Supervised Learning Framework Research Articles

Image-domain material decomposition for dual-energy CT using unsupervised learning with data-fidelity loss.

Dual-energy computed tomography (DECT) and material decomposition play vital roles in quantitative medical imaging. However, the decomposition process may suffer from significant noise amplification, leading to severely degraded image signal-to-noise ratios (SNRs). While existing iterative algorithms perform noise suppression using different image priors, these heuristic image priors cannot accurately represent the features of the target image manifold. Although deep learning-based decomposition methods have been reported, these methods are in the supervised-learning framework requiring paired data for training, which is not readily available in clinical settings. This work aims to develop an unsupervised-learning framework with data-measurement consistency for image-domain material decomposition in DECT. The proposed framework combines iterative decomposition and deep learning-based image prior in a generative adversarial network (GAN) architecture. In the generator module, a data-fidelity loss is introduced to enforce the measurement consistency in material decomposition. In the discriminator module, the discriminator is trained to differentiate the low-noise material-specific images from the high-noise images. In this scheme, paired images of DECT and ground-truth material-specific images are not required for the model training. Once trained, the generator can perform image-domain material decomposition with noise suppression in a single step. In the simulation studies of head and lung digital phantoms, the proposed method reduced the standard deviation (SD) in decomposed images by 97% and 91% from the values in direct inversion results. It also generated decomposed images with structural similarity index measures (SSIMs) greater than 0.95 against the ground truth. In the clinical head and lung patient studies, the proposed method suppressed the SD by 95% and 93% compared to the decomposed images of matrix inversion. Since the invention of DECT, noise amplification during material decomposition has been one of the biggest challenges, impeding its quantitative use in clinical practice. The proposed method performs accurate material decomposition with efficient noise suppression. Furthermore, the proposed method is within an unsupervised-learning framework, which does not require paired data for model training and resolves the issue of lack of ground-truth data in clinical scenarios.

A novel weakly supervised learning framework for hazardous item localization in terahertz security imaging

Terahertz security image analysis is crucial for non-contact, continuous, and covert human security, as well as the detection of dangerous items. However, current supervised detection algorithms require manual annotation of numerous pixels to identify areas containing hazardous items. This manual annotation task is repetitive and time-consuming. To address this issue, we propose an enhanced cascading pyramid weakly supervised learning framework (CPA) for terahertz images. In our framework, we utilize pixel-level image labels to segment terahertz images into grids of various sizes based on multi-instance learning (MIL). Each small grid is treated as an individual instance and generates pseudo-labels. By focusing on high-probability grids during image calculations, we expedite the training and inference speed. Experimental results demonstrate that our approach outperforms weakly supervised learning frameworks with similar levels of supervised information. In summary, our proposed method offers a viable and effective solution for inferring coarse-grained image-level labels while reducing annotation costs. It provides an efficient alternative to manual pixel-level annotation in the field of terahertz security image analysis.

Pixel-Wise Interstitial Lung Disease Interval Change Analysis: A Quantitative Evaluation Method for Chest Radiographs Using Weakly Supervised Learning.

Interstitial lung disease (ILD) is characterized by progressive pathological changes that require timely and accurate diagnosis. The early detection and progression assessment of ILD are important for effective management. This study introduces a novel quantitative evaluation method utilizing chest radiographs to analyze pixel-wise changes in ILD. Using a weakly supervised learning framework, the approach incorporates the contrastive unpaired translation model and a newly developed ILD extent scoring algorithm for more precise and objective quantification of disease changes than conventional visual assessments. The ILD extent score calculated through this method demonstrated a classification accuracy of 92.98% between ILD and normal classes. Additionally, using an ILD follow-up dataset for interval change analysis, this method assessed disease progression with an accuracy of 85.29%. These findings validate the reliability of the ILD extent score as a tool for ILD monitoring. The results of this study suggest that the proposed quantitative method may improve the monitoring and management of ILD.

