Transportation agencies receive large volumes of free-form public comments describing infrastructure conditions, safety concerns, and service issues. These comments are often processed manually for downstream operational actions, which is time-consuming, inconsistent across reviewers, and difficult to scale, thereby limiting their value for operational decision-making. This study presents a machine learning and Large Language Model (LLM) framework for automated triage of free-form public comments, assigning each report to a three-level hierarchical taxonomy consisting of Category, Subcategory, and Final Decision. The proposed framework uses agency historical data together with retrieval-based evidence, where semantically similar past comments are provided to the LLM as contextual support to better align predictions with agency-specific labeling practices. The framework was evaluated using TF-IDF with Logistic Regression, TF-IDF with Linear SVM, embedding-based kNN with cosine similarity, few-shot LLM prompting, and retrieval-based LLM prompting. Results show that retrieval-based prompting achieved the best overall performance, with the highest accuracy at both the Category and Subcategory levels. At the Final Decision level, retrieval-based prompting slightly outperformed kNN, while few-shot prompting performed worse. Error analysis showed that many misclassifications were semantically plausible alternatives, reflecting the overlap across infrastructure-related complaint categories. When a second candidate label was allowed, further improving performance. Latency analysis also indicated that the framework can process more than 2000 comments in under 30 min, supporting faster and more consistent agency workflows.

The construction industry remains among the most hazardous, with workers in horizontal transportation infrastructure facing additional risks from dynamic work zones, live traffic exposure, and variable environmental conditions. Immersive technologies such as Virtual Reality (VR) and Augmented Reality (AR) offer new approaches to accident analysis and prevention, yet their applications toward improving occupational safety in transportation construction have not been comprehensively reviewed. This paper presents a systematic review of 54 studies published between 2016 and 2025 collected from two online databases (Transportation Research International Documentation and Web of Science). This review synthesizes how immersive technologies contribute to occupational risk assessment, safety training, and real-time hazard monitoring in the construction of roads, bridges, tunnels, and work zones. Each study is classified across two dimensions: the immersive medium (VR, AR, etc.) and the operational context within the construction lifecycle (onsite tools, offsite monitoring and planning, simulation-based analysis, and workforce education). This dual classification is the first to systematically map immersive technology applications for occupational safety, specifically within horizontal transportation infrastructure. The findings of this review demonstrate the unique use cases of each immersive medium, revealing that VR is primarily used for controlled experimentation and full-immersion remote analysis, whereas AR and handheld devices are preferred for field-deployed applications. Despite these promising capabilities, widespread adoption remains limited by hardware constraints, challenging field conditions, and organizational resistance. This suggests that future work should focus on safety systems tested in real-world settings and rigorously evaluated by domain experts to enable their integration into standard workplace risk management practices.

Efficient construction monitoring and project visualization are vital in civil engineering: they promote safety, minimize costs, and ensure adherence to design plans. With advances in reality capture techniques, such as LiDAR, point clouds have emerged as a powerful tool for digitizing largescale scenes with excellent accuracy. However, the challenges of processing and visualizing large-scale point cloud data remain significant, particularly for applications in horizontal infrastructure projects. In this case study, a point cloudbased digital reconstruction of an interchange conversion project was developed to aid in defining best practices for data processing of large-scale point clouds and to develop novel digital tools to enable remote construction site inspection and analysis. The obtained models are leveraged to provide insights on three advanced methodologies for data exploration: (1) desktop interfaces for accessible remote monitoring, (2) holographic interfaces for collaborative visualization, and (3) immersive virtual environments for enhanced interaction and simulation. These three methods are compared for accessibility, opportunity, and their potential to improve decision-making and project outcomes in construction monitoring and analysis.

The construction industry accounts for a significant portion of workplace fatalities in the United States. Health and safety hazards frequently go unrecognized, potentially leading to injuries and death. However, traditional computer vision methods are often limited to specific object detection tasks [e.g., personal protective equipment (PPE) compliance] and their adoption introduces challenges in interpreting complex, contextual hazard scenarios. Furthermore, the scarcity of annotated accident data hinders the development of fully supervised models. Consequently, this manuscript formally characterizes the performance of pretrained multimodal Artificial Intelligence (AI) for automating hazard recognition. Furthermore, the performance of such models is also tested on game engine-based synthetic data, to investigate whether it can be leveraged for data augmentation in order to overcome the scarcity of real-world training examples. To address these questions, this study formally evaluates the effectiveness of AI models over multiple iterations of the models’ architecture for the domain-specific application of automated construction hazard assessment from multimodal inputs. The research presented herein leverages publicly available pretrained vision-language models and evaluates their performance across three core tasks: binary hazard alerts, detailed hazard understanding, and automated citation generation. A dataset of annotated real-world construction images is presented to benchmark the performance of models. The dataset is also made public to provide a standardized means for comparing performance across different models. Results reported herein indicate that leading AI models can achieve high, although not perfect, recognition accuracy without fine-tuning. However, model performance varies across hazard categories, and newer generations show diminishing returns. Consequently, the study introduces and validates high-fidelity, game engine-based synthetic images as a solution. By generating high-fidelity digital images of dangerous activities, synthetic data can help bridge the scarcity of real-world hazard examples. This approach increases opportunities to improve these models with task-specific data, supporting continued progress beyond current limitations.