INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025

Application of AI in the Construction Industry: A Systematic Review

Bulama Abubakar ¹, Abdulmumini Imam Ibrahim^2,3, Muhammad Zaid Sagir¹, Ali Bulama Gambo ¹

Usman Babagana^4,5

¹Department of Civil Engineering, FE & IT, Integral University, 226026 Lucknow, India

²Department of Computer Science and Engineering, Integral University, 226026 Lucknow, India

³Department of Computer Science, Ramat Polytechnic, 600251 Maiduguri, Nigeria

⁴Department of Electrical Engineering, FE & IT, Integral University, 226026 Lucknow, India

⁵ Department of Electrical Engineering, Ramat Polytechnic, 600251 Maiduguri, Nigeria

DOI : https://doi.org/10.51583/IJLTEMAS.2025.1412000035

Received: 17 December 2025; Accepted: 24 December 2025; Published: 31 December 2025

ABSTRACT

The construction industry continues to face persistent challenges such as cost and time overruns, safety risks,

low productivity, and labor shortages. Despite its economic significance, the sector remains one of the least

digitized globally, limiting its ability to address these challenges effectively. Artificial Intelligence (AI), as an

advanced digital technology, has demonstrated the potential to transform traditional construction practices,

similar to its impact on manufacturing, retail, and telecommunications.

This study presents a systematic literature review of AI applications in the construction industry, aiming to

identify dominant application areas, commonly adopted AI techniques, and existing research gaps. The review

was conducted in accordance with the PRISMA 2020 guidelines to ensure transparency and methodological

rigor. Relevant peer-reviewed studies published between 2015 and 2025 were identified through structured

searches of Scopus, Web of Science, Science Direct, and Google Scholar. Over 200 records were initially

retrieved. After duplicate removal and multi-stage screening, 15 studies met the inclusion criteria and were

selected for in-depth qualitative analysis.

The findings indicate that AI has been applied across key construction domains, including structural health

monitoring, safety and risk management, design and pre-construction planning, sustainability, waste

management, and on-site robotics. Machine learning and neural network-based approaches were the most

frequently used techniques. While the reviewed studies demonstrate AI’s strong potential to improve efficiency,

safety, and sustainability in construction projects, significant challenges remain, particularly regarding data

quality, lack of standardization, system integration, and user trust. This review provides a consolidated overview

of AI applications in construction and outlines critical directions for future research and industry adoption.

Keywords: Artificial intelligence; Construction industry; Construction project management; Systematic review;

PRISMA

INTRODUCTION

Artificial Intelligence (AI) refers to computer systems designed to perform tasks that normally require human

intelligence, including learning, reasoning, pattern recognition, and decision-making. By analysing large

volumes of structured and unstructured data, AI systems can identify complex patterns and generate insights that

support informed and timely decisions. Through continuous learning, these systems can improve performance

and accuracy over time [1].

www.ijltemas.in

Page 399

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025

Construction projects are inherently complex, involving significant financial investments, multiple stakeholders,

and highly interdependent activities. These characteristics make effective management challenging when relying

solely on traditional tools and human judgement. Consequently, construction projects worldwide frequently

experience schedule delays, cost overruns, safety incidents, and low productivity levels. To address these

persistent challenges, the construction industry has increasingly explored Industry 4.0 technologies, particularly

AI, to enhance project planning, monitoring, and performance optimization [2].

Despite this growing interest, construction remains one of the least innovative and least digitalized industries

globally. Compared with sectors such as manufacturing and telecommunications, construction productivity has

grown at an estimated rate of only about 1% annually over the past two decades [3]. This slow growth is largely

attributed to the industry’s fragmented structure, project-based operations, and reliance on traditional practices.

Recent advancements in AI offer opportunities to overcome these limitations. AI can support predictive

analytics, optimize scheduling and cost estimation, automate hazardous and repetitive tasks, and improve safety

management. By analyzing data from design models, project schedules, site sensors, and images, AI systems

can predict project outcomes and support proactive decision-making. Furthermore, AI-driven robotics and

automation can reduce human exposure to high-risk activities, thereby improving site safety and consistency

[4,5].

