Next Article in Journal
Soil Sharing and Equipment Operations Through Digitalization of Large-Scale Earthworks
Previous Article in Journal
Standardization of CAD Drawing Formats and GeoJSON-Based Processing for 3D Spatial Data Extraction of Underground Utilities
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Systematic Review

Integrating Artificial Intelligence and the Internet of Things in Cultural Heritage Preservation: A Systematic Review of Risk Management and Environmental Monitoring Strategies

by
Neeraparng Laohaviraphap
and
Tanut Waroonkun
*
Faculty of Architecture, Chiang Mai University, Chiang Mai 50200, Thailand
*
Author to whom correspondence should be addressed.
Buildings 2024, 14(12), 3979; https://doi.org/10.3390/buildings14123979
Submission received: 16 October 2024 / Revised: 27 November 2024 / Accepted: 13 December 2024 / Published: 15 December 2024
(This article belongs to the Section Architectural Design, Urban Science, and Real Estate)

Abstract

Heritage buildings are increasingly vulnerable to environmental challenges like air pollution and climate change. Traditional preservation methods primarily rely on periodic inspections and manual interventions and struggle to address these evolving and dynamic threats. This systematic review analyzes how integrating Artificial Intelligence (AI) and Internet of Things (IoT) technologies can transform cultural heritage preservation. Using the PRISMA guidelines, 92 articles from SCOPUS were reviewed, highlighting key risk management and environmental monitoring methodologies. The study found that while IoT enables real-time air quality and structural health monitoring, AI enhances data analysis, providing predictive insights. The combination of IoT and AI facilitates proactive risk management, ensuring more resilient conservation strategies. Despite the growing use of these technologies, adoption remains uneven, particularly in regions most impacted by climate change. The study identifies significant research gaps and proposes an innovative framework that leverages Heritage Building Information Modeling (H-BIM) and Digital Twin (DT) for continuous monitoring and predictive maintenance through a multi-step process, beginning with the digitalization of heritage assets using H-BIM, followed by the creation of real-time digital replicas via DT. By integrating advanced technologies, the framework offers a more adaptive and sustainable approach to preserving cultural heritage, addressing both immediate threats and long-term vulnerabilities. This research underscores the need for a global, technology-driven response to safeguard heritage buildings for future generations.

1. Introduction

Cultural heritage buildings are crucial symbols of historical and architectural significance but are increasingly threatened by environmental challenges, particularly climate change and air pollution [1,2,3]. Recent research has shifted focus from thermal comfort to air pollution and health-related issues, especially highlighted by the COVID-19 pandemic [4,5,6,7,8]. The United Nations (UN) has referred to this era as one of “global boiling”, emphasizing the increasing frequency and severity of climate-related events [9,10]. These events not only threaten public health but also accelerate the degradation of historic monuments. Research has shown a rapid pace of deterioration in heritage buildings due to climate fluctuations—such as increasing average temperatures and variations in temperature and relative humidity—and intense air pollution. Pollutants like CO2, PM2.5, SO2, volatile organic compounds (VOCs) and radon (Rn) contribute to erosion, discoloration, and structural vulnerabilities, affecting both exteriors and interiors and pose risks to occupants and visitors [3,11,12]. Studies by Oliveira et al. [13] and Broomandi et al. [14] highlighted the detrimental effects of air pollutants on the degradation of heritage structures in urban environments.
Developing areas face unique challenges in heritage preservation due to inadequate infrastructure and uncontrolled urban expansion [15,16]. Regions with stronger technological infrastructures can integrate advanced technologies into their heritage conservation efforts more easily. These regional disparities underscore the need for customized technological solutions that consider the unique environmental and cultural conditions of each area, ensuring that advanced technologies are both feasible and sustainable. In contrast, advanced technology can enhance heritage conservation through scalable, cost-effective, low-power solutions, particularly in resource-limited areas, by monitoring environmental changes and protecting cultural heritage [17].
Traditional preservation methods are increasingly ineffective against dynamic environmental challenges, necessitating standardized evaluation and more integrated, technology-driven approaches [17,18,19,20]. Integrated, tech-driven strategies are essential for enhancing resilience to environmental impacts and maintaining optimal preservation quality, as demonstrated by case studies from Huatzai Village in Taiwan [21], the University of Seville in Spain [19], and the Finnish Heritage Agency in Finland [20].
Current risk management strategies are often reactive, highlighting the need for proactive measures through advanced technologies. The integration of advanced technologies like Artificial Intelligence (AI) and the Internet of Things (IoT) presents a transformative shift in preservation practices, enabling real-time monitoring and predictive analytics. This allows for early detection of potential threats, facilitating timely intervention before irreversible damage occurs [22,23,24]. IoT provides real-time monitoring of environmental and structural health, while AI, through machine learning (ML) and deep learning (DL), facilitates efficient data analysis, object recognition, and classification [25,26].
The integration of AI and IoT in cultural heritage preservation has grown significantly over the past decade, with frameworks like Digital Twin (DT) and Building Information Modeling (BIM) enhancing monitoring capabilities. For instance, Hu et al. [22] proposed a novel DT framework that combines BIM, IoT, AI, and indoor positioning technologies for real-time indoor environment monitoring and visualization in educational buildings. Marzouk and Mohamed [27] developed an IoT and DL-based system to assess Indoor Air Quality (IAQ) in academic buildings. Moreover, Mishra et al. [28] reviewed state-of-the-art AI applications that assist manual visual risk inspections of large-scale architectural heritage. These advancements enhance the efficiency of preservation efforts and contribute to proactive risk management strategies.
Despite these technological advancements, most applications have been reactive, introduced after damage has occurred [28,29]. Proactive risk assessment is crucial for safeguarding heritage value, as AI and IoT facilitate earlier threat detection and more effective preservation strategies [30,31,32]. These technologies also support the Sustainable Development Goals (SDGs) by extending the lifespan of heritage structures and enhancing occupant well-being. The incorporation of smart sensors and IoT technology, coupled with AI and neural network algorithms, enables real-time monitoring of IAQ, allowing for prompt responses to any deterioration in air quality [30,33].
As environmental challenges intensify, the need for adaptive, technology-driven solutions grows [34,35]. The trend in heritage preservation and risk assessment publications shown in Figure 1 emphasizes the growing academic interest in these topics.
This systematic review aims to:
  • Analyze patterns and trends in the integration of AI and IoT technologies in cultural heritage preservation, focusing on risk management and environmental monitoring.
  • Identify key factors and methodologies in applying AI and IoT to improve air quality, structural health monitoring, and conservation outcomes.
  • Propose an innovative framework in heritage preservation that leverages advanced technologies for adaptive and proactive solutions to dynamic environmental challenges.

2. Materials and Methods

This study employed a systematic literature review (SLR) to meet the research objectives, following the guidelines provided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology [36]. A tailored protocol with clear inclusion and exclusion criteria was developed, using carefully selected keywords to ensure a comprehensive and unbiased review of global assessment criteria related to cultural heritage preservation. The PRISMA approach facilitated a structured, transparent, and replicable methodology, providing a thorough evaluation of relevant technologies for the preservation of cultural heritage buildings.

2.1. Database Search

The initial search strategy incorporated three databases: SCOPUS, ScienceDirect, and Web of Science (WoS). During the screening phase, we identified that all relevant articles from ScienceDirect and WoS were also indexed in SCOPUS.
SCOPUS was selected as the primary database to minimize redundancy and enhance clarity. This approach minimizes redundancy while ensuring comprehensive coverage of relevant literature across multiple major platforms. SCOPUS, indexing over 39,100 titles, provides extensive access to global and regional research, including emerging studies in fields such as environmental science and cultural heritage preservation. Furthermore, SCOPUS offers advanced tools for citation analysis and detailed author and institution profiling, thereby facilitating the identification of key trends and influential studies within the field [37,38,39].
The database’s breadth, precision in citation linking, and interdisciplinary scope make it the ideal choice for this systematic review, ensuring a thorough and relevant search of global strategies for cultural heritage preservation.

2.2. Inclusion and Exclusion Criteria of the Study

Explicit inclusion and exclusion criteria were defined to ensure the selected studies aligned with the research objectives (see Table 1). The initial screening targeted articles within the fields of Architecture, Engineering, Environmental Science, or Social Sciences. Each article needed to include the term “heritage building” along with additional keywords such as “risk assessment”, “air pollution”, “climate risk”, “IoT”, and “Artificial Intelligence”. Boolean operators were used to refine search results—for instance, “heritage building” AND “risk assessment”, “heritage building” AND “air pollution”, and “heritage building” AND “climate risk”. Only peer-reviewed articles in English were considered to maintain the quality and reliability of the sources. Non-English studies were excluded to avoid translation and interpretation challenges that could have affected the review’s accuracy and consistency.
In this research, the advanced queries were designed to capture relevant literature related to heritage buildings and their preservation. The search was conducted using the “TITLE-ABS-KEY” field, which targets the title, abstract, and keywords of each document. This ensures that the key concepts—such as heritage, risk assessment, air pollution, climate risk, artificial intelligence, and IoT—are prominently addressed in the retrieved articles.
The publication timeframe of 2014–2024, defined by the query “PUBYEAR > 2013 AND PUBYEAR < 2025”, includes publications published after 2013 and before 2025. This range was chosen to reflect a decade of significant advancements in the field of heritage preservation and risk assessment. This period follows the adoption of the Sustainable Development Goals (SDGs) in 2015, marking a global shift toward sustainability in various sectors, including cultural heritage. The 10-year span is appropriate as it captures the increased focus on these topics driven by key international agreements, such as the Sendai Framework and the Paris Agreement [40].
The search was further refined using the “LIMIT-TO” function, which allowed us to narrow the results to publications between 2013 and 2025, limited to journal articles (“ar”), published in English, and within specific subject areas including Engineering (“ENGI”), Environmental Science (“ENVI”), and Social Sciences (“SOCI”). We also filtered the results to include only articles from journals (“j”).
The search query, as summarized in Table 2, applied to SCOPUS, based on these inclusion and exclusion criteria, initially identified 583 relevant documents: 314 from the search “heritage building AND risk assessment”, 80 from “heritage building AND air pollution”, 117 from “heritage building AND climate risk”, 51 from “heritage building AND Artificial Intelligence”, and 21 from “heritage building AND IoT”. After detecting 79 duplicate entries, they were removed using the EndNote version 21 reference manager tool [41], leaving a total of 504 documents.
The next step involved screening the titles and abstracts of the remaining documents. This led to the exclusion of 287 articles that were not directly relevant to the research focus (e.g., studies on seismic or fire risks that are unrelated to air pollution or climate risk in heritage buildings). A manual full-text review of the remaining 217 articles was then conducted to assess their relevance, specifically focusing on risk assessments in heritage buildings or related technologies. An additional 125 articles were excluded due to irrelevance, resulting in a final set of 92 articles for detailed review.
As shown in Figure 2, the PRISMA flowchart outlines the filtering process from the identification of the initial 583 papers to the final inclusion of 92 articles for detailed review.

2.3. Data Analysis and Synthesis Method

This study employed a combination of Bibliometrix® and qualitative synthesis methods for data analysis and integration. Bibliometrix® was selected for its ability to efficiently handle large volumes of scientific data, providing structured, objective, and reliable analyses through intuitive visualizations, such as thematic networks and country collaboration maps [42]. These visualizations facilitated the identification of research trends, leading contributors, and global collaboration networks within the domain of cultural heritage preservation [43].
The analysis combined quantitative and qualitative approaches. Quantitative data, such as frequency counts and geographical distributions, were presented descriptively to highlight global patterns and country-level scientific contributions. Qualitative thematic synthesis was then applied to interpret the broader context of how AI and IoT technologies are integrated into heritage preservation. This mixed-methods approach enabled an in-depth exploration of emerging patterns and themes, capturing the nuances of technological applications across diverse contexts.
This approach enhanced the depth and rigor of the synthesis by combining bibliometric mapping with qualitative narrative interpretation. It supported the identification of gaps and emerging opportunities in the literature, ensuring a comprehensive understanding of the research landscape.

