaciones estratégicas de la ia en la seguridad marítima. Accedido: 2025-06-09.

Authors’ Biography

Oscar Alejandro Torres Salcedo Marine Infantry Lieutenant, Escuela Naval de Cadetes "Almi-

rante Padilla".

Ginary Sarmiento Meneses Frigate Lieutenant (Surface Specialty), Escuela Naval de Cadetes

"Almirante Padilla".

Juan David Vélez Restrepo Ship Lieutenant, Escuela Naval de Cadetes "Almirante Padilla".

Disclaimer/Editor’s Note: Statements, opinions, and data contained in all publications are solely those of the individual

authors and contributors and not of the OnBoard Knowledge Journal and/or the editor(s), disclaiming any responsibility

for any injury to persons or property resulting from any ideas, methods, instructions, or products referred to in the

content.