Although research on AI in construction has increased significantly, existing studies are often fragmented,

focusing on specific technologies, applications, or regional contexts. This fragmentation makes it difficult to

obtain a comprehensive understanding of how AI is applied across the construction project lifecycle. To address

this gap, this study adopts the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)

2020 guidelines to systematically identify, screen, and synthesize relevant literature on AI applications in the

construction industry.

The objectives of this study are:

1. To systematically review existing literature on the application of Artificial Intelligence in the

construction industry.

2. To identify dominant AI application areas and highlight key research gaps for future studies

METHODOLOGY

This study employed a systematic literature review approach to examine AI applications in the construction

industry. The review process followed the PRISMA 2020 guidelines to ensure transparency, consistency, and

reproducibility.

Search Strategy

A comprehensive literature search was conducted using four academic databases: Scopus, Web of Science,

Science Direct, and Google Scholar. Scopus and Web of Science were selected as primary sources due to their

extensive coverage of high-quality peer-reviewed journals, while Science Direct and Google Scholar were used

to enhance coverage and validate relevant publications.

The search strategy combined AI-related keywords (artificial intelligence, AI, machine learning, deep learning,

computer vision, robotics) with construction-related terms (construction industry, construction management,

project planning, safety, cost estimation, scheduling, design optimization, building information modelling

(BIM)). Searches were limited to titles, abstracts, and keywords. The publication period was restricted to 2015–

2025 to capture recent technological development.

Inclusion criteria:



Peer-reviewed journal articles and conference proceedings

www.ijltemas.in

Page 400

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025



Studies explicitly addressing AI applications in construction or closely related AEC domains

Publications written in English

Studies published between 2015 and 2025

Exclusion criteria:



Editorials, opinion papers, and grey literature

Duplicate records

Studies not directly related to the construction industry

Studies addressing general digital tools without a clear AI component

Studies with insufficient methodological detail or unclear outcomes

Study Selection and Data Extraction

The initial search identified 212 records. After removing duplicates, 180 records remained for title and abstract

screening. Following this screening, 132 records were excluded due to lack of relevance. Full-text assessment

was conducted on 48 articles, of which 33 were excluded because they lacked a clear construction focus, did not

explicitly apply AI techniques, or exhibited weak methodological quality. Ultimately, 15 studies met all

inclusion criteria and were selected for qualitative synthesis.

For each selected study, data were extracted on publication year, country, AI techniques used, application areas,

data sources, and key findings.

Figure 1. PRISMA 2020 flow diagram illustrating the study selection process.

RESULT

The results of the systematic review are based on the qualitative analysis of 15 selected studies. These studies

demonstrate the application of AI across multiple construction domains, including structural health monitoring,

safety and risk management, design and pre-construction planning, sustainability, waste management, and on-

site robotics.

www.ijltemas.in

Page 401

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025

Machine learning and artificial neural networks were the most frequently adopted AI techniques, followed by

deep learning, computer vision, reinforcement learning, and digital twin technologies. A significant proportion

of studies focused on safety-related applications. For example, neural network-based models were used for

structural damage detection, while computer vision systems enabled real-time monitoring of personal protective

equipment compliance and hazardous site conditions.

Design and pre-construction planning applications were also prominent. Several studies reported that AI-enabled

BIM and sensor integration reduced design conflicts and improved coordination during early project stages.

More recent studies emphasized emerging themes such as explainable AI, human-centred AI, and sustainability,

highlighting the importance of transparency, user trust, and environmental performance.

Overall, the findings indicate increasing adoption of AI technologies across construction project phases, although

most applications remain at pilot stages.

Table 1. Summary of selected studies on AI applications in the construction industry

S/N Author (Year) AI Technologies

Construction

Area

Key Findings / Application

1

2

3

Hooda et al. Artificial

(2021) Networks (ANN)

Neural Structural

Monitoring

The project involves the automated

detection of structural damage in

building systems.