3. Results

3.1. Bibliometrix® Analysis

3.1.1. Research Gaps from Keywords Co-Occurrence Network

The bibliometric map (Figure 3) visually represents keyword co-occurrence derived from 92 academic papers [2,3,11,12,19,23,24,25,26,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126], showcasing the interconnections between key research themes in heritage conservation. This network offers valuable insights into the current research state, revealing dominant focus areas such as climate effects, air pollution, and cultural heritage preservation. However, despite the extensive range of topics, the map also highlights significant research gaps through the density and distribution of clusters, as well as the absence or weak connections between key terms related to heritage preservation, air pollution, and advanced technologies such as AI and IoT. This reveals opportunities for further research and cross-disciplinary collaboration.
By analyzing the network’s structure, we can identify areas where further research is needed to enhance risk assessment methodologies for heritage buildings, particularly concerning the impacts of air pollution and climatic changes on their long-term preservation. The following section explores these research gaps in greater detail, underscoring the potential for technological innovations to address these challenges.
The network shows multiple clusters or themes:
  • Climate and Environmental Impact (green cluster): There is a significant grouping of terms related to climate effects, such as “temperature effect”, “climate models”, “airflow”, and “ventilation”. This highlights how environmental factors, such as changing climates and airflow, impact heritage buildings, indicating concern over physical deterioration and performance under varying conditions.
  • Cultural Heritage and Risk Assessment (purple cluster): “Cultural heritage”, “building”, and “risk assessment” form another critical theme, connecting to concerns like “damage detection”, “decision-making”, and “microclimate”. These keywords suggest the importance of evaluating the risks that cultural heritage buildings face due to external factors, emphasizing preventive measures and monitoring.
  • Air Quality and Pollution (red cluster): There is a prominent cluster related to air quality, including keywords such as “particulate matter”, “carbon dioxide”, and “atmospheric pollution”. This indicates a focus on how pollutants and environmental contaminants affect building materials, especially those used in heritage buildings like limestone and calcium carbonate.
  • Historic Buildings and Conservation Strategies (blue cluster): Terms related to “preventive conservation”, “building materials”, and “monitoring” emphasize practical approaches to preserving heritage buildings through sustainable practices and careful material management.
  • Architectural Design and AI (orange and brown clusters): Emerging technologies like “artificial intelligence” and “machine learning” are seen interacting with concepts related to “architectural heritage” and “building information modeling”, indicating that advanced computational methods are increasingly being applied to heritage preservation efforts.
Despite the clear focus on environmental concerns such as climate effects and air pollution (green and red clusters) and the growing application of AI and machine learning in the architectural domain (orange and brown clusters), there remains a significant gap in integrating these technological advancements with both environmental risk factors and practical conservation strategies (blue cluster). Notably, the lack of IoT—an essential technology for real-time environmental monitoring—limits the potential to enhance both risk assessment (purple cluster) and preventive conservation.
This gap suggests that current research is not fully addressing the complex challenges posed by climate change and air pollution. Heritage buildings remain vulnerable to these risks without the integration of advanced technologies.
To close this gap, future research should prioritize the integration of IoT and AI technologies to monitor and assess key environmental factors. Doing so will enable the development of more effective, data-driven strategies for heritage conservation, improving both risk mitigation and long-term preservation efforts.

3.1.2. Publications per Country

Figure 4 visualizes the frequency of article production among 40 countries. Italy leads with 53 publications, followed by Spain (26) and Romania (19), indicating solid contributions from these European countries. Conversely, large parts of Africa, Central America, and many South America and Asia countries remain underrepresented.
This geographic imbalance is significant when researching the vulnerability of heritage buildings to climatic factors. However, these regions often face competing priorities such as economic development, public health, and poverty alleviation. As a result, heritage preservation tends to be deprioritized, with limited funding allocated to related research. The World Bank’s income classifications further illustrate the connection between economic capacity and research output [127]. Countries with lower income levels face significant funding constraints, which limit their ability to invest in the research infrastructure and technologies (e.g., AI and IoT) needed to assess and mitigate the impacts of climate change on cultural heritage. Many countries in sub-Saharan Africa, South Asia, and parts of the Middle East remain classified as low or lower-middle-income, which exacerbates the disparity in research output. These regions, with limited resources, often struggle to generate scientific research on heritage preservation, particularly in the context of climate change.
This imbalance in research production highlights the urgent need for targeted efforts to enhance research infrastructure and capacity in underrepresented regions. Strengthening regional policy priorities, increasing funding for heritage preservation, and fostering international collaborations will be essential to address these gaps and build a more inclusive approach to protecting cultural heritage from the impacts of climate change.

3.2. Environmental Risk Factors in Heritage Building Conservation

A comparative analysis of 92 studies examined the impact of air hazards on heritage buildings, focusing on both climatic risks and air pollution. From these, 38 studies were selected based on the parameters monitored (Table 3). Early studies (2014–2016) concentrated on traditional pollutants like CO2, SO2, NO2, and temperature with relative humidity, while more recent studies (2020–2024) expanded to include particulate matter (PM2.5, PM10), VOCs, acetic and formic acids, and additional parameters like air change rates (ACH) and microflora. This shift reflects a heightened concern over pollutants and their impact on both the structural integrity of heritage buildings and the health of occupants and visitors.
The preservation of heritage buildings is heavily influenced by a combination of:
  • Climatic factors: temperature, relative humidity, precipitation, wind, solar radiation, and atmospheric pressure directly affect structural integrity. Fluctuations cause expansion and contraction, leading to physical stress and degradation.
  • Air quality factors: level of pollutants such as PM2.5, PM10, SO2, NO2, O3, and VOCs lead to soiling, corrosion, and chemical reactions that weaken materials. For example, SO2 and NO2 react with calcium carbonate-based materials, accelerating decay.
Additional risks stem from biological factors like microflora, which contribute to material deterioration, and human activity, such as tourism and urbanization, which aggravate deterioration through physical wear and the introduction of pollutants.
Despite technological advances like IoT and AI, they remain underutilized in assessing air pollution and climate risks in heritage conservation. Addressing these challenges requires an integrated approach, combining climate and air quality monitoring with modern technologies.

3.3. Technological Approaches to Risk Management in Heritage Buildings

Table 4 outlines how various risks, methods, and technologies are used to protect cultural heritage buildings. The table highlights five main areas showing how modern technologies are helping manage risks in heritage buildings. Below is a summary:

3.3.1. Risk Types

The table covers a range of risks, such as structural integrity, microclimatic challenges, and AI-driven predictions for indoor climate and structural decay. These risks underscore the complex challenges that heritage buildings encounter. As a result, the choice of technologies depends on the specific type of risk:
  • Structural Integrity Risks: IoT monitors real-time structural parameters like stress and strain, while AI and Heritage BIM (H-BIM) predict long-term vulnerabilities. Photogrammetry captures surface damage, and these technologies work together to ensure structural integrity.
  • Microclimatic and Environmental Risks: IoT monitors temperature, humidity, and pollutants. Computational Fluid Dynamics (CFD) simulates environmental conditions, and AI predicts future impacts. This combination allows for continuous environmental risk assessments.
  • Energy Efficiency Risks: IoT tracks energy consumption, while AI models suggest improvements and predict future energy needs. Dynamic energy models simulate performance, ensuring that energy efficiency is maintained.
  • Decay and Surface Damage: Photogrammetry and Mask Region-based Convolutional Neural Network (Mask R-CNN) detect surface-level damage, while AI forecasts the progression of decay. This combination ensures that surface-level risks are addressed in a timely manner.
  • Cultural and Historical Risks: H-BIM stores historical data about the building’s original design, materials, and modifications. AI analyzes the impact of proposed changes on cultural significance, ensuring that interventions preserve both physical and cultural heritage.

3.3.2. Data Sources

Sensor data and monitoring systems dominate the data sources, particularly through IoT infrastructure. This underscores the increasing reliance on real-time data collection for dynamic decision-making in heritage site management. Additionally, ML and image datasets are growing in use, pointing to the expanding role of AI and computer vision in heritage preservation.

3.3.3. Frameworks

IoT-based monitoring systems and AI-driven decision-making frameworks are commonly employed, particularly for managing risks related to structural integrity and indoor environmental conditions. Some projects also focus on energy efficiency and environmental quality frameworks, reflecting the increasing need for sustainable heritage preservation.

3.3.4. Methodologies

The methodologies show a clear trend towards ML and DL approaches, such as Mask R-CNN for structural decay detection. Simulation-based methodologies, like dynamic energy simulations and AI-driven decision trees, are also prevalent, highlighting the use of advanced computational techniques for predicting and managing risks.

3.3.5. Technologies

Advanced technologies are used to assess risks to heritage buildings. The following analysis provides an overview of the key technologies, their contributions to risk assessment, and strategies for integrating these tools to protect heritage structures more effectively.
  • Artificial Intelligence (AI): AI technologies, such as ML algorithms (e.g., J48 decision trees and XGBoost) and DL models like Mask R-CNN, play an essential role in processing large datasets collected by IoT devices. AI-driven systems are capable of predicting structural decay, energy efficiency, and microclimatic changes. In heritage conservation, AI models also facilitate image-based analysis for detecting structural damage (e.g., cracks) using tools like Convolutional Generative Adversarial Networks (CGAN) and computer vision techniques [25,26,52,53,68,108]. In addition, crack detection and surface damage monitoring rely heavily on AI-powered models such as Fully Convolutional Networks (FCN), Mask R-CNN, and YOLO (You Only Look Once) object detection models. These models analyze image datasets from photogrammetry and laser scanning to identify and quantify cracks and surface damage, allowing for early intervention and repair. YOLOv8, the newest model in the YOLO algorithm series (YOLOv4 in [124] is an older version), offers advanced capabilities for real-time object detection, improving the accuracy of identifying structural damage. AI-powered tools like CNN algorithms, including the ResNet architecture, data labeling tools, and image processing software, significantly enhance the accuracy and efficiency of detecting and managing structural risks [52,59,108,121,125]. Python-based DL models further extend the AI framework, enabling customized algorithms for crack detection and damage assessment tailored specifically to the conditions and requirements of heritage sites. These models provide high flexibility and accuracy in image-based heritage monitoring [87,121].
  • Internet of Things (IoT): IoT is a cornerstone technology for real-time environmental and structural monitoring in heritage buildings. IoT enables real-time monitoring through Wireless Sensor Networks (WSN), which track environmental conditions. The FIWARE platform provides a robust infrastructure for large-scale IoT deployments, enabling seamless communication between sensors and centralized monitoring systems. This platform integrates with Structural Health Monitoring (SHM) systems to gather and analyze real-time data on the structural condition of heritage sites. Various smart sensors are used to collect data, including NB-IoT-enabled smart sensors such as Sensirion SHTC3 (for temperature and humidity) and SAMYOUNG SY-DS-1L (for air quality). These sensors use Message Queue Telemetry Transport (MQTT) protocols to ensure low-power, long-range communication, making them ideal for hard-to-reach heritage sites. LoRa-enabled IoT edge devices and sensors like Bosch BME 280 (for temperature, humidity, and pressure) and CCS811 (for CO2 and VOCs) further extend the capabilities of the IoT network. Data collected by these sensors can be visualized and managed using platforms like Node-RED, ensuring that real-time insights are accessible to decision-makers [23,47,83,88,89,97]. In addition, Arduino-based sensor systems provide a customizable approach to collecting data on structural and environmental conditions. DHT11 (temperature/humidity), MPL3115A2 (pressure), and RD200M Rn (radon) sensors enhance the environmental monitoring scope, and FFT analysis (Fast Fourier Transform) is used to assess structural vibrations, ensuring that any early signs of damage are detected and addressed [59,108]. Moreover, risk assessment tools such as Art-Risk 3.5 are integrated into IoT frameworks to provide a comprehensive risk profile for heritage sites. By combining data from IoT sensors, SHM, and AI models, Art-Risk 3.5 enhances decision-making processes for preventive conservation and ensures that interventions are data-driven [26,59,103,108,119]. Radio Frequency Identification (RFID) technology is another valuable tool for material tracking in heritage conservation. It allows for the precise identification and monitoring of materials within heritage sites, contributing to better inventory management and ensuring that original or restoration materials are properly tracked and maintained [53].
  • Heritage Building Information Modeling (H-BIM): H-BIM is an advanced digital platform that models heritage buildings’ structural and historical aspects. These models integrate data from various sources (IoT, AI, and sensor networks) and provide a holistic understanding of the building’s condition. By storing and analyzing data on the building’s materials, structure, and historical alterations, H-BIM helps predict and manage risks like structural decay and energy inefficiency. Integrating BIM Server and MongoDB ensures efficient data management, while Node-RED helps visualize the real-time data collected from IoT devices, making H-BIM a comprehensive tool for risk management [26,52,59,79,89,103]. Furthermore, Geometric Description Language (GDL) scripting is used within H-BIM to create precise parametric models of heritage buildings, capturing the intricate geometric details that are crucial for their preservation. GDL scripting allows the customization of digital models to reflect the unique structural and design elements of heritage sites, enhancing the accuracy of simulations and predictive analyses [59,125]. Revit plug-ins are also integral to H-BIM workflows, facilitating the integration of architectural models with real-time data collected from IoT devices and AI models. These plug-ins enable seamless interoperability between various digital tools used in heritage conservation, improving both workflow efficiency and model accuracy [52,108].
  • Advanced Imaging Technologies: Technologies like photogrammetry, laser scanning, and drone-based photogrammetry are critical for high-resolution 3D modeling of heritage structures. Drones such as Anafi Parrot UAV are used for aerial photogrammetry, capturing detailed images that are processed into 3D models using Structure from Motion (SfM) algorithms and software like Context Capture. These models help detect surface damage and monitor structural changes over time. Photogrammetry is particularly valuable when combined with AI-based detection models (e.g., CNN algorithms for crack identification and surface damage detection). The Terrestrial Laser Scanner (TLS) is an essential tool in this domain, providing precise 3D measurements of heritage structures. Cyclone Register 360 is often used alongside TLS for accurate point cloud registration, ensuring that data from different scans is correctly aligned and processed into comprehensive 3D models [72,108,121,123,125].
  • Computational Fluid Dynamics (CFD): CFD models simulate airflow, temperature, and humidity distribution, helping researchers understand how these factors influence the microclimate inside and around heritage buildings. Predictive simulations are crucial for assessing how heritage buildings respond to environmental factors over time. Climate impact assessments use models based on RCP2.6 and RCP8.5 scenarios to predict the effects of climate change on structural integrity and material preservation. Tools like Xfuzzy 3.0 are used to develop fuzzy logic algorithms that model uncertain environmental conditions, enabling predictive maintenance and risk management strategies. These algorithms are particularly effective when integrated with DTs, which simulate real-time responses of heritage buildings to environmental and structural stress [26,47,53,102,103].
  • Digital Twin (DT): DT creates a dynamic virtual replica of a heritage building, integrating real-time data from IoT sensors with historical and structural information. DT enables continuous monitoring of the building’s condition and simulates how it responds to various factors such as environmental changes, structural stress, or maintenance actions. Acting as the convergence point for multiple technologies like IoT, AI, H-BIM, imaging, and predictive simulations, DT provides a comprehensive, real-time representation of the heritage building. By integrating data from these various technologies, DT creates a virtual environment that reflects both current and predicted conditions, offering insights for risk management and conservation strategies. This holistic approach allows heritage conservation teams to make informed decisions by not only monitoring present conditions but also forecasting future risks. DT transforms static building models into dynamic, responsive systems that evolve as the building and its surrounding environment change, ensuring the building’s long-term preservation and sustainability [26,52,59,79,89,93,103,108,125].
Integrating IoT, AI, H-BIM, CFD, photogrammetry, and DT can achieve a comprehensive system for real-time risk assessment and management. The selection of technologies is tailored to address specific risk types. The integration of these technologies provides a holistic view of the risks, allowing for better decision-making and more effective heritage preservation strategies. This combination allows heritage buildings to be continuously monitored, with real-time updates and predictive insights guiding preservation strategies. These technologies not only support proactive maintenance but also ensure that the cultural and historical significance of heritage buildings is preserved alongside their physical structure.