Robust Seismic data denoising via self-supervised deep learning

Seismic data denoising is a critical component of seismic data processing, yet effectively removing erratic noise, characterized by its non-Gaussian distribution and high amplitude, remains a substantial challenge for conventional methods and deep learning (DL) algorithms. Supervised learning frameworks typically outperform others, but they require pairs of noisy datasets alongside corresponding clean ground truth, which is impractical for real-world seismic datasets. On the other hand, unsupervised learning methods, which do not rely on ground truth during training, often fall short in performance when compared to their supervised or traditional denoising counterparts. Moreover, current unsupervised deep learning methods fail to address the specific challenges posed by erratic seismic noise adequately. This paper introduces a novel zero-shot unsupervised DL framework designed specifically to mitigate random and erratic noise, with a particular emphasis on blending noise. Drawing inspiration from Noise2Noise and data augmentation principles, we present a robust self-supervised denoising network named ““Robust Noiser2Noiser.”.” Our approach eliminates the need for paired noisy and clean datasets as required by supervised methods or paired noisy datasets as in Noise2Noise (N2N). Instead, our framework relies solely on the original noisy seismic dataset. Our methodology generates two independent re-corrupted datasets from the original noisy dataset, using one as the input and the other as the training target. Subsequently, we employ a deep-learning-based denoiser, DnCNN, for training purposes. To address various types of random and erratic noise, the original noisy dataset is re-corrupted with the same noise type. Detailed explanations for generating training input and target data for blended data are provided in the paper. We apply our proposed network to both synthetic and real marine data examples, demonstrating significantly improved noise attenuation performance compared to traditional denoising methods and state-of-the-art unsupervised learning methods.

Artificial Intelligence for safety and reliability: A descriptive, bibliometric and interpretative review on machine learning

This research provides a structured review of studies that utilize Artificial Intelligence for safety and reliability. In particular, it focuses on Machine Learning techniques to perform fault detection and diagnosis, anomaly detection, system prognosis, reliability analysis, and risk assessment of engineering-related systems across the industry. Relevant studies were identified through clear research questions, screened, and assessed for eligibility. Explicit inclusion and exclusion criteria were defined to verify the suitability of the records. The analysis encompasses a descriptive, bibliometric, and interpretative review. The descriptive analysis details how different ML approaches are adapted and implemented across various domains of safety and reliability. The bibliometric analysis provides in-depth and comprehensive statistics, covering aspects such as data types used, preprocessing steps undertaken, and categories of ML algorithms employed. The interpretative analysis offers a critical and forward-looking perspective on the current state of the field. A total of 308 papers were analyzed, mostly adopting supervised learning frameworks (81%) and addressing fault detection and diagnosis (57%) in more than 16 different industrial fields. The outcome of this study reflects the rapid development of this cross-cutting and interdisciplinary research field and highlights the potential for future improvement in the data-driven operational safety of industrial plants. Challenges and limitations have been highlighted and discussed, including data availability and label scarcity, data quality, trust and explainability, and interdisciplinary collaboration. Additionally, suggestions on potential solutions to overcome existing limitations and outline future directions are provided.

A building change detection framework with patch-pairing single-temporal supervised learning and metric guided attention mechanism

Building change detection (CD) aims to detect changes in buildings from bi-temporal pairwise images obtained at different times. Typically, a deep learning-based building CD algorithm requires bi-temporal samples with significant building changes for training. However, obtaining such bi-temporal samples is challenging because building changes have a low probability of occurrence. Fortunately, it is relatively simple to obtain single-temporal samples that include a substantial number of buildings. By using these single-temporal building samples, pseudo bi-temporal building change samples can be generated, which can effectively address the problem of limited available bi-temporal building change samples. In view of that, this study proposes a metric guided single-temporal supervised learning framework that uses single-temporal building samples for building CD. In the proposed framework, patch-pairing single-temporal supervised learning (PPSL) adopts a patch-pairing method to construct pseudo bi-temporal building change samples, while equipping the network to effectively suppresses the negative impact of geometric offset and radiation difference in real samples. To further suppress the impact of radiation difference and enhance the effectiveness of our framework, a metric-guided spatial attention module (MGSAM) is designed to minimize the intra-class feature differences between temporal samples and augment the spatial context modeling ability. The proposed method is verified by experiments on different datasets, and the results demonstrate that the proposed method can outperform the existing methods and achieve superior performance.

LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions

Implicit 3D surface reconstruction of an object from its partial and noisy 3D point cloud scan is the classical geometry processing and 3D computer vision problem. In the literature, various 3D shape representations have been developed, differing in memory efficiency and shape retrieval effectiveness, such as volumetric, parametric, and implicit surfaces. Radial basis functions provide memory-efficient parameterization of the implicit surface. However, we show that training a neural network using the mean squared error between the ground-truth implicit surface and the linear basis-based implicit surfaces does not converge to the global solution. In this work, we propose locally supported compact radial basis functions for a linear representation of the implicit surface. This representation enables us to generate 3D shapes with arbitrary topologies at any resolution due to their continuous nature. We then propose a neural network architecture for learning the linear implicit shape representation of the 3D surface of an object. We learn linear implicit shapes within a supervised learning framework using ground truth Signed-Distance Field (SDF) data for guidance. The classical strategies face difficulties in finding linear implicit shapes from a given 3D point cloud due to numerical issues (requires solving inverse of a large matrix) in basis and query point selection. The proposed approach achieves better Chamfer distance and comparable F-score than the state-of-the-art approach on the benchmark dataset. We also show the effectiveness of the proposed approach by using it for the 3D shape completion task.

Spatial-Logic-Aware Weakly Supervised Learning for Flood Mapping on Earth Imagery

Flood mapping on Earth imagery is crucial for disaster management, but its efficacy is hampered by the lack of high-quality training labels. Given high-resolution Earth imagery with coarse and noisy training labels, a base deep neural network model, and a spatial knowledge base with label constraints, our problem is to infer the true high-resolution labels while training neural network parameters. Traditional methods are largely based on specific physical properties and thus fall short of capturing the rich domain constraints expressed by symbolic logic. Neural-symbolic models can capture rich domain knowledge, but existing methods do not address the unique spatial challenges inherent in flood mapping on high-resolution imagery. To fill this gap, we propose a spatial-logic-aware weakly supervised learning framework. Our framework integrates symbolic spatial logic inference into probabilistic learning in a weakly supervised setting. To reduce the time costs of logic inference on vast high-resolution pixels, we propose a multi-resolution spatial reasoning algorithm to infer true labels while training neural network parameters. Evaluations of real-world flood datasets show that our model outperforms several baselines in prediction accuracy. The code is available at https://github.com/spatialdatasciencegroup/SLWSL.

Short term forecasting of persistent air quality deterioration events in the metropolis of Sao Paulo

Air pollution is one of the main environmental problems in metropolitan areas. Negative impacts to human health are intensified when poor air quality conditions persist for many consecutive days, with gradual accumulation of pollutants in the atmosphere. Persistent air quality deterioration events are typically associated with occurrence of stagnant atmospheric conditions and reach the regional scale. In this study, data-driven models were developed to forecast the occurrence of persistent air pollution events of inhalable particulate matter (PM10) and ozone (O3) in the metropolis of Sao Paulo, Brazil. On average, 8 events per year were observed between 2005 and 2022, comprising 73 event days per year. The logistic regression method was used in a supervised learning framework. Daily timeseries of surface weather variables were used as predictors. In the case of PM10, a consistent long-term decrease in the number events impacted the model performance. The PM10 model benefited from the restriction of the training set to recent years, with a significant increase in the model accuracy despite the reduction in the volume of data. The final models correctly reproduced the seasonal distribution of events, with overall accuracies of 0.92 and 0.87 for O3 and PM10, respectively, in 2022. Despite the fact that persistent exceedance events are relatively rare, the models were able to detect 81% and 97% of the event days in 2022, respectively for O3 and PM10. Daily maximum temperature was an important predictor, increasing the event odds by 483% (O3) and 84% (PM10). The classification models developed in this study can successfully forecast the occurrence of regional air pollution events concerning both primary and secondary air pollutants, which have different drivers for accumulation in the atmosphere. The models require simple input data and low computational resources, aiming to stimulate future usage by the general public and decision-makers, in order to mitigate exposure to harmful air pollutant concentrations.

