The modular building industry is increasingly challenged by small, highly customized orders, resulting in frequent changeover that can consume up to 30% of total production time. Reducing overall changeover time is crucial to address the high costs and scalability limitations in modular housing. Optimizing production sequences to minimize sequence-dependent changeover times is essential for reducing delays in customized building manufacturing. However, the lack of historical data and understanding of factors affecting changeover time for unobserved customization-driven changeover types hinders job-shop scheduling optimization and changeover time reduction. While data-driven methods are often employed to predict production-related times, they suffer from domain shift issues when models trained on standard products are applied to customized products. The absence of mechanisms to explain invariant causal relationships that drive changeover time changes during production reconfiguration further reduces the effectiveness of domain adaptation. This study addresses these challenges by introducing a causal-informed Generative Adversarial Network (GAN) framework that enhances prediction accuracy by incorporating causal relationships revealing the changeover time change mechanism. Integrating causal analysis, this framework identifies key factors that influence changeover times, enabling the GAN to generate synthetic data aligned with these relationships. The proposed method effectively adapts to domain shifts, thereby improving the accuracy of changeover time predictions, which in turn supports better job-shop scheduling and reduces time waste in customized manufacturing. In a case study involving the production of customized ductwork for modular buildings, the application of this causal-informed GAN framework demonstrated an improvement in prediction accuracy and generated optimized sequences that achieved 12%–25% reductions in total changeover time compared to historical production sequences. This indicates the practicality and effectiveness of the approach in highly customized manufacturing environments, providing support for optimizing production processes and lowering costs.

Generative artificial intelligence (GAI) has the potential to reshape workflows across the Architecture, Engineering, and Construction (AEC) sector. While previous research has offered valuable technical demonstrations and conceptual analyses, empirical evidence quantifying GAI-related impacts across AEC occupations and systematic assessment of adoption readiness remain limited. This study develops a domain-specific socio-technical evaluation framework that provides occupational-level analysis of technical capabilities, social risks, and adoption barriers across thirteen O*NET-defined AEC occupations. Data were collected through a six-month survey of 162 AEC professionals, complemented by six expert interviews and a systematic literature review. The findings reveal: (1) Technical Capability , measured using exposure scores ranging from −1 (low applicability) to +1 (high applicability), shows moderate applicability in design-oriented roles (e.g., architectural drafters: 0.16) and minimal alignment for site-based and manual activities (e.g., construction laborers: −0.89). (2) Social Risks , assessed on a 0–1 scale of concern, identify hallucinations (0.71), data privacy (0.70), and intellectual property issues (0.69) as critical concerns. (3) Socio-Technical Adoption highlights limited technical expertise (26.0%) and uncertain return on investment (16.8%) as primary barriers, while respondents emphasized the need for usage guidelines and standards (29.6%) and targeted training (29.2%) to facilitate responsible integration. Based on these findings, the study outlines strategic priorities for responsible GAI deployment, including AEC-specific standards, targeted workforce training, human-in-the-loop validation mechanisms, and domain-tailored digital infrastructure. The framework and empirical evidence provide a foundation for researchers, practitioners, and policymakers seeking to guide the safe and effective integration of GAI into AEC workflows. • A socio-technical evaluation framework tailored to AEC GAI integration. • Task- and occupation-level analysis of capability readiness across thirteen O*NET roles. • Quantitative assessment of risks, adoption barriers, and organizational support needs. • Evidence-based recommendations on guidelines, training, human oversight, and digital infrastructure.