4. Discussion

4.1. Adoption Trends and Geographical Imbalance in AI and IoT Applications for Heritage Preservation

The systematic review reveals a growing number of studies employing IoT sensors for the ongoing observation of heritage buildings, facilitating real-time data gathering for anticipatory conservation measures. AI systems interpret this information to improve decision-making concerning environmental factors and structural integrity. Nonetheless, research is unevenly distributed, heavily favoring European nations, particularly Italy, Spain, and Romania, which boast robust research infrastructures and notable cultural landmarks. Illustrative examples include the Royal Alcázar of Seville, Spain [119], the Monastery of Jerónimos, Portugal [116], and Roman mortars in Tharros, Italy [117].
Conversely, areas such as sub-Saharan Africa, South Asia, and South America remain underrepresented despite confronting serious environmental challenges. This disparity arises from financial limitations and insufficient research facilities in low- and lower-middle-income countries, where funding often prioritizes urgent requirements like poverty reduction and healthcare services. The classifications provided by the World Bank underscore this issue, as numerous nations lack the ability to invest in cutting-edge preservation technologies.
This geographic imbalance highlights systemic barriers that prevent broader participation in heritage preservation research. To remedy this inequality, focused strategies must be implemented: increasing research funding via international grants, promoting partnerships between affluent and less affluent regions, creating open-access research platforms, and designing specialized training initiatives for local researchers. The prevailing emphasis on well-documented locations in high-income areas constrains the formulation of universally applicable conservation strategies, overlooking diverse climatic and socio-economic settings.
Key criteria for case study selection should include cultural significance, environmental vulnerability, climatic diversity, and technological feasibility. Notable examples include the Basilica of St. Anthony, Italy, which is an ideal example of culturally significant sites under threat [121], and the Nożyk Synagogue, Poland, has been indicated to be at risk of structural displacement or deformation due to external factors [123]. Similarly, the San Juan Bautista Church in Spain is exposed to humidity fluctuations [122]. While these examples provide valuable insights, similar challenges in tropical, arid, or monsoon-affected regions remain understudied. Technological feasibility is another critical consideration. For instance, IoT sensors used in the Art Nouveau Museum in Romania and AI-based monitoring systems implemented in the Classical Gardens of Suzhou, China, highlight the transformative potential of advanced technologies in preserving cultural heritage [78,124]. Expanding the geographical scope to include sites from underrepresented regions can yield insights into the impact of varying climates on heritage preservation. Addressing these disparities through international collaboration and enhanced funding can lead to more inclusive conservation strategies.

4.2. Comprehensive Environmental and Structural Monitoring Parameters

Deploying IoT sensors is critical for collecting real-time data on environmental and structural parameters. Studies have monitored indoor conditions, outdoor pollutants, and meteorological factors. Comprehensive monitoring enables a holistic understanding of the factors affecting heritage buildings and supports timely interventions. Real-time data collection allows for the immediate identification of adverse conditions that could lead to material degradation or structural damage.
The studies reviewed emphasize several key environmental parameters that significantly impact heritage buildings:
  • Temperature and relative humidity: Fluctuations cause materials to expand and contract, leading to physical stress and degradation. Nearly all studies monitored these parameters, highlighting their fundamental importance.
  • Air Pollutants: Pollutants like SO2, NO2, O3, CO2, PM2.5, PM10, and VOCs contribute to chemical reactions that weaken materials. Many studies focused on these pollutants.
  • Microclimatic Factors: Some studies monitored parameters like air change rates, natural and artificial light, and microflora, reflecting an interest in comprehensive indoor environmental conditions.

4.3. Innovative Methodologies for Adaptive and Proactive Solutions

4.3.1. Integrated IoT and AI Systems for Real-Time Risk Management

Combining IoT sensors with AI analytics enables a proactive approach to risk management. Continuous data collection allows for real-time monitoring of environmental and structural conditions. AI models analyze this data to predict potential risks, such as material degradation due to pollutant exposure or structural vulnerabilities from environmental stressors [19,23,93,97]. Automated damage detection using DL algorithms further enhanced conservation efforts by identifying structural issues like cracks in building facades in near real-time [25,68,72,108,125].
For example, in a case study utilizing IoT devices with IoT Hub, an environmental parameter such as equivalent CO2 (eCO2) and total volatile organic compounds (TVOCs) were monitored. The data were processed using an ML algorithm to forecast emissions and optimize ventilation systems for improved indoor air quality [23,128].
These AI-enabled predictions allowed facility managers to proactively mitigate risks associated with pollutant exposure.

4.3.2. Development of Comprehensive DTs

DTs represent a holistic approach by integrating IoT data, AI analytics, and H-BIM models. They provide dynamic, continuously updated virtual representations of heritage buildings, enabling simulation of environmental scenarios and assessment of potential threats [93,108,125].
For instance, in a pilot project focusing on carbon emissions, a DT system is used to visualize real-time data on a 3D BIM model, enabling stakeholders to simulate environmental scenarios like temperature fluctuations and air pollutant dispersion. The project incorporated predictive analytics powered by machine learning models to assess the structural impact of prolonged pollutant exposure, helping stakeholders evaluate long-term interventions [22,127].
Such systems allow stakeholders to visualize the effects of interventions virtually, ensuring that restoration strategies are both effective and sustainable.

4.3.3. Enhanced Environmental Monitoring for Air Quality Improvement

Improving air quality within and around heritage buildings is critical for preserving structural integrity and ensuring occupant health. Utilizing IoT sensors to monitor a broad range of pollutants provides detailed insights into air quality [3,47,62,65,74,88,110,111]. AI models facilitate the regulation of indoor climate conditions, such as temperature and relative humidity, to prevent the deterioration of artifacts and building materials [53,88,97].

4.3.4. Application of Advanced AI Techniques for Specific Conservation Challenges

Advanced AI techniques address specialized preservation needs. Fuzzy logic models predict functional deterioration under climate change scenarios, aiding long-term planning and resource allocation [102]. Generative Adversarial Networks (GANs) support urban cultural regeneration by generating facade designs that align with historical aesthetics, addressing architectural style inconsistencies [86].

4.3.5. Collaborative Platforms and Knowledge Sharing

Promoting interdisciplinary collaboration enhances conservation outcomes. H-BIM platforms facilitate engagement among architects, engineers, conservationists, and policymakers by providing a shared digital environment [26,52,59,89,103]. Developing standardized protocols ensures consistency in data collection and analysis, improving the effectiveness of preservation strategies. Collaborative platforms support knowledge sharing and capacity building among stakeholders.

4.4. Future Research Directions

The proposed innovative integrated research framework is a multi-layered, iterative process designed to proactively monitor, analyze, and conserve heritage buildings by integrating IoT, AI, H-BIM, advanced imaging technologies, and collaborative platforms. This framework aims to maintain the structural integrity and cultural significance of heritage buildings through data-driven insights and adaptive interventions. While initially implemented in a specific context, it is adaptable for use in different regions and heritage sites worldwide.
The Framework Implementation Steps are described below.

4.4.1. Step 1: Preliminary Assessment

The framework begins with a comprehensive evaluation of the heritage building’s geographic, historical, and architectural context. For instance, the city walls of Siena, Italy, were assessed for structural vulnerabilities using crack displacement monitoring [23]. This assessment determines the specific risks to be addressed, whether structural, environmental, or human-induced. Based on this assessment, appropriate technologies are selected, such as IoT sensors for environmental monitoring or advanced imaging tools. For example, in the Hazzazi House in Saudi Arabia, natural ventilation and air change rates were simulated using Computational Fluid Dynamics (CFD) to address identified vulnerabilities [45].
This assessment includes examining the building’s physical state to identify existing damage or areas of concern; understanding environmental factors like climate, pollution levels, and urban development; and identifying specific threats such as structural vulnerabilities, environmental hazards, and potential degradation processes. Appropriate technologies are then selected to address these needs, including IoT sensors for monitoring, AI models for data analysis, advanced imaging equipment for detailed surveys, and simulation tools for environmental modeling.

4.4.2. Step 2: Deployment of Monitoring Systems (Environmental and Structural Monitoring)

Once the preliminary assessment is complete, the framework proceeds with the deployment of IoT sensors to monitor environmental factors and structural integrity. A network of IoT sensors is strategically deployed throughout the heritage building to monitor key environmental parameters such as temperature, humidity, and pollutants like CO2, PM2.5, and VOCs, as well as structural health indicators like stress, strain, and vibrations. Sensors are placed both indoors and outdoors to capture comprehensive data [44,47,88,97]. Data transmission and storage are managed using reliable wireless communication protocols like NB-IoT and LoRaWAN, with cloud-based storage solutions implemented for scalability and accessibility.
The monitoring process should balance the need for comprehensive data with efficient time management, tailoring the duration to specific objectives. For material degradation studies, a six-month period is typically sufficient to observe significant changes, as in [46], which studied self-cleaning and UV aging on historic marble surfaces over six months. For environmental monitoring and indoor air quality assessments, a three- to seven-month period is ideal. Studies like [78] (Art Nouveau Museum) effectively tracked indoor air quality over different seasons. For structural integrity monitoring, shorter durations of one to three months are typically adequate. For example, [87] (James Jackson Gymnasium) used 3D laser scanning over one to two months to detect pathology cracks. For simulated environmental models or studies focusing on specific short-term events, data collection may only need to span a few days to a few weeks.
Therefore, the duration of monitoring should be determined by the specific research objectives. This will ensure that researchers gather comprehensive data while keeping the study efficient and focused.