Transforming two-dimensional tensor networks into quantum circuits for supervised learning

There have been numerous quantum neural networks reported, but they struggle to match traditional neural networks in accuracy. Given the huge improvement of the neural network models’ accuracy by two-dimensional tensor network (TN) states in classical tensor network machine learning (TNML), it is promising to explore whether its application in quantum machine learning can extend the performance boundary of the models. Here, we transform two-dimensional TNs into quantum circuits for supervised learning. Specifically, we encode two-dimensional TNs into quantum circuits through rigorous mathematical proofs for constructing model ansätze, including string-bond states, entangled-plaquette states and isometric TN states. In addition, we propose adaptive data encoding methods and combine with TNs. We construct a tensor-network-inspired quantum circuit (TNQC) supervised learning framework for transferring TNML from classical to quantum, and build several novel two-dimensional TN-inspired quantum classifiers based on this framework. Finally, we propose a parallel quantum machine learning method for multi-class classification to construct 2D TNQC-based multi-class classifiers. Classical simulation results on the MNIST benchmark dataset show that our proposed models achieve the state-of-the-art accuracy performance, significantly outperforming other quantum classifiers on both binary and multi-class classification tasks, and beat simple convolutional classifiers on a fair track with identical inputs. The noise resilience of the models makes them successfully run and work in a real quantum computer.

Enhancing the Damage Detection and Classification of Unknown Classes with a Hybrid Supervised–Unsupervised Approach

Most damage-assessment strategies for dynamic systems only distinguish between undamaged and damaged conditions without recognizing the level or type of damage or considering unseen conditions. This paper proposes a novel framework for structural health monitoring (SHM) that combines supervised and unsupervised learning techniques to assess damage using a system’s structural response (e.g., the acceleration response of big infrastructures). The objective is to enhance the benefits of a supervised learning framework while addressing the challenges of working in an SHM context. The proposed framework uses a Linear Discriminant Analysis (LDA)/Probabilistic Linear Discriminant Analysis (PLDA) strategy that enables learning the distributions of known classes and the performance of probabilistic estimations on new incoming data. The methodology is developed and proposed in two versions. The first version is used in the context of controlled, conditioned monitoring or for post-damage assessment, while the second analyzes the single observational data. Both strategies are built in an automatic framework able to classify known conditions and recognize unseen damage classes, which are then used to update the classification algorithm. The proposed framework’s effectiveness is first tested considering the acceleration response of a numerically simulated 12-degree-of-freedom system. Then, the methodology’s practicality is validated further by adopting the experimental monitoring data of the benchmark study case of the Z24 bridge.

Weakly supervised crack segmentation using crack attention networks on concrete structures

Crack detection or segmentation on concrete structures is a vital process in structural health monitoring (SHM). Though supervised machine learning techniques have gained tremendous success in this domain, data collection and annotation continue to be challenging. Image data collection is challenging, tedious, and laborious, including accessing representative datasets and manually labeling training data in the SHM domain. According to the literature, there are significant issues with the hand-annotation of image data. To address this gap, this paper proposes a two-stage weakly supervised learning framework utilizing a novel “crack attention network (CrANET)” with attention mechanism to detect and segment cracks on images with no human annotations in pixel-level labels. This framework classifies concrete surface images into crack or no-cracks and then uses gradient class activation mapping visualization to generate crack segmentation. Professionals and domain experts subsequently evaluate these segmentation results via a human expert validation study. As the literature suggests that weakly supervised learning is a limited practice in SHM, this research title will motivate researchers in SHM to research and develop a weakly supervised learning approach processing as state of the art.