Owolabi et al. AI-enabled BIM, Sensor Design and Pre- Integration of sensors with BIM

(2022)

Fusion

construction

significantly

conflicts.

reduced

design

Chen & Ying Metaheuristic

Evolutionary

Review

I have reviewed over 30 years of AI

development in AEC, which shows a

shift from rule-based systems to deep

learning.

(2022)

Programming

Algorithms (MPA), ML,

DL, ANN

4

5

6

7

8

Regona et al. Machine Learning, Deep Industry

(2022) Learning, Big Data Adoption

The study identified a lack of data

standards as a major barrier to global

AI adoption.

Imran et al. Computer

Vision, Safety

Language Productivity

and The system has enabled real-time

PPE detection and automation of

hazardous construction tasks.

(2022)

Natural

Processing

Pan & Zhang Deep

Learning,

IoT, Smart

Construction

Identified six integration clusters

forming a digital backbone for BIM–

AI systems.

(2023)

Digital Twins

Management

Rafsanjani

Nabizadeh

(2023)

& Human-Centred

AI, Human–AI

The emphasis was on AI systems that

support, rather than replace, human

decision-making.

NLP, Machine Reading

Interaction

Ivanova et al. Digital Twins, Genetic Crane Safety

(2023) Algorithms

Reduced collision risks through real-

time site simulation.

www.ijltemas.in

Page 402

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025

9

Adeloye et al. Explainable AI, IoT

(2023)

Trust

Adoption

and Demonstrated that explainable AI

improves user trust and acceptance.

10

Datta

(2024)

et

al. Convolutional

Recurrent

and Project

Neural Forecasting

Used RNN models to predict project

recovery after schedule delays.

Networks

11

Feng

et

al. Reinforcement Learning

Sustainability

Optimised HVAC operations to

(2024)

significantly

emissions.

reduce

carbon

12

13

Adewale et al. IoT,

Digital

Twins, Waste

Management

Reported up to 40% reduction in

construction site waste.

(2024)

Reinforcement Learning

Hriday

Rehman

(2025)

& Genetic

Algorithms, Cost Performance Quantified measurable cost savings

NLP, Ensemble Models

linked to increased AI adoption.

14

15

Adebayo et al. Predictive Analytics

(2025)

Industry Trends

On-site Robotics

Analysed the transition of the AEC

sector into the Fourth Industrial

Revolution.

Ren & Kim Sense–Think–Act

Defined an operational framework

for autonomous construction robots.

(2025)

Framework, ML, RL

DISCUSSION

This section critically discusses the findings of the systematic review by synthesising evidence from the selected

studies, comparing AI techniques across application areas, and highlighting methodological limitations and

research gaps. In line with the reviewer’s suggestions, the discussion moves beyond description to analytical

comparison and evaluation.

Distribution of AI Applications Across Construction Phases

The reviewed studies demonstrate that Artificial Intelligence is being applied across multiple phases of the

construction project lifecycle, including design and pre-construction planning, on-site operations, safety

management, sustainability, and post-construction monitoring. However, the distribution of research is uneven.

A large proportion of studies focus on on-site safety, risk management, and monitoring, while fewer studies

address strategic planning, procurement, and long-term asset management.

This imbalance suggests that AI adoption in construction is currently driven by problems that are highly visible

and data-rich, such as accident prevention and site monitoring. In contrast, areas that require integrated

organisational data and long-term decision-making remain underexplored, indicating a clear opportunity for

future research.

Comparison of AI Techniques and Their Effectiveness

Across the selected studies, machine learning (ML) and artificial neural networks (ANNs) were the most

frequently applied AI techniques. These methods were particularly effective in pattern recognition tasks, such

as structural health monitoring, safety compliance detection, and project performance forecasting. For example,

ANN-based models demonstrated strong performance in detecting structural damage, while recurrent neural

networks were effective in predicting schedule recovery patterns.