4.4.3. Step 3: Data Integration and Model Development (H-BIM Platform and AI Training)

Collected data are integrated into a Heritage Building Information Model (H-BIM), incorporating historical information, architectural and material data, and real-time IoT data, ensuring an up-to-date digital representation [52,59,89,93]. Data standardization is crucial, with standardized data formats and protocols established to ensure compatibility and facilitate integration across different technologies and systems.
AI and ML models are developed and trained using the integrated data. ML algorithms like decision trees and XGBoost perform predictive analysis on environmental and structural data, forecasting potential risks [52,53,102]. DL algorithms like Mask R-CNN and YOLOv8 enable automated damage detection and image analysis, identifying structural issues from visual data [25,68,108]. These AI models analyze historical and real-time data to identify patterns and predict potential risks through time-series analysis and anomaly detection.

4.4.4. Step 4: Development of the DT (Dynamic Virtual Representation)

DT of the heritage building is developed by integrating the H-BIM with real-time IoT data and AI analytics, ensuring the DT reflects the building’s current state. Environmental simulations, including CFD and dynamic energy modeling, simulate environmental interactions and energy performance [47,93,103,125]. This dynamic virtual representation is validated against actual conditions and historical records to ensure accuracy. The DT serves as a tool for continuous monitoring, scenario simulation, and predictive maintenance planning.

4.4.5. Step 5: Model Validation and Accuracy Assessment

The accuracy and reliability of AI models and DT simulations are validated using a combination of field measurements, international standards comparisons, point cloud data, and historical data. For example, field measurements validate real-world environmental models, as in studies of Sweden’s heritage buildings [44] and Gadara in Jordan [11]. On-site inspections verify structural and environmental risk assessments. Comparing environmental data against international standards ensures compliance, as demonstrated in Serbian museums where data were aligned with American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) guidelines [126]. Point cloud data processed by Artificial Neural Networks (ANN), as used in the Nożyk Synagogue [123], help validate structural models and detect deformations. Comparing current data with historical records aids in validating long-term predictive models.

4.4.6. Step 6: Continuous Monitoring and Analysis

Using the DT, AI models continuously analyze incoming real-time data to detect anomalies, identify patterns, and generate predictive insights. Regular risk assessments are conducted based on AI predictions and simulation outcomes, ensuring proactive conservation efforts. Time-series analysis and anomaly detection techniques help foresee environmental changes and structural vulnerabilities. The DT and AI models continuously monitor real-time IoT data to detect any emerging risks. In Gadara, Jordan, for example, real-time analysis of pollutants like SO2 and NO2 would provide insights into material degradation [11]. By identifying patterns and forecasting potential risks, such as structural weaknesses or material degradation, the AI models facilitate a proactive approach to risk management. Additionally, in the Hazzazi House, environmental data on airflow and humidity could be continuously analyzed to predict risks associated with natural ventilation inefficiencies [45].

4.4.7. Step 6: Prevention Strategies and Maintenance Planning

Based on data-driven insights from continuous monitoring, maintenance strategies are developed by designing tailored interventions to address identified risks effectively. Conservation actions are implemented promptly to mitigate risks, and a feedback loop is established to monitor the effectiveness of these interventions through the DT, allowing for adjustments as needed.
Prevention strategies are central to the long-term preservation of heritage buildings, aiming to minimize deterioration and reduce the need for reactive interventions. This framework emphasizes data-driven, proactive approaches based on continuous monitoring, AI-driven predictions, and environmental modeling.
Environmental control plays a crucial role in preventing damage from pollutants, humidity, and temperature fluctuations. For example, in the study of Sweden’s heritage office buildings [44], indoor air quality was improved through real-time adjustments to energy performance and airflow based on CO2 concentration data. Similarly, pollutant exposure in Gadara, Jordan [11], can be mitigated through air filtration systems.
For material degradation prevention, treatments such as protective coatings or surface cleaning methods should be applied in alignment with laboratory findings. The use of hydrophobic and self-cleaning materials on historic marble facades [46] is an example of how these treatments can shield surfaces from UV radiation, moisture, and dirt accumulation.
Structural health monitoring enables preventive strategies for maintaining the stability of heritage buildings. Through real-time monitoring of stress, strain, and crack growth, early signs of structural failure can be detected. In cases like the Nożyk Synagogue [123], point cloud data processed by ANN can detect structural deformations, enabling the reinforcement of vulnerable areas before serious damage occurs.
Preventive maintenance scheduling should be based on AI-driven predictions and DT simulations, allowing conservation teams to forecast when and where maintenance interventions will be needed. By using time-series analysis to detect patterns and anomalies in real-time IoT data, AI can suggest optimal intervention schedules.
In conclusion, this framework represents a significant advancement in heritage preservation methodologies. It not only leverages advanced technologies to enhance conservation efforts but also contributes to a deeper understanding of the factors affecting heritage sites globally. By adopting this framework, stakeholders can develop tailored interventions and make informed decisions to protect heritage buildings for future generations. The proposed innovative technology-integrated heritage framework, illustrated in Figure 5, serves as a blueprint for future research and practical applications in the field of cultural heritage preservation.

5. Conclusions

This systematic review critically examined the integration of AI and IoT in preserving cultural heritage buildings, focusing on risk management and environmental monitoring. The preservation of cultural heritage buildings faces increasing challenges due to environmental threats like climate change and air pollution. This review underscores the transformative potential of integrating AI and IoT technologies to develop adaptive and proactive solutions. Leveraging real-time monitoring, predictive analytics, and collaborative platforms allows stakeholders to make informed decisions, safeguarding heritage structures for future generations.
The study analyzed patterns and trends, identified key factors and methodologies, and proposed innovative approaches to address dynamic environmental challenges threatening heritage structures.
Implementing the proposed integrated research framework can enhance the resilience of heritage buildings, ensuring they continue to embody historical, cultural, and architectural significance amid evolving environmental challenges.

Author Contributions

Conceptualization, N.L. and T.W.; methodology, N.L. and T.W.; software, N.L.; formal analysis, N.L. and T.W.; investigation, N.L. and T.W.; resources, N.L.; data curation, N.L.; writing—original draft preparation, N.L.; writing—review and editing, N.L. and T.W.; visualization N.L.; supervision, T.W.; project administration, T.W.; funding acquisition, N.L. and T.W. All authors have read and agreed to the published version of the manuscript.

Funding

N.L. is supported by a CMU Presidential Scholarship, Chiang Mai University (2567-038). The APC was funded by Chiang Mai University.

Data Availability Statement

The original contributions presented in the study are included in the article; further inquiries can be directed to the corresponding author.

Acknowledgments

This research, conducted as part of the Doctor of Philosophy Program in Architecture (International Program) at the Faculty of Architecture, Chiang Mai University, is funded under the CMU Presidential Scholarship.

Conflicts of Interest

The authors declare no conflicts of interest.

Nomenclature

ACHAir Change Rates
AIArtificial Intelligence
ANNArtificial Neural Network
ASHRAEAmerican Society of Heating, Refrigerating and Air-Conditioning Engineers
CFDComputational Fluid Dynamics
CGANConvolutional Generative Adversarial Networks
CNNConvolutional Neural Network
DLDeep Learning
DRMDisaster Risk Management
DRRDisaster Risk Reduction
DTDigital Twins
FCNFully Convolutional Network
FFTFast Fourier Transform
GANsGenerative Adversarial Networks
GDLGeometric Description Language
GISGeographic Information System
H-BIMHeritage Building Information Modeling
HVACHeating, Ventilation and Air Conditioning systems
IAQIndoor Air Quality
IoTInternet of Things
Mask R-CNNMask Region-based Convolutional Neural Network
MLMachine Learning
MQTTMessage Queue Telemetry Transport
NB-IoTNarrowband Internet of Things
PMParticulate Matter
PRISMAPreferred Reporting Items for Systematic Reviews and Meta-Analyses
RCPRepresentative Concentration Pathways
RFIDRadio Frequency Identification
RHRelative Humidity
RnRadon (gas)
SDGsSustainable Development Goals
SfMStructure from Motion
SHMStructural Health Monitoring
SLRSystematic Literature Review
TLSTerrestrial Laser Scanner
UAVUnmanned Aerial Vehicle
UNUnited Nations
UV Ultraviolet radiation
VOCsVolatile Organic Compounds
WHWorld Heritage
WoSWeb of Science
WSNWireless Sensor Networks
XGBoosteXtreme Gradient Boosting
YOLOYou Only Look Once (object detection model)