Predicting separation errors in the daily tasks of air traffic controllers (ATCOs) is essential for the timely implementation of mitigation strategies before performance declines and the prevention of loss of separation and aircraft collisions. However, three challenges impede accurate separation errors forecasting: 1) compounding relationships between many human factors and control processes require sufficient operation process data to capture how separation errors occur and propagate within controller-in-the-loop processes; 2) previous human factor measurement approaches are disruptive to controllers’ daily operations because they use invasive sensors, such as electroencephalography (EEG) and electrocardiography (ECG), 3) errors accumulated in using the tasks and human behaviors for estimating system dynamics challenge accurate separation error predictions with sufficient leading time for proactive control actions. This study proposed a separation error prediction framework with a long leading time (>50 s) to address the above challenges, including 1) a multi-factorial model that characterizes the inter-relationships between task complexity, behavioral activity, cognitive load, and operational performance; 2) a multimodal data analytics approach to non-intrusively extract the task features (i.e., traffic density) from high-fidelity simulation systems and visual behavioral features (i.e., head pose, eyelid movements, and facial expressions) from ATCOs’ facial videos; 3) an encoder-decoder Long Short-Term Memory (LSTM) network to predict long-time-ahead separation errors by integrating multimodal features for reducing accumulated errors. A user study with six experienced ATCOs tested the proposed framework using the Phoenix Terminal Radar Approach Control (TRACON) simulator. The authors evaluated the model performance through two types of metrics: 1) point-level metrics, including precision, recall, and F1-score, and 2) sequence-level metrics, including alignment accuracy and sequence similarity. The results showed that 1) the model using the task and visual behavioral features significantly improved the prediction performance compared to the model using one single feature (eyelid movements), with an improvement of up to 26.95% in alignment accuracy for 10s-ahead prediction; 2) the model that combined task and visual behavioral features had a higher or comparable performance to models with different hybrid features, achieving an alignment accuracy of 82.38% for 50s-ahead error prediction; and (3) the proposed method outperformed three baseline models – Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU), and classic LSTM – by 8.21%, 3.47%, and 3.14% in alignment accuracy, respectively, for predicting 50s-ahead separation errors. These results suggest that the proposed model can effectively predict separation errors in air traffic control.

Maintenance planning of groundwater delivery infrastructure, such as canals, requires labor-intensive field inspection for properly allocating maintenance resources to sections of water infrastructure based on their deterioration conditions. Defective canal sections have cracks where the water delivery performance degrades. In practice, canals can be tens or even hundreds of miles long. Manual canal inspections could take weeks, while could hardly achieve comprehensive water leakage assessment. Another difficulty is that most cracks are developing under the water. Without drying up the canals, inspectors could not observe underwater conditions. They would have to assess visible parts of water facilities and environments (e.g., humidity changes and vegetation growths nearby) for prioritizing canal sections in terms of leaking risks. Even experienced inspectors need much time to complete a reliable canal condition assessment. This paper presents a deep-learning approach augmented by canal inspection knowledge to achieve automated and reliable water leak detection of canal sections from Landsat 8 satellite images. Such integration utilizes the domain knowledge of experienced inspectors in augmenting the deep-learning methods for more reliable image pattern classification that supports rapid canal condition assessment. Compared with machine learning algorithms trained by raw satellite images manually labeled as leaking, domain-knowledge-augmented deep learning algorithms use satellite image augmented by pixel-level land surface temperature (LST), fractional vegetation coverage (FVC) and Temperature Vegetation Dryness Index (TVDI) as training samples. Specifically, LST, FVC, and TVDI for each pixel are physical parameters derived from Landsat 8 satellite images by remote sensing methods. The “leaking” or “no-leaking” labels of the training samples are from the concrete surface inspection records collected during annual dry-ups of the canal from 2016 to 2019. Testing results on data sets collected for canals flowing through both urban and rural areas show that the proposed approach can achieve recall at 86%, precision at 86%, and accuracy at 85%. The precision, recall, and accuracy of the proposed approach are similar to a conventional deep learning algorithm that uses raw images for training while being more computationally efficient. The reason is that the new approach only processes three channels rather than the 11 channels in raw images. The authors also tested how different combinations of environmental features influence the performance of the algorithm. The results showed that two feature combinations: (LST, FVC) and (LST, FVC, TVDI) achieve the most robust performance in diverse geospatial environments.