More advanced techniques, such as reinforcement learning (RL) and digital twins, were primarily applied in

sustainability and smart construction management contexts. While these approaches showed promising results—

www.ijltemas.in

Page 403

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025

such as energy optimisation and waste reduction—their implementation often relied on simulated or controlled

environments. This raises concerns about their scalability and reliability under real-world construction

conditions. Overall, simpler ML-based models appear more mature for industry deployment, whereas advanced

AI systems remain largely experimental.

Emerging Themes: Explainable and Human-Centered AI

Recent studies have begun to shift attention from purely technical performance toward human-centered and

explainable AI (XAI). The reviewed literature highlights that lack of transparency remains a major barrier to AI

adoption in construction. Explainable AI approaches were found to significantly improve user trust, particularly

among construction professionals who rely heavily on experience-based decision-making.

Human-centered AI frameworks argue that AI should augment rather than replace human expertise. This

perspective is particularly important in safety-critical applications, where over-reliance on opaque AI systems

could introduce new risks. However, despite growing interest, empirical evaluations of XAI and human-centered

approaches remain limited, indicating a gap between conceptual frameworks and practical implementation.

Sustainability and Environmental Performance Implications

AI applications targeting sustainability demonstrated measurable benefits, including reduced energy

consumption, lower carbon emissions, and significant reductions in construction waste. Reinforcement learning-

based energy management systems and digital twin-enabled waste tracking systems showed particularly strong

potential.

Nevertheless, most sustainability-focused studies were conducted as case studies or simulations, often using

limited datasets. As a result, their findings may not be fully generalizable across different project types or

geographic regions. Future research should focus on large-scale, longitudinal studies to validate the

environmental benefits of AI in diverse construction contexts.

Methodological Limitations in Existing Studies

Despite promising outcomes, the reviewed literature exhibits several methodological limitations. Many studies

rely on small, project-specific datasets, which restricts model generalization. Additionally, inconsistent data

formats, lack of standardized benchmarks, and limited reporting of model validation procedures reduce

reproducibility.

Another key limitation is that a significant number of studies remain at the pilot or prototype stage, with few

demonstrating sustained implementation in real construction projects. This highlights a gap between academic

research and industry adoption, reinforcing the need for stronger collaboration between researchers and

practitioners.

Implications for Industry Practice and Policy

From a practical perspective, the findings suggest that AI can deliver tangible benefits in construction when

supported by high-quality data, standardized workflows, and user training. Industry stakeholders should

prioritize AI applications with proven reliability, such as safety monitoring and predictive analytics, while

gradually integrating more advanced systems.

From a policy standpoint, there is a need for data governance frameworks, interoperability standards, and ethical

guidelines to support responsible AI deployment. Policymakers can play a critical role in facilitating data sharing

and encouraging adoption through regulatory support and incentives

www.ijltemas.in

Page 404

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025

CONCLUSION

his study systematically reviewed recent literature on the application of Artificial Intelligence in the construction

industry using PRISMA 2020 guidelines. The analysis of 15 selected studies shows that AI is increasingly

applied across multiple construction activities, including safety management, design and planning, sustainability,

waste reduction, and on-site automation.

While AI demonstrates strong potential to improve construction performance, its large-scale adoption remains

constrained by data-related, technical, and organizational challenges. Future research should focus on developing

standardized datasets, explainable AI systems, and long-term empirical studies that assess real-world

performance and implementation feasibility. Strengthening collaboration between researchers, industry

practitioners, and policymakers will be essential to fully realize AI’s benefits in the construction sector.

REFERENCES

1. Owolabi, J. D., Malagwi, D., Oyeyipo, O., Ola-Ade, E. O., & Tunji-Olayeni, P. F. (2022). Application

of artificial intelligence in the Nigerian building and construction industry. International Journal of

Advanced and Applied Sciences, 9(10), 33–39.

2. Silitonga, D. M., & Jin, O. F. (2024). Application of artificial intelligence in construction management:

A systematic literature review. Jurnal Inovasi Vokasional dan Teknologi, 23(3), 155–166.