References

  1. Morkunaite, Z.; Podvezko, V.; Zavadskas, E.K.; Bausys, R. Contractor selection for renovation of cultural heritage buildings by PROMETHEE method. Arch. Civ. Mech. Eng. 2019, 19, 1056–1071. [Google Scholar] [CrossRef]
  2. Hollesen, J. Climate change and the loss of archaeological sites and landscapes: A global perspective. Antiquity 2022, 96, 1382–1395. [Google Scholar] [CrossRef]
  3. Bucur, E.; Vasile, A.; Diodiu, R.; Catrangiu, A.; Petrescu, M. Assessment of indoor air quality in a wooden church for preventive conservation. J. Environ. Prot. Ecol. 2015, 16, 7–17. [Google Scholar]
  4. Costa, M.; Carneiro, M.J. The influence of interpretation on learning about architectural heritage and on the perception of cultural significance. J. Tour. Cult. Change 2021, 19, 230–249. [Google Scholar] [CrossRef]
  5. Zhang, S.; Wang, B.y.; Wang, S.; Hu, W.; Wen, X.; Shao, P.; Fan, J. Influence of Air Pollution on Human Comfort in Five Typical Chinese Cities. Environ. Res. 2020, 195, 110318. [Google Scholar] [CrossRef]
  6. Faridi, S.; Yousefian, F.; Janjani, H.; Niazi, S.; Azimi, F.; Naddafi, K.; Hassanvand, M.S. The effect of COVID-19 pandemic on human mobility and ambient air quality around the world: A systematic review. Urban Clim. 2021, 38, 100888. [Google Scholar] [CrossRef]
  7. González-Lezcano, R.A. Editorial: Design of efficient and healthy buildings. Front. Built Environ. 2023, 9, 1210956. [Google Scholar] [CrossRef]
  8. Zoran, M.A.; Savastru, R.S.; Savastru, D.M.; Tautan, M.N. Impacts of exposure to air pollution, radon and climate drivers on the COVID-19 pandemic in Bucharest, Romania: A time series study. Environ. Res. 2022, 212, 113437. [Google Scholar] [CrossRef]
  9. UN. Hottest July Ever Signals ‘Era of Global Boiling Has Arrived’ Says UN Chief|UN News. Available online: https://news.un.org/en/story/2023/07/1139162 (accessed on 18 September 2024).
  10. Amnuaylojaroen, T. Perspective on the Era of Global Boiling: A Future beyond Global Warming. Adv. Meteorol. 2023, 2023, 5580606. [Google Scholar] [CrossRef]
  11. Abu-Allaban, M.; El-Khalili, M.M.M. Antiquity impact of air pollution at Gadara, Jordan. Mediterr. Archaeol. Archaeom. 2014, 14, 191–199. [Google Scholar]
  12. Mohd Dzulkifli, S.N.; Abdullah, A.H.; Leman, A.M. Design and material in museum: Does it affect the ventilation in indoor air quality? ARPN J. Eng. Appl. Sci. 2016, 11, 7341–7348. [Google Scholar]
  13. Oliveira, M.L.S.; Neckel, A.; Pinto, D.; Maculan, L.S.; Dotto, G.L.; Silva, L.F.O. The impact of air pollutants on the degradation of two historic buildings in Bordeaux, France. Urban Clim. 2021, 39, 100927. [Google Scholar] [CrossRef]
  14. Broomandi, P.; Jahanbakhshi, A.; Fathian, A.; Darynova, Z.; Janatian, N.; Nikfal, A.; Kim, J.R.; Karaca, F. Impacts of ambient air pollution on UNESCO world cultural heritage sites in Eastern Asia: Dose-response calculations for material corrosions. Urban Clim. 2022, 46, 101275. [Google Scholar] [CrossRef]
  15. Baglioni, M.; Poggi, G.; Chelazzi, D.; Baglioni, P. Advanced Materials in Cultural Heritage Conservation. Molecules 2021, 26, 3967. [Google Scholar] [CrossRef]
  16. Elfadaly, A.; Attia, W.; Qelichi, M.M.; Murgante, B.; Lasaponara, R. Management of Cultural Heritage Sites Using Remote Sensing Indices and Spatial Analysis Techniques. Surv. Geophys. 2018, 39, 1347–1377. [Google Scholar] [CrossRef]
  17. Fatorić, S.; Seekamp, E. Securing the Future of Cultural Heritage by Identifying Barriers to and Strategizing Solutions for Preservation under Changing Climate Conditions. Sustainability 2017, 9, 2143. [Google Scholar] [CrossRef]
  18. Bertolin, C. Preservation of Cultural Heritage and Resources Threatened by Climate Change. Geosciences 2019, 9, 250. [Google Scholar] [CrossRef]
  19. Bienvenido-Huertas, D.; León-Muñoz, M.; Martín-del-Río, J.J.; Rubio-Bellido, C. Analysis of climate change impact on the preservation of heritage elements in historic buildings with a deficient indoor microclimate in warm regions. Build. Environ. 2021, 200, 107959. [Google Scholar] [CrossRef]
  20. Paschalidou, E.; Fafet, C.; Milios, L. A Strong Sustainability Framework for Digital Preservation of Cultural Heritage: Introducing the Eco-Sufficiency Perspective. Heritage 2022, 5, 1066–1088. [Google Scholar] [CrossRef]
  21. Hsu, H.-H.; Huang, J.-S. Passive Environmental Control at Neighborhood and Block Scales for Conservation of Historic Settlements: The Case Study of Huatzai Village in Wang-An, Taiwan. Sustainability 2022, 14, 11840. [Google Scholar] [CrossRef]
  22. Hu, X.; Assaad, R.H. A BIM-enabled digital twin framework for real-time indoor environment monitoring and visualization by integrating autonomous robotics, LiDAR-based 3D mobile mapping, IoT sensing, and indoor positioning technologies. J. Build. Eng. 2024, 86, 108901. [Google Scholar] [CrossRef]
  23. Addabbo, T.; Fort, A.; Mugnaini, M.; Panzardi, E.; Pozzebon, A.; Vignoli, V. A city-scale IoT architecture for monumental structures monitoring. Meas. J. Int. Meas. Confed. 2019, 131, 349–357. [Google Scholar] [CrossRef]
  24. Mitro, N.; Krommyda, M.; Amditis, A. Smart Tags: IoT Sensors for Monitoring the Micro-Climate of Cultural Heritage Monuments. Appl. Sci. 2022, 12, 2315. [Google Scholar] [CrossRef]
  25. Bruno, S.; Galantucci, R.A.; Musicco, A. Decay detection in historic buildings through image-based deep learning. Vitruvio 2023, 8, 6–17. [Google Scholar] [CrossRef]
  26. Croce, V.; Caroti, G.; Piemonte, A.; De Luca, L.; Véron, P. H-BIM and Artificial Intelligence: Classification of Architectural Heritage for Semi-Automatic Scan-to-BIM Reconstruction. Sensors 2023, 23, 2497. [Google Scholar] [CrossRef]
  27. Marzouk, M.; Atef, M. Assessment of Indoor Air Quality in Academic Buildings Using IoT and Deep Learning. Sustainability 2022, 14, 7015. [Google Scholar] [CrossRef]
  28. Mishra, M.; Lourenço, P.B. Artificial intelligence-assisted visual inspection for cultural heritage: State-of-the-art review. J. Cult. Herit. 2024, 66, 536–550. [Google Scholar] [CrossRef]
  29. Elabd, N.M.; Mansour, Y.M.; Khodier, L.M. Utilizing innovative technologies to achieve resilience in heritage buildings preservation. Dev. Built Environ. 2021, 8, 100058. [Google Scholar] [CrossRef]
  30. Metwally, E.A.; Ismail, M.R.; Farid, A.A. Advancing Building Assessment Tools: Achieving Sustainable Development Goals through the Fusion of Internet of Things Occupant-Centric Principles and Sustainable Practices. Buildings 2024, 14, 1798. [Google Scholar] [CrossRef]
  31. Kang, T.W.; Mo, Y. A comprehensive digital twin framework for building environment monitoring with emphasis on real-time data connectivity and predictability. Dev. Built Environ. 2024, 17, 100309. [Google Scholar] [CrossRef]
  32. Franco, A.; Crisostomi, E.; Dalmiani, S.; Poletti, R. Synergy in Action: Integrating Environmental Monitoring, Energy Efficiency, and IoT for Safer Shared Buildings. Buildings 2024, 14, 1077. [Google Scholar] [CrossRef]
  33. The National Institute of Building Sciences. Sustainable Historic Preservation. Available online: https://www.wbdg.org/design-objectives/historic-preservation/sustainable-historic-preservation (accessed on 19 September 2024).
  34. Siccardi, S.; Villa, V. Trends in Adopting BIM, IoT and DT for Facility Management: A Scientometric Analysis and Keyword Co-Occurrence Network Review. Buildings 2023, 13, 15. [Google Scholar] [CrossRef]
  35. Karatzas, S.; Papageorgiou, G.; Lazari, V.; Bersimis, S.; Fousteris, A.; Economou, P.; Chassiakos, A. A text analytic framework for gaining insights on the integration of digital twins and machine learning for optimizing indoor building environmental performance. Dev. Built Environ. 2024, 18, 100386. [Google Scholar] [CrossRef]
  36. Page, M.J.; Moher, D.; Bossuyt, P.M.; Boutron, I.; Hoffmann, T.C.; Mulrow, C.D.; Shamseer, L.; Tetzlaff, J.M.; Akl, E.A.; Brennan, S.E.; et al. PRISMA 2020 explanation and elaboration: Updated guidance and exemplars for reporting systematic reviews. BMJ 2021, 372, n160. [Google Scholar] [CrossRef]
  37. Arachchige, G.R.P.; Thorstensen, E.B.; Coe, M.; McKenzie, E.J.; O’Sullivan, J.M.; Pook, C.J. LC-MS/MS quantification of fat soluble vitamers—A systematic review. Anal. Biochem. 2021, 613, 113980. [Google Scholar] [CrossRef]
  38. Baas, J.; Schotten, M.; Plume, A.; Côté, G.; Karimi, R. Scopus as a curated, high-quality bibliometric data source for academic research in quantitative science studies. Quant. Sci. Stud. 2020, 1, 377–386. [Google Scholar] [CrossRef]
  39. Zhu, J.; Liu, W. A tale of two databases: The use of Web of Science and Scopus in academic papers. Scientometrics 2020, 123, 321–335. [Google Scholar] [CrossRef]
  40. UN. THE 17 GOALS|Sustainable Development. Available online: https://sdgs.un.org/goals (accessed on 15 November 2024).
  41. Bramer, W.M.; Giustini, D.M.; de Jonge, G.B.; Holland, L.; Bekhuis, T. De-duplication of database search results for systematic reviews in EndNote. J. Med. Libr. Assoc. JMLA 2016, 104, 240–243. [Google Scholar] [CrossRef]
  42. Aria, M.; Cuccurullo, C. bibliometrix: An R-tool for comprehensive science mapping analysis. J. Informetr. 2017, 11, 959–975. [Google Scholar] [CrossRef]
  43. Wei, W.; Jiang, Z. A bibliometrix-based visualization analysis of international studies on conversations of people with aphasia: Present and prospects. Heliyon 2023, 9, e16839. [Google Scholar] [CrossRef]
  44. Abdul Hamid, A.; Johansson, D.; Bagge, H. Ventilation measures for heritage office buildings in temperate climate for improvement of energy performance and IEQ. Energy Build. 2020, 211, 109822. [Google Scholar] [CrossRef]
  45. Alaidroos, A.; Almaimani, A.; Baik, A.; Al-Amodi, M.; Rahaman, K.R. Are historical buildings more adaptive to minimize the risks of airborne transmission of viruses and public health? A study of the hazzazi house in Jeddah (Saudi Arabia). Int. J. Environ. Res. Public Health 2021, 18, 3601. [Google Scholar] [CrossRef] [PubMed]
  46. Aldoasri, M.A.; Darwish, S.S.; Adam, M.A.; Elmarzugi, N.A.; Ahmed, S.M. Protecting of marble stone facades of historic buildings using multifunctional TiO2 nanocoatings. Sustainability 2017, 9, 2002. [Google Scholar] [CrossRef]
  47. Alizzio, D.; De Capua, C.; Fulco, G.; Lugarà, M.; Palco, V.; Ruffa, F. IOT enviromental quality monitoring in smart buildings in presence of measurement uncertainty: A decision making approach. Acta IMEKO 2023, 12, 1–8. [Google Scholar] [CrossRef]
  48. Aste, N.; Adhikari, R.S.; Buzzetti, M.; Della Torre, S.; Del Pero, C.; Huerto, C.H.E.; Leonforte, F. Microclimatic monitoring of the Duomo (Milan Cathedral): Risks-based analysis for the conservation of its cultural heritage. Build. Environ. 2019, 148, 240–257. [Google Scholar] [CrossRef]
  49. Balocco, C.; Colaianni, A. Modelling of reversible plant system operations in a cultural heritage school building for indoor thermal comfort. Sustainability 2018, 10, 3776. [Google Scholar] [CrossRef]
  50. Berto, L.; Doria, A.; Faccio, P.; Saetta, A.; Talledo, D. Vulnerability Analysis of Built Cultural Heritage: A Multidisciplinary Approach for Studying the Palladio’s Tempietto Barbaro. Int. J. Archit. Herit. 2017, 11, 773–790. [Google Scholar] [CrossRef]
  51. Bertolin, C.; Camuffo, D.; Bighignoli, I. Past reconstruction and future forecast of domains of indoor relative humidity fluctuations calculated according to EN 15757:2010. Energy Build. 2015, 102, 197–206. [Google Scholar] [CrossRef]
  52. Bienvenido-Huertas, D.; Nieto-Julián, J.E.; Moyano, J.J.; Macías-Bernal, J.M.; Castro, J. Implementing Artificial Intelligence in H-BIM Using the J48 Algorithm to Manage Historic Buildings. Int. J. Archit. Herit. 2020, 14, 1148–1160. [Google Scholar] [CrossRef]
  53. Boesgaard, C.; Hansen, B.V.; Kejser, U.B.; Mollerup, S.H.; Ryhl-Svendsen, M.; Torp-Smith, N. Prediction of the indoor climate in cultural heritage buildings through machine learning: First results from two field tests. Herit. Sci. 2022, 10, 176. [Google Scholar] [CrossRef]
  54. Bonazza, A.; Sardella, A.; Kaiser, A.; Cacciotti, R.; De Nuntiis, P.; Hanus, C.; Maxwell, I.; Drdácký, T.; Drdácký, M. Safeguarding cultural heritage from climate change related hydrometeorological hazards in Central Europe. Int. J. Disaster Risk Reduct. 2021, 63, 102455. [Google Scholar] [CrossRef]
