Andrés José Prieto

Machine learning can contribute to more proactive, data-driven construction project management. However, most research efforts have focused on predicting final project outcomes, which may miss short-term variations that reveal emerging risks, thereby limiting the utility of their solutions as practical predictive tools for on-site project control. This paper develops and evaluates an early-warning machine learning model based on extreme gradient boosting (XGBoost) to classify next-month performance of building construction projects (Good, At-Risk, or Poor) using earned value management (EVM) and earned schedule (ES) metrics. Monthly EVM/ES records from 17 building projects were used along with schedule and cost performance indices to build the dataset. Three acceleration features were proposed to capture the trend in project performance. The model was trained on a time-aware experimental design using expanding-window cross-validation, light XGBoost tuning, probability calibration, and class-specific decision thresholds, and evaluated on a chronologically held-out test set. The model yielded a Macro- F 1 score of 0.760 on the test set, with a recall of 91% for “Poor” and 82% for “Good” classes, and a conservative behavior for “At-Risk” cases. Permutation importance and Shapley additive explanations (SHAP) analyses indicated that schedule indices are the main drivers of predicted performance outcomes, with cost and acceleration indicators providing complementary signals. In contrast to existing ML-based EVM studies that focus on final-outcome prediction, this study proposes a near-term multiclass early-warning approach that relies solely on standard EVM/ES metrics and achieves acceptable predictive performance using a relatively small dataset, providing guidance for designing feasible early-warning solutions under limited data availability and aligned with field managers’ information needs. The model can be implemented on-site using monthly control data to provide timely alerts on next-month project performance and support more proactive, data-driven project control.

The construction industry continues to face persistent challenges related to productivity, safety, sustainability, and fragmented project delivery. In this context, digital construction management has emerged as a strategic paradigm to enhance coordination, transparency, and decision-making across the project lifecycle. This editorial introduces the Special Issue on Digital Construction Management, which aims to consolidate current advances and critical perspectives on the managerial use of digital technologies in construction. Emphasis is placed on moving beyond isolated technological applications toward integrated digital ecosystems that align tools, processes, and human-centered practices. The Special Issue highlights the importance of linking digitalization with lean principles, collaborative frameworks, and performance-based decision-making to address uncertainty and complexity in construction projects. Overall, this issue seeks to foster dialogue between academia and industry and to position digital construction management as a key enabler of a more resilient and sustainable construction sector.

Modern Methods of Construction (MMC) represent a significant opportunity to address the stagnation of productivity in the construction sector, offering advantages such as reduced uncertainty in schedules and costs, minimized waste, and improved sustainability. However, in Chile, the adoption of MMC remains low due to limited information and the lack of early integration in project planning, leading to subjective decision-making. The OptimizIA project, developed by CDT, proposes an artificial intelligence (AI) model to predict and recommend the most suitable MMC solutions based on specific project conditions. This tool supports objective early decision-making in housing projects. The research involved piloting the model across nine projects, achieving a 77.7% match rate (exact or partial) between the MMC solutions historically used by companies and those recommended by the model. Positive user feedback suggests that OptimizIA has significant potential to enhance MMC adoption and optimize project performance. The findings indicate that AI can bridge gaps in early decision-making, offering actionable insights for integrating MMC solutions into construction projects. This study highlights the transformative role of AI in fostering productivity and sustainability in the construction industry, providing a foundation for future research and broader application.

As climate change continues to manifest its effects globally, the built environment faces escalating challenges in maintaining functionality and resilience against extreme weather events. This study analyses the interaction between functional service life and building resilience amidst climate change impacts, focusing on contrasting regions within Chile: the north and extreme south. Through a series of 158 case studies, this research examines how buildings in these regions adapt and endure under changing climatic conditions. Employing a qualitative and quantitative approach, data collection involved on-site inspections, interviews with stakeholders, and analysis of historical records. The findings underscore the importance of localized solutions tailored to the specific climatic challenges faced by each region. Furthermore, the research highlights the significance of proactive measures such as robust design, materials selection, and maintenance protocols in enhancing building resilience. By synthesizing insights from diverse climatic contexts, this study contributes to a broader understanding of the complex dynamics shaping the functional service life and resilience of buildings in Chile. Finally, the findings offer some guidance for different stakeholders seeking to enhance the built environment against the escalating impacts of climate change.

In Chile, photography arrived at the end of the 19th century together with the establishment of settlements of migrants from central Europe to southern Chile. The aims of this study are: (i) contextualise functional states of existing buildings in a specific sector of the historic Valdivia city centre; (ii) determine the state of conservation of the 42 cases under study; (iii) conduct qualitative and quantitative analyses of the main pathologies presented in the sample; (iv) perform an analysis focused on the urban context according to façade alignment, façade visibility index, and ratio of height versus street width; and (v) comparatively analyse the results achieved. This research reflects the importance of developing innovative procedures and mitigation strategies focused on preventive maintenance actions and future control systems that can maximise the resilience of a specific local context (Los Ríos region) and its surroundings. This study revealed that the number of pathologies detected was directly proportional to the state of conservation of the cases, classified by the functional service life model. Properties in Condition C were mainly affected by pathologies of a structural nature, which indicates that their functionality is not guaranteed, and a deeper inspection is needed for conservation and preservation actions.

Industrialized construction (IC) has experienced significant achievements in the development of innovative construction methods in response to the demands of the construction industry. In this context, building information modeling (BIM) integrates and manages data throughout prefabrication phases (design, bid, and procurement) within an IC project. However, manual tasks such as data transfer between BIM models and enterprise resource planning (ERP) systems results in delays and errors due to the constant change of versions and large data flow between the involved parties. In this context, this research proposes the implementation of novel methods based on artificial intelligence (AI) to integrate the required information contained in elements in the BIM model with construction materials databases normally managed by ERP systems to procure and purchase materials in IC enterprises. Using a case study approach, this research presents a workflow with the proposed methods whereas the results show that 81.57% of the elements were successfully identified, leading to a 63.47% reduction in the time compared to the manual assignment approach. Despite classifying a considerable percentage of the elements, it was identified that the implemented workflow depends on manual-dependent tasks during the design phase, such as modeling methodologies. This research contributes by providing new methods to improve IC projects and and is expected to contribute to future research related to AI-based.

Concerning one of the most important tasks of road structure management is the development of methods to predict their own functional or physical service life, which allows for objectively evaluating the state of road structures that are being considered or are already in operation with minimal labor and monetary incomes. Fuzzy logic systems constitute one successful methodology used for the valuation of pavement degradation. The clustering that focuses on pavement degradation conditions is normally performed by a visual inspection or using data collected by automated distress measurement equipment. Fuzzy sets theory provides different advantages for including a certain degree of uncertainty in the pavement performance index, subjective analysis, and maintenance assessments and can greatly improve consistency and reduce subjectivity in the degradation process. The main objective of this study was to develop a new fuzzy logic-based model to predict the functional service life of concrete pavement conditions and maintenance action evaluations concerning the airport network of Viña del Mar, Central Chile, and using pavement distress data from the Directorate of Airports, Ministry of Public Works of Chile. The proposed fuzzy logic model can be remarkably beneficial for design, construction, and maintenance, to evaluate design decisions for the measurable and objective valuation of deviations in the quality of construction, and for timely forecasting work based on continuous observing of the current infrastructure system.