3. Imran, C. A. B., Shakir, M. K., & Qureshi, M. A. B. (2022). Applications of artificial intelligence in

enhancing construction safety and productivity. The Asian Bulletin of Big Data Management, 2(1), 63–

74.

4. Yigitcanlar, T. (2021). Greening artificial intelligence for a sustainable planet: An editorial commentary.

Sustainability, 13(24), 13508. https://doi.org/10.3390/su132413508

5. Mohapatra, A., Mohammed, A. R., & Panda, S. (2023). Role of artificial intelligence in the construction

industry: A systematic review. International Journal of Advanced Research in Computer and

Communication Engineering, 12, 24–29.

6. Hooda, Y., Kuhar, P., Sharma, K., & Verma, N. K. (2021). Emerging applications of artificial intelligence

in structural engineering and construction industry. Journal of Physics: Conference Series, 1950(1),

012062. https://doi.org/10.1088/1742-6596/1950/1/012062

7. Datta, S. D., Islam, M., Sobuz, M. H. R., Ahmed, S., & Kar, M. (2024). Artificial intelligence and

machine learning applications in the project lifecycle of the construction industry: A comprehensive

review. Heliyon, 10(5), eXXXXX.

8. Ivanova, S., Kuznetsov, A., Zverev, R., & Rada, A. (2023). Artificial intelligence methods for the

construction and management of buildings. Sensors, 23(21), 8740. https://doi.org/10.3390/s23218740

9. Feng, Z., Ge, M., & Meng, Q. (2024). Enhancing energy efficiency in green buildings through artificial

intelligence. Journal name pending.

10. Hriday, M. S. H., & Rehman, A. (2025). Artificial intelligence and machine learning applications in

construction project management: Enhancing scheduling, cost estimation, and risk mitigation.

International Journal of Business and Economics Insights, 5(3), 30–64.

11. Adeloye, A. O., Diekola, O., Delvin, K., & Gbenga, C. (2023). Applications of artificial intelligence in

the construction industry: A review of observational studies. Applied Sciences Research Periodicals,

1(4), 28–38.

12. Adebayo, Y., Udoh, P., Kamudyariwa, X. B., & Osobajo, O. A. (2025). Artificial intelligence in

construction project management: A structured literature review of its evolution and future trends.

Digital, 5(3), 26. https://doi.org/10.3390/digital5030026

13. Adewale, B. A., Ene, V. O., Ogunbayo, B. F., & Aigbavboa, C. O. (2024). Application of artificial

intelligence in the sustainable building lifecycle: A systematic literature review. Buildings, 14, 2137.

https://doi.org/10.3390/buildings14122137

14. Abioye, S. O., Oyedele, L. O., Akanbi, L., Ajayi, A., Delgado, J. M. D., & Bilal, M. (2021). Artificial

intelligence in the construction industry: Present status, opportunities, and future challenges. Journal of

Building Engineering, 44, 103299. https://doi.org/10.1016/j.jobe.2021.103299

www.ijltemas.in

Page 405

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025

15. Pan, Y., & Zhang, L. (2023). Integrating BIM and AI for smart construction management: Current status

and future directions. Archives of Computational Methods in Engineering, 30(2), 1081–1110.

https://doi.org/10.1007/s11831-022-09774-2

16. Chen, H. P., & Ying, K. C. (2022). Artificial intelligence in the construction industry: Main development

trajectories and future outlook. Applied Sciences, 12(12), 5832. https://doi.org/10.3390/app12125832

17. Rafsanjani, H. N., & Nabizadeh, A. H. (2023). Towards human-centred artificial intelligence in the

architecture, engineering, and construction industry. Computers in Human Behavior Reports, 11, 100319.

https://doi.org/10.1016/j.chbr.2023.100319

18. Ren, Z., & Kim, J. I. (2025). The role of AI in on-site construction robotics: A state-of-the-art review

using

the

Sense–Think–Act

framework.

Buildings,

15(13),

2374.

https://doi.org/10.3390/buildings15132374

www.ijltemas.in

Page 406