  55. Califano, A.; Baiesi, M.; Bertolin, C. Analysing the Main Standards for Climate-Induced Mechanical Risk in Heritage Wooden Structures: The Case of the Ringebu and Heddal Stave Churches (Norway). Atmosphere 2022, 13, 791. [Google Scholar] [CrossRef]
  56. Carpio, M.; Ortega, J.; Prieto, A.J. Expert panel on in-situ visual inspections for masonry churches maintenance stage. J. Civ. Eng. Manag. 2021, 27, 454–471. [Google Scholar] [CrossRef]
  57. Carpio, M.; Prieto, A.J. Expert panel, preventive maintenance of heritage buildings and fuzzy logic system: An application in valdivia, Chile. Sustainability 2021, 13, 6922. [Google Scholar] [CrossRef]
  58. Casprini, E.; Passoni, C.; Marini, A.; Bartoli, G. DEMSA Protocol: Deterioration Effect Modelling for Structural Assessment of RC Buildings. Buildings 2022, 12, 574. [Google Scholar] [CrossRef]
  59. Ceccarelli, L.; Bevilacqua, M.G.; Caroti, G.; Castiglia, R.B.F.; Croce, V. Semantic segmentation through Artificial Intelligence from raw point clouds to H-BIM representation. Disegnarecon 2023, 16, 171–178. [Google Scholar] [CrossRef]
  60. Coelho, G.B.A.; Silva, H.E.; Henriques, F.M.A. Impact of climate change on cultural heritage: A simulation study to assess the risks for conservation and thermal comfort. Int. J. Glob. Warm. 2019, 19, 382–406. [Google Scholar] [CrossRef]
  61. Costa-Carrapiço, I.; González, J.N.; Raslan, R.; Sánchez-Guevara, C.; Redondas Marrero, M.D. Understanding thermal comfort in vernacular dwellings in Alentejo, Portugal: A mixed-methods adaptive comfort approach. Build. Environ. 2022, 217, 109084. [Google Scholar] [CrossRef]
  62. Daengprathum, N.; Onchang, R.; Nakhapakorn, K.; Robert, O.; Tipayarom, A.; Sturm, P.J. Estimation of Effects of Air Pollution on the Corrosion of Historical Buildings in Bangkok. Environ. Nat. Resour. J. 2022, 20, 505–514. [Google Scholar] [CrossRef]
  63. De Marco, A.; Screpanti, A.; Mircea, M.; Piersanti, A.; Proietti, C.; Fornasier, M.F. High resolution estimates of the corrosion risk for cultural heritage in Italy. Environ. Pollut. 2017, 226, 260–267. [Google Scholar] [CrossRef]
  64. Dişli, G.; Kilit, R.M. Risk Management and Preventive Conservation of Cultural Heritage: The Case of Karaman Hatuniye Madrasa and Karaman City Museum. J. Integr. Disaster Risk Manag. 2024, 14, 49–74. [Google Scholar] [CrossRef]
  65. Elnaggar, A.; Said, M.; Kraševec, I.; Said, A.; Grau-Bove, J.; Moubarak, H. Risk analysis for preventive conservation of heritage collections in Mediterranean museums: Case study of the museum of fine arts in Alexandria (Egypt). Herit. Sci. 2024, 12, 59. [Google Scholar] [CrossRef]
  66. Esteban-Cantillo, O.J.; Menendez, B.; Quesada, B. Climate change and air pollution impacts on cultural heritage building materials in Europe and Mexico. Sci. Total Environ. 2024, 921, 170945. [Google Scholar] [CrossRef]
  67. Falk, M.; Hagsten, E. A management perspective on threats to Cultural World Heritage Sites. Int. J. Herit. Stud. 2023, 29, 167–183. [Google Scholar] [CrossRef]
  68. Fan, J.; Chen, Y.; Zheng, L. Artificial Intelligence for Routine Heritage Monitoring and Sustainable Planning of the Conservation of Historic Districts: A Case Study on Fujian Earthen Houses (Tulou). Buildings 2024, 14, 1915. [Google Scholar] [CrossRef]
  69. Fiorini, L.; Conti, A.; Pellis, E.; Bonora, V.; Masiero, A.; Tucci, G. Machine Learning-Based Monitoring for Planning Climate-Resilient Conservation of Built Heritage. Drones 2024, 8, 249. [Google Scholar] [CrossRef]
  70. Florescu, O.; Ichim, P.; Sfîcă, L.; Kadhim-Abid, A.L.; Sandu, I.; Nănescu, M. Risk Assessment of Artifact Degradation in a Museum, Based on Indoor Climate Monitoring—Case Study of “Poni-Cernătescu” Museum from Iași City. Appl. Sci. 2022, 12, 3313. [Google Scholar] [CrossRef]
  71. Frasca, F.; Verticchio, E.; Cornaro, C.; Siani, A.M. Performance assessment of hygrothermal modelling for diagnostics and conservation in an Italian historical church. Build. Environ. 2021, 193, 107672. [Google Scholar] [CrossRef]
  72. Galantucci, R.A.; Musicco, A.; Verdoscia, C.; Fatiguso, F. Machine Learning for the Semi-Automatic 3D Decay Segmentation and Mapping of Heritage Assets. Int. J. Archit. Herit. 2023, 1–19. [Google Scholar] [CrossRef]
  73. García-Florentino, C.; Maguregui, M.; Carrero, J.A.; Morillas, H.; Arana, G.; Madariaga, J.M. Development of a cost effective passive sampler to quantify the particulate matter depositions on building materials over time. J. Clean. Prod. 2020, 268, 122134. [Google Scholar] [CrossRef]
  74. Gibeaux, S.; Martínez-Garrido, M.I.; Vázquez, P.; Thomachot-Schneider, C.; Fort, R. Wireless environmental monitoring coupled to NDT for decay risk analysis (at St. Joseph Chapel in Reims, France). Sens. Actuators A Phys. 2018, 272, 102–113. [Google Scholar] [CrossRef]
  75. Giglio, F.; Frontera, P.; Malara, A.; Armocida, F. Materials and Climate Change: A Set of Indices as the Benchmark for Climate Vulnerability and Risk Assessment for Tangible Cultural Heritage in Europe. Sustainability 2024, 16, 2067. [Google Scholar] [CrossRef]
  76. Haznedar, B.; Bayraktar, R.; Ozturk, A.E.; Arayici, Y. Implementing PointNet for point cloud segmentation in the heritage context. Herit. Sci. 2023, 11, 2. [Google Scholar] [CrossRef]
  77. Hedayatnia, H.; Top, S.; Caluwaerts, S.; Kotova, L.; Steeman, M.; Van Den Bossche, N. Evaluation of alaro-0 and remo regional climate models over iran focusing on building material degradation criteria. Buildings 2021, 11, 376. [Google Scholar] [CrossRef]
  78. Ilieș, A.; Caciora, T.; Marcu, F.; Berdenov, Z.; Ilieș, G.; Safarov, B.; Hodor, N.; Grama, V.; Shomali, M.A.A.; Ilies, D.C.; et al. Analysis of the Interior Microclimate in Art Nouveau Heritage Buildings for the Protection of Exhibits and Human Health. Int. J. Environ. Res. Public Health 2022, 19, 16599. [Google Scholar] [CrossRef]
  79. Ladiana, D.; Di Sivo, M. Programmed conservation of historical and architectural heritage. tools for optimising a process based on knowledge and information. Int. J. Des. Nat. Ecodyn. 2019, 14, 229–240. [Google Scholar] [CrossRef]
  80. Leijonhufvud, G. Making sense of climate risk information: The case of future indoor climate risks in Swedish churches. Clim. Risk Manag. 2016, 13, 76–87. [Google Scholar] [CrossRef]
  81. Leissner, J.; Kilian, R.; Kotova, L.; Jacob, D.; Mikolajewicz, U.; Broström, T.; Ashley-Smith, J.; Schellen, H.L.; Martens, M.; Van Schijndel, J.; et al. Climate for culture: Assessing the impact of climate change on the future indoor climate in historic buildings using simulations. Herit. Sci. 2015, 3, 38. [Google Scholar] [CrossRef]
  82. Leon, I.; Pérez, J.J.; Senderos, M. Advanced techniques for fast and accurate heritage digitisation in multiple case studies. Sustainability 2020, 12, 6068. [Google Scholar] [CrossRef]
  83. Lerario, A.; Varasano, A. An IoT smart infrastructure for S. Domenico Church in Matera’s “Sassi”: A multiscale perspective to built heritage conservation. Sustainability 2020, 12, 6553. [Google Scholar] [CrossRef]
  84. Lerma, C.; Borràs, J.G.; Mas, Á.; Torner, M.E.; Vercher, J.; Gil, E. Evaluation of hygrothermal behaviour in heritage buildings through sensors, CFD modelling and IRT. Sensors 2021, 21, 566. [Google Scholar] [CrossRef] [PubMed]
  85. Li, M. Disaster risk management of cultural heritage: A global scale analysis of characteristics, multiple hazards, lessons learned from historical disasters, and issues in current DRR measures in world heritage sites. Int. J. Disaster Risk Reduct. 2024, 110, 104633. [Google Scholar] [CrossRef]
  86. Lin, H.; Huang, L.; Chen, Y.; Zheng, L.; Huang, M.; Chen, Y. Research on the Application of CGAN in the Design of Historic Building Facades in Urban Renewal—Taking Fujian Putian Historic Districts as an Example. Buildings 2023, 13, 1478. [Google Scholar] [CrossRef]
  87. Luo, S.; Wang, H. Digital Twin Research on Masonry–Timber Architectural Heritage Pathology Cracks Using 3D Laser Scanning and Deep Learning Model. Buildings 2024, 14, 1129. [Google Scholar] [CrossRef]
  88. Marcelli, A.; Sebastianelli, M.; Conte, A.; Lucci, F.; Della Ventura, G. Micro-climatic investigation and particulate detection in indoor environments: The case of the historical museum of Bersaglieri in Rome. Rend. Lincei 2020, 31, 807–817. [Google Scholar] [CrossRef]
  89. Martinelli, L.; Calcerano, F.; Adinolfi, F.; Chianetta, D.; Gigliarelli, E. Open HBIM-IoT Monitoring Platform for the Management of Historical Sites and Museums. An Application to the Bourbon Royal Site of Carditello. Int. J. Archit. Herit. 2023, 1–18. [Google Scholar] [CrossRef]
  90. Marzouk, M.; ElSharkawy, M.; Elsayed, P.; Eissa, A. Resolving deterioration of heritage building elements using an expert system. Int. J. Build. Pathol. Adapt. 2020, 38, 721–735. [Google Scholar] [CrossRef]
  91. Matrone, F.; Martini, M. Transfer learning and performance enhancement techniques for deep semantic segmentation of built heritage point clouds. Virtual Archaeol. Rev. 2021, 12, 73–84. [Google Scholar] [CrossRef]
  92. Metals, M.; Lesinskis, A.; Borodinecs, A.; Turauskis, K. Study on indoor air temperature and moisture behaviour in historical churches. Energy Build. 2024, 310, 114083. [Google Scholar] [CrossRef]
  93. Mohamed El Abd, N. Smart monitoring solution through internet of things utilization to achieve resilient preservation. Ain Shams Eng. J. 2023, 14, 102176. [Google Scholar] [CrossRef]
  94. Moreno, M.; Prieto, A.J.; Ortiz, R.; Cagigas-Muñiz, D.; Becerra, J.; Garrido-Vizuete, M.A.; Segura, D.; Macías-Bernal, J.M.; Chávez, M.J.; Ortiz, P. Preventive Conservation and Restoration Monitoring of Heritage Buildings Based on Fuzzy Logic. Int. J. Archit. Herit. 2023, 17, 1153–1170. [Google Scholar] [CrossRef]
  95. Mouffok, M.; Zemmouri, N.; Aidaoui, L.; Lasbet, Y.; De Herde, A. Effects of building morphologies on CO2 air pollution case study: The vernacular urban fabric, city of Ghardaïa (Algeria). Asian J. Civ. Eng. 2017, 18, 1–19. [Google Scholar]
  96. Mustafin, M.; Nasrullah, M.; Abboud, M. 3D Modeling of Sidon Sea Castle Utilizing Terrestrial Laser Scanner Combined with Photogrammetry. Int. J. Geoinform. 2024, 20, 28–39. [Google Scholar] [CrossRef]
  97. Nunes, L.J.R.; Curado, A.; Lopes, S.I. Understanding Seasonal Indoor Radon Variability from Data Collected with a LoRa-Enabled IoT Edge Device. Appl. Sci. 2023, 13, 4735. [Google Scholar] [CrossRef]
  98. O’Neill, S.; Tett, S.F.B.; Donovan, K. Extreme rainfall risk and climate change impact assessment for Edinburgh World Heritage sites. Weather Clim. Extrem. 2022, 38, 100514. [Google Scholar] [CrossRef]
  99. O’Brien, G.; O’Keefe, P.; Jayawickrama, J.; Jigyasu, R. Developing a model for building resilience to climate risks for cultural heritage. J. Cult. Herit. Manag. Sustain. Dev. 2015, 5, 99–114. [Google Scholar] [CrossRef]
  100. Pereira, L.D.; Tavares, V.; Soares, N. Up-to-date challenges for the conservation, rehabilitation and energy retrofitting of higher education cultural heritage buildings. Sustainability 2021, 13, 2061. [Google Scholar] [CrossRef]
  101. Perez-Garcia, A.; Guardiola, A.P.; Gómez-Martínez, F.; Guardiola-Víllora, A. Energy-saving potential of large housing stocks of listed buildings, case study: L’Eixample of Valencia. Sustain. Cities Soc. 2018, 42, 59–81. [Google Scholar] [CrossRef]
  102. Prieto, A.J.; Verichev, K.; Silva, A.; de Brito, J. On the impacts of climate change on the functional deterioration of heritage buildings in South Chile. Build. Environ. 2020, 183, 107138. [Google Scholar] [CrossRef]
  103. Prizeman, O.; Pezzica, C.; Taher, A.; Boughanmi, M. Networking historic environmental standards to address modern challenges for sustainable conservation in HBIM. Appl. Sci. 2020, 10, 1283. [Google Scholar] [CrossRef]
  104. Quesada-Ganuza, L.; Garmendia, L.; Alvarez, I.; Roji, E. Vulnerability assessment and categorization against heat waves for the Bilbao historic area. Sustain. Cities Soc. 2023, 98, 104805. [Google Scholar] [CrossRef]
  105. Radulescu, C.; Stihi, C.; Ion, R.M.; Dulama, I.D.; Stanescu, S.G.; Stirbescu, R.M.; Teodorescu, S.; Gurgu, I.V.; Let, D.D.; Olteanu, L.; et al. Seasonal variability in the composition of particulate matter and the microclimate in cultural heritage areas. Atmosphere 2019, 10, 595. [Google Scholar] [CrossRef]
  106. Rajčić, V.; Skender, A.; Damjanović, D. An innovative methodology of assessing the climate change impact on cultural heritage. Int. J. Archit. Herit. 2018, 12, 21–35. [Google Scholar] [CrossRef]
  107. Rieser, A.; Pfluger, R.; Troi, A.; Herrera-Avellanosa, D.; Thomsen, K.E.; Rose, J.; Arsan, Z.D.; Akkurt, G.G.; Kopeinig, G.; Guyot, G.; et al. Integration of energy-efficient ventilation systems in historic buildings—Review and proposal of a systematic intervention approach. Sustainability 2021, 13, 2325. [Google Scholar] [CrossRef]
  108. Rodrigues, F.; Cotella, V.; Rodrigues, H.; Rocha, E.; Freitas, F.; Matos, R. Application of Deep Learning Approach for the Classification of Buildings’ Degradation State in a BIM Methodology. Appl. Sci. 2022, 12, 7403. [Google Scholar] [CrossRef]
  109. Ruggiero, G.; Marmo, R.; Nicolella, M. A methodological approach for assessing the safety of historic buildings’ Façades. Sustainability 2021, 13, 2812. [Google Scholar] [CrossRef]
  110. Sánchez, B.; de Oliveira Souza, M.; Vilanova, O.; Canela, M.C. Volatile organic compounds in the Spanish National Archaeological Museum: Four years of chemometric analysis. Build. Environ. 2020, 174, 106780. [Google Scholar] [CrossRef]
  111. Saraiva, N.B.; Pereira, L.D.; Gaspar, A.R.; Costa, J.J. Measurement of particulate matter in a heritage building using optical counters: Long-term and spatial analyses. Sci. Total Environ. 2023, 862, 160747. [Google Scholar] [CrossRef]
  112. Scatigno, C.; Moricca, C.; Tortolini, C.; Favero, G. The influence of environmental parameters in the biocolonization of the Mithraeum in the roman masonry of casa di Diana (Ostia Antica, Italy). Environ. Sci. Pollut. Res. 2016, 23, 13403–13412. [Google Scholar] [CrossRef]
  113. Shillito, L.M.; Namdeo, A.; Bapat, A.V.; Mackay, H.; Haddow, S.D. Analysis of fine particulates from fuel burning in a reconstructed building at Çatalhöyük World Heritage Site, Turkey: Assessing air pollution in prehistoric settled communities. Environ. Geochem. Health 2022, 44, 1033–1048. [Google Scholar] [CrossRef]
  114. Silva, H.E.; Henriques, F.M.A. Preventive conservation of historic buildings in temperate climates. The importance of a risk-based analysis on the decision-making process. Energy Build. 2015, 107, 26–36. [Google Scholar] [CrossRef]
  115. Silva, H.E.; Henriques, F.M.A. Hygrothermal analysis of historic buildings: Statistical methodologies and their applicability in temperate climates. Struct. Surv. 2016, 34, 12–23. [Google Scholar] [CrossRef]
  116. Silva, H.E.; Henriques, F.M.A. The impact of tourism on the conservation and IAQ of cultural heritage: The case of the Monastery of Jerónimos (Portugal). Build. Environ. 2021, 190, 160747. [Google Scholar] [CrossRef]
  117. Sitzia, F.; Peters, M.J.H.; Lisci, C. Climate change and its outcome on the archaeological areas and their building materials. The case study of Tharros (Italy). Digit. Appl. Archaeol. Cult. Herit. 2022, 25, e00226. [Google Scholar] [CrossRef]
  118. Tavolare, R.; Cabrera, E.; Verdoscia, C.; Buldo, M. A point cloud classification method for the Scan-to-BIM process in Architectural Heritage. Disegnarecon 2023, 16, 201–208. [Google Scholar] [CrossRef]
  119. Torres-González, M.; Prieto, A.J.; Alejandre, F.J.; Blasco-López, F.J. Digital management focused on the preventive maintenance of World Heritage Sites. Autom. Constr. 2021, 129, 103813. [Google Scholar] [CrossRef]
  120. Tysiac, P.; Sieńska, A.; Tarnowska, M.; Kedziorski, P.; Jagoda, M. Combination of terrestrial laser scanning and UAV photogrammetry for 3D modelling and degradation assessment of heritage building based on a lighting analysis: Case study—St. Adalbert Church in Gdansk, Poland. Herit. Sci. 2023, 11, 53. [Google Scholar] [CrossRef]
  121. Vandenabeele, L.; Loverdos, D.; Pfister, M.; Sarhosis, V. Deep Learning for the Segmentation of Large-Scale Surveys of Historic Masonry: A New Tool for Building Archaeology Applied at the Basilica of St Anthony in Padua. Int. J. Archit. Herit. 2023, 18, 1749–1761. [Google Scholar] [CrossRef]
  122. Varas-Muriel, M.J.; Fort, R.; Martínez-Garrido, M.I.; Zornoza-Indart, A.; López-Arce, P. Fluctuations in the indoor environment in Spanish rural churches and their effects on heritage conservation: Hygro-thermal and CO2 conditions monitoring. Build. Environ. 2014, 82, 97–109. [Google Scholar] [CrossRef]
  123. Wojtkowska, M.; Kedzierski, M.; Delis, P. Validation of terrestrial laser scanning and artificial intelligence for measuring deformations of cultural heritage structures. Meas. J. Int. Meas. Confed. 2021, 167, 108291. [Google Scholar] [CrossRef]
  124. Yan, L.; Chen, Y.; Zheng, L.; Zhang, Y. Application of computer vision technology in surface damage detection and analysis of shedthin tiles in China: A case study of the classical gardens of Suzhou. Herit. Sci. 2024, 12, 72. [Google Scholar] [CrossRef]
  125. Yiğit, A.Y.; Uysal, M. Automatic crack detection and structural inspection of cultural heritage buildings using UAV photogrammetry and digital twin technology. J. Build. Eng. 2024, 94, 109952. [Google Scholar] [CrossRef]
  126. Živković, V.; Džikić, V. Return to basics—Environmental management for museum collections and historic houses. Energy Build. 2015, 95, 116–123. [Google Scholar] [CrossRef]
  127. Metreau, E.; Young, K.E.; Eapen, S.G. World Bank Country Classifications by Income Level for 2024–2025. Available online: https://blogs.worldbank.org/en/opendata/world-bank-country-classifications-by-income-level-for-2024-2025 (accessed on 16 November 2024).
  128. Arsiwala, A.; Elghaish, F.; Zoher, M. Digital twin with Machine learning for predictive monitoring of CO2 equivalent from existing buildings. Energy Build. 2023, 284, 112851. [Google Scholar] [CrossRef]
Figure 1. Number of documents by year in the Scopus database (keyword “heritage” and “risk assessment”).
Figure 1. Number of documents by year in the Scopus database (keyword “heritage” and “risk assessment”).
Buildings 14 03979 g001
Figure 2. PRISMA2020 flow diagram illustrating the systematic review process. The arrows indicate the progression through the stages (Identification, Screening, and Included).
Figure 2. PRISMA2020 flow diagram illustrating the systematic review process. The arrows indicate the progression through the stages (Identification, Screening, and Included).
Buildings 14 03979 g002
Figure 3. A map of Keywords Co-occurrence Network visualized from Bibliometrix®.
Figure 3. A map of Keywords Co-occurrence Network visualized from Bibliometrix®.
Buildings 14 03979 g003
Figure 4. Distribution of Country Scientific Production from Bibliometrix®.
Figure 4. Distribution of Country Scientific Production from Bibliometrix®.
Buildings 14 03979 g004
Figure 5. Heritage preservation framework integrating AI, IoT, H-BIM, and DT. The figure outlines a seven-step process, detailing the Purpose and Technologies for each step, with arrows showing the sequential flow.
Figure 5. Heritage preservation framework integrating AI, IoT, H-BIM, and DT. The figure outlines a seven-step process, detailing the Purpose and Technologies for each step, with arrows showing the sequential flow.
Buildings 14 03979 g005
Table 1. Inclusion criteria and exclusion criteria for SLR.
Table 1. Inclusion criteria and exclusion criteria for SLR.
Criterion TypeInclusion CriteriaExclusion Criteria
Research areaArchitecture or Engineering or Environmental Science or Social SciencesNot related to Architecture or Engineering or Environmental Science or Social Sciences
DatabaseSCOPUSOutside SCOPUS
TopicHeritage building; risk assessment; air pollution; climate risk; IoT; Artificial IntelligenceNot related to heritage building
Year of publication2014–2024Outside the set range
Publication typePeer-reviewed academic paperOther types of publication (e.g., conference proceedings and books)
LanguageEnglishOther languages
Table 2. Searching query from keywords.
Table 2. Searching query from keywords.
KeywordsDocument Found (N)Advanced Query
Heritage
Building
Risk
assessment
314TITLE-ABS-KEY (heritage AND building AND risk AND assessment) AND PUBYEAR > 2013 AND PUBYEAR < 2025 AND (LIMIT-TO (DOCTYPE, “ar”)) AND (LIMIT-TO (LANGUAGE, “English”)) AND (LIMIT-TO (SUBJAREA, “ENGI”) OR LIMIT-TO (SUBJAREA, “ENVI”) OR LIMIT-TO (SUBJAREA, “SOCI”)) AND (LIMIT-TO (SRCTYPE, “j”))
Air
pollution
80TITLE-ABS-KEY (heritage AND building AND air AND pollution) AND PUBYEAR > 2013 AND PUBYEAR < 2025 AND (LIMIT-TO (DOCTYPE, “ar”)) AND (LIMIT-TO (LANGUAGE, “English”)) AND (LIMIT-TO (SUBJAREA, “ENGI”) OR LIMIT-TO (SUBJAREA, “ENVI”) OR LIMIT-TO (SUBJAREA, “SOCI”)) AND (LIMIT-TO (SRCTYPE, “j”))
Climate risk117TITLE-ABS-KEY (heritage AND building AND climate AND risk) AND PUBYEAR > 2013 AND PUBYEAR < 2025 AND (LIMIT-TO (DOCTYPE, “ar”)) AND (LIMIT-TO (LANGUAGE, “English”)) AND (LIMIT-TO (SUBJAREA, “ENGI”) OR LIMIT-TO (SUBJAREA, “ENVI”) OR LIMIT-TO (SUBJAREA, “SOCI”)) AND (LIMIT-TO (SRCTYPE, “j”))
Artificial
Intelligence
51TITLE-ABS-KEY (heritage AND building AND artificial AND intelligence) AND PUBYEAR > 2013 AND PUBYEAR < 2025 AND (LIMIT-TO (DOCTYPE, “ar”)) AND (LIMIT-TO (LANGUAGE, “English”)) AND (LIMIT-TO (SUBJAREA, “ENGI”) OR LIMIT-TO (SUBJAREA, “ENVI”) OR LIMIT-TO (SUBJAREA, “SOCI”)) AND (LIMIT-TO (SRCTYPE, “j”))
IoT21TITLE-ABS-KEY (heritage AND building AND iot) AND PUBYEAR > 2013 AND PUBYEAR < 2025 AND (LIMIT-TO (DOCTYPE, “ar”)) AND (LIMIT-TO (LANGUAGE, “English”)) AND (LIMIT-TO (SUBJAREA, “ENGI”) OR LIMIT-TO ( SUBJAREA, “ENVI”) OR LIMIT-TO (SUBJAREA, “SOCI”)) AND (LIMIT-TO (SRCTYPE, “j”))
Total                                  583
Table 3. Key parameters investigated in published studies on heritage buildings and environmental monitoring.
Table 3. Key parameters investigated in published studies on heritage buildings and environmental monitoring.
YearMonitored ParametersIndoorOutdoorSource
2014relative humidity, temperature, wind speed,
CO, SO2, NO, NO2, O3
-[11]
2014CO2, relative humidity, temperature[122]
2015relative humidity, temperature[51]
2015relative humidity, temperature, NO2,
SO2, CO2, O3, PM2.5, microflora
[3]
2015temperature, relative humidity, total precipitation (normal rain), wind speed, wind direction, global radiation, diffuse radiation, global counter radiation, cloud coverage, ground temperature, ground reflectance, air pressure[81]
2015relative humidity, temperature[113]
2015relative humidity, temperature, infrared radiation[126]
2016relative humidity, temperature, CO, CO2, light-[112]
2016relative humidity, temperature-[115]
2017air pollution (SO2, HNO3, O3, PM10) and meteorological conditions (temperature, precipitation, relative humidity)-[63]
2017CO2, temperature, wind speed and solar radiation-[95]
2018temperature, humidity, pressure, O3, NO, NO2, SO2-[74]
2018relative humidity, temperature[106]
2019relative humidity, temperature[48]
2019relative humidity, temperature-[60]
2019temperature, relative humidity, apparent temperature, PM10, PM2.5[105]
2020relative humidity, temperature, CO2, air change rates -[44]
2020PM-[73]
2020relative humidity, temperature, PM10, PM2.5- [88]
2020VOCs[110]
2021relative humidity, temperature-[19]
2021relative humidity, temperature, volumetric water content[71]
2021relative humidity, temperature[84]
2021relative humidity, temperature[116]
2022relative humidity-[53]
2022relative humidity, temperature[55]
2022outdoor and indoor air temperature, relative humidity, globe and surface temperature, air velocity[61]
2022SO2, NO2, O3, and PM10-[62]
2022relative humidity, temperature[70]
2022temperature, humidity, the amount of natural light and artificial light, CO2, PM2.5, PM10, HCHO, VOC, O2, SO2, O3, NO2, NO, H2S, CO, CH4-[78]
2022relative humidity, temperature[24]
2022PM2.5-[113]
2023CO2, PM10, PM2.5, temperature, relative humidity[47]
2023Rn, relative humidity, temperature-[97]
2023PM10, PM2.5[111]
2024temperature, relative humidity, concentrations of NO2, SO2,O3, CO2, acetic, formic acid [65]
2024air pollution (SO2, HNO3, O3, PM10) and meteorological conditions (temperature, precipitation, relative humidity, wind)-[66]
2024relative humidity, temperature[92]
The “✓” symbol indicates that the data is available. The “-” symbol indicates that it is unavailable.
Table 4. Methodologies and technologies used for risk management in heritage buildings.
Table 4. Methodologies and technologies used for risk management in heritage buildings.
SourceRisk TypeData SourceFrameworkMethodologyTechnology
[23]Structural integritySensor data from IoT infrastructureIoT architecture for cultural heritage monitoringDevelopment and testing of IoT sensorsWireless sensor networks (WSN)
[47]Microclimatic risk and energy efficiency Monitoring data and simulation results Energy efficiency and environmental quality assessmentDynamic energy simulations and in-field measurementsIoT sensors, CFD, dynamic energy models
[52]Implementation of AI in H-BIM using J48 algorithm for building managementH-BIM model of a case studyAI-based decision-making framework for building managementApplication of decision trees and AI for building managementJ48 decision tree algorithm, H-BIM platform, Geometric Description Language (GDL) scripting
[53]Prediction of indoor climate through MLML datasets from climate monitoring ML model XGBoost for prediction of relative humidityTime-series analysis with ML algorithmsML, XGBoost model, climate control systems
[25]Structural decay and damage detectionImage dataset from historic buildings DL for decay detectionImage-based DL using Mask R-CNNMask R-CNN, Computer Vision
[56]Hygrothermal assessmentHygrothermal monitoring and IoT sensor dataIoT-based environmental monitoring frameworkIoT sensor deployment and monitoring of environmental variablesIoT sensors, Heating, Ventilation and Air Conditioning (HVAC) systems, energy-saving models
[59]AI-based segmentation of point clouds for H-BIM Point cloud data from a case studyAI-based segmentation with H-BIM frameworkSemantic segmentation with multi-level and multi-resolutionML, point cloud segmentation, H-BIM tools
[26]Structural integrity and conservation planning3D survey data from case studyAI and H-BIM for heritage reconstructionSemantic segmentation and 3D reconstruction using ML H-BIM, Scan-to-BIM, ML, Geomagic Design X
[68]Wooden heritage structure damage detectionYOLOv8, preservation dataComputer Vision, AI-driven preservationYOLOv8 model for damage detection in wooden structuresComputer vision, Object detection technology
[72]Damage segmentation and decay mapping Photogrammetric and 3D point cloud data from architectural heritage case studies Semi-automatic decay detection and mapping using ML (supervised and unsupervised clustering) for 3D modelsCombination of photogrammetry and ML for unsupervised clustering of point clouds and supervised texture-based ML to detect decay.ML techniques (Random Forest, hierarchical clustering), photogrammetry, and 3D point cloud processing tools
[76]Automated segmentation and classification of heritage buildings using 3D point cloud data for HBIM integrationPoint cloud data collected from heritage buildings, processed using PointNetH-BIM enhanced by PointNet for automated segmentation and classification of heritage building elementsAI-based segmentation using PointNet applied to 140 rooms across 19 historical buildings. The training used five segmentation labels: walls, roofs, floors, doors, windowsPointNet DL architecture integrated with HBIM for efficient heritage building information modeling using 3D point cloud data
[79]Physical deterioration, material decayKnowledge-based conservation studies Programmed conservation approachAnalysis, monitoring, diagnosis, and data catalogingBIM, H-BIM
[83]Structural degradation IoT smart infrastructure monitoring, Wireless sensor networks (WSN)Preventive conservation and resilience enhancement using Structural Health Monitoring systems (SHM)Sensor-based monitoring, IoT integrationWSN, FIWARE platform, SHM, IoT devices
[85]Multiple natural and human-induced hazards affecting World Heritage (WH) sites globallyHistorical disaster records, management plans, and disaster risk reduction (DRR) strategies from 48 WH sites across 41 countriesDisaster risk management (DRM) for cultural heritage, integrating historical lessons with preventive strategiesAnalysis of past disasters, hazard mapping, vulnerability assessment, and development of DRM plansGeographic Information System (GIS) for hazard mapping, satellite imagery, early warning systems, and IoT sensors for disaster monitoring
[86]Architectural style inconsistency and urban renewalImage data of facades, Conditional Generative Adversarial Network (CGAN)-generated facade styles, field surveysUse of CGAN for facade design and urban cultural regenerationCGAN-based style generation, image processing, and ML for facade designCGAN, image processing software, data labeling tools
[87]Pathology cracks in masonry and timber architectural heritage3D laser scanning data, DL model for crack detection and identificationDT modeling for the detection, classification, and restoration of pathology cracksIntegration of 3D laser scanning with Mask R-CNN for crack area detection and Fully Convolutional Network (FCN) for single crack identification and calculation3D laser scanner (Leica BLK360), DL models (Mask R-CNN, FCN), point cloud data processing
[88]Indoor air quality impact on historical artifactsIndoor air quality data from Historical Museum Microclimatic investigation for conservationMonitoring of temperature, humidity, and particulate matter using low-cost sensorsArduino-based sensor system
[89]Environmental risks (temperature, humidity, VOC, CO2) affecting cultural heritage and buildings IoT sensors for monitoring temperature, relative humidity, VOCs, and CO2, integrated with the H-BIM platformPreventive conservation using real-time environmental monitoring and DT technologyIntegration of IoT sensor data with H-BIM for real-time monitoring and management, 3D modeling of building components, analysis of environmental conditionsWSN, H-BIM, IoT devices (Bosch BME 280 sensors, CCS811 for CO2 and VOCs), BIM Server, MongoDB (database management system), Node-RED (web-based editor for IoT data collection and management)
[24]Environmental risks (temperature fluctuations, humidity, wet/dry conditions) affecting heritage degradationIoT sensors from four cultural heritage sites A project integrating IoT for continuous microclimate monitoring with real-time risk assessmentIoT sensors monitoring temperature, humidity, wet/dry conditions, data transmitted via Narrowband Internet of Things (NB-IoT), edge processingNB-IoT-enabled smart sensors (Sensirion SHTC3, SAMYOUNG SY-DS-1L), Message Queue Telemetry Transport (MQTT) protocols, Node-RED visualization
[93]Degradation risks (humidity, temperature, structural issues and biological growth)Case studies from heritage buildings with IoT sensor deployment for continuous environmental monitoringIntegration of IoT and H-BIM for smart monitoring, real-time data collection, and resilient preservation managementIoT sensors tracking environmental factors (temperature, humidity, gas, vibration), integrated with H-BIM for predictive maintenanceIoT sensors, Radio Frequency Identification (RFID) for material tracking, AI for hazard detection, H-BIM for visualization and data management
[97]Seasonal indoor radon (Rn) variability and exposure risks, particularly during winter monthsLong-term monitoring of a heritage building using LoRa-enabled IoT edge deviceIoT monitoring for indoor radon and environmental factors, focusing on seasonal variation and IAQ-energy efficiency balanceContinuous data acquisition with Rn, temperature, humidity, and pressure sensors, using Fast Fourier Transform (FFT) analysis for trend detectionLoRa-enabled IoT edge device, RD200M Rn sensor, DHT11 temperature/humidity sensor, MPL3115A2 pressure sensor, FFT analysis
[102]Functional deterioration due to climate changeAnalysis of 79 heritage timber buildings across five locationsFuzzy logic model (FBSL2.0) for functional service life prediction under climate change scenarios (RCP2.6 and RCP8.5)AI-based analysis using fuzzy logic to model the functional deterioration under predicted climate change scenarios (2045–2069)Xfuzzy 3.0, predictive simulations for climate impact assessment (RCP2.6 and RCP8.5)
[103]Challenges in conservation and refurbishment of historic public buildings Survey data, historic datasets, photographic surveys, laser scansH-BIM for knowledge sharing and sustainable conservationML for object recognition, CFD modeling, parametric modeling of typical building systems (e.g., vaulted ceilings, ventilation systems)H-BIM, GIS mapping, CFD analysis, 3D laser scanning, DL for object recognition
[108]Degradation and anomaly detection in historic buildingsCase study datasets BIM integrated with DL models for anomaly detection and classification3D point cloud data acquisition, supervised DL Convolutional Neural Networks (CNN), and automated classification of building anomaliesTerrestrial Laser Scanner (TLS), CNN (ResNet architecture), Revit plug-in, Cyclone Register 360, Python-based DL models, Binder
[119]Preventive maintenance and resilience management of World Heritage Sites Expert system applying the fuzzy inference system (Art-Risk3.5) for assessing vulnerability and functional service lifeDigital management for preventive conservation and resilience of heritage sitesFuzzy inference system (FIS) to evaluate vulnerability, risks, and service life of heritage buildingsFuzzy logic algorithms, Art-Risk3.5, digital management tools, IoT devices for monitoring
[121]Data sensitivity to lighting and texture conditionsDrone and laser scanning survey of a case studyDL for Historical Masonry SegmentationConvolutional Neural Networks (CNN) for image segmentation of brickworkDrone photogrammetry, laser scanning, CNN algorithms
[123]Deformation monitoring of cultural heritage structures Terrestrial laser scanning (TLS), point clouds, 3D model of structuresValidation of deformation measurement techniques for historic buildingsTLS point cloud comparison, Artificial Neural Network (ANN) for deformation prediction, multi-epoch point cloud analysisTLS (Leica Scan Station 2), ANN, Cloud Compare software, 3D modeling
[124]Surface damage (water stains, scaling, color aberration, wide gaps)On-site photos from a case studyComputer Vision for Surface Damage DetectionML-based method using YOLOv4 for damage detectionComputer vision, YOLOv4 model
[125]Structural cracking and deformation monitoring Unmanned Aerial Vehicle (UAV) photogrammetry, Structure from Motion (SfM), 3D Digital TwinDT model for damage-augmented structural health monitoringUAV photogrammetry, SfM, automatic crack detection using ML, and comparison with manual measurementUAV (Anafi Parrot), Context Capture software, ML-based crack detection, SfM algorithms
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

Laohaviraphap, N.; Waroonkun, T. Integrating Artificial Intelligence and the Internet of Things in Cultural Heritage Preservation: A Systematic Review of Risk Management and Environmental Monitoring Strategies. Buildings 2024, 14, 3979. https://doi.org/10.3390/buildings14123979

AMA Style

Laohaviraphap N, Waroonkun T. Integrating Artificial Intelligence and the Internet of Things in Cultural Heritage Preservation: A Systematic Review of Risk Management and Environmental Monitoring Strategies. Buildings. 2024; 14(12):3979. https://doi.org/10.3390/buildings14123979

Chicago/Turabian Style

Laohaviraphap, Neeraparng, and Tanut Waroonkun. 2024. "Integrating Artificial Intelligence and the Internet of Things in Cultural Heritage Preservation: A Systematic Review of Risk Management and Environmental Monitoring Strategies" Buildings 14, no. 12: 3979. https://doi.org/10.3390/buildings14123979

APA Style

Laohaviraphap, N., & Waroonkun, T. (2024). Integrating Artificial Intelligence and the Internet of Things in Cultural Heritage Preservation: A Systematic Review of Risk Management and Environmental Monitoring Strategies. Buildings, 14(12), 3979. https://doi.org/10.3390/buildings14123979

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