Choice of training label matters: how to best use deep learning for quantitative MRI parameter estimation

Deep learning (DL) is gaining popularity as a parameter estimation method for quantitative MRI. A range of competing implementations have been proposed, relying on either supervised or self-supervised learning. Self-supervised approaches, sometimes referred to as unsupervised, have been loosely based on auto-encoders, whereas supervised methods have, to date, been trained on groundtruth labels. These two learning paradigms have been shown to have distinct strengths. Notably, self-supervised approaches offer lower-bias parameter estimates than their supervised alternatives. This result is counterintuitive – incorporating prior knowledge with supervised labels should, in theory, lead to improved accuracy. In this work, we show that this apparent limitation of supervised approaches stems from the naïve choice of groundtruth training labels. By training on labels which are deliberately not groundtruth, we show that the low-bias parameter estimation previously associated with self-supervised methods can be replicated – and improved on – within a supervised learning framework. This approach sets the stage for a single, unifying, deep learning parameter estimation framework, based on supervised learning, where trade-offs between bias and variance are made by careful adjustment of training label.

Enabling Graph Neural Networks for Semi-Supervised Risk Prediction in Online Credit Loan Services

Graph neural networks (GNNs) are playing exciting roles in the application scenarios where features are hidden in information associations. Fraud prediction of online credit loan services (OCLSs) is such a typical scenario. But it has another rather critical challenge, i.e., the scarcity of data labels. Fortunately, GNNs can also cope with this problem due to their good ability of semi-supervised learning by mining structure and feature information within graphs. Nevertheless, the gain of internal information is often too limited to help GNNs handle the extreme deficiency of labels with high performance beyond the basic requirement of fraud prediction in OCLSs. Therefore, adding labels from the experts, such as manually adding labels through rules, has become a logical practice. However, the existing rule engines for OCLSs have the confliction problem among continuously accumulated rules. To address this issue, we propose a Snorkel-based Semi-Supervised GNN (S3GNN). Under S3GNN, we specially design an upgraded version of the rule engines, called Graph-Oriented Snorkel (GOS), a graph-specific extension of Snorkel, a widely used weakly supervised learning framework, to design rules by subject matter experts (SMEs) and resolve confliction. In particular, in the graph of an anti-fraud scenario, each node pair may have multiple different types of edges, so we propose the Multiple Edge-Types Based Attention mechanism. In general, for the heterogeneous information and multiple relations in the graph, we first obtain the embedding of applicant nodes by aggregating the representation of attribute nodes, and then use the attention mechanism to aggregate neighbor nodes on multiple meta-paths to get ultimate applicant node embedding. We conduct experiments over the real-life data of a large financial platform. The results demonstrate that S3GNN can outperform the state-of-the-art methods, including the method of pilot platform.

Supervised Stratified Subsampling for Predictive Analytics

Predictive analytics involves the use of statistical models to make predictions; however, the power of these techniques is hindered by ever-increasing quantities of data. The richness and sheer volume of big data can have a profound effect on computation time and/or numerical stability. In the current study, we develop a novel approach to subsampling with the aim of overcoming this issue when dealing with regression problems in a supervised learning framework. The proposed method integrates stratified sampling and is model-independent. We assess the theoretical underpinnings of the proposed subsampling scheme, and demonstrate its efficacy in yielding reliable predictions with desirable robustness when applied to different statistical models.

Learning peptide properties with positive examples only.

Deep learning can create accurate predictive models by exploiting existing large-scale experimental data, and guide the design of molecules. However, a major barrier is the requirement of both positive and negative examples in the classical supervised learning frameworks. Notably, most peptide databases come with missing information and low number of observations on negative examples, as such sequences are hard to obtain using high-throughput screening methods. To address this challenge, we solely exploit the limited known positive examples in a semi-supervised setting, and discover peptide sequences that are likely to map to certain antimicrobial properties via positive-unlabeled learning (PU). In particular, we use the two learning strategies of adapting base classifier and reliable negative identification to build deep learning models for inferring solubility, hemolysis, binding against SHP-2, and non-fouling activity of peptides, given their sequence. We evaluate the predictive performance of our PU learning method and show that by only using the positive data, it can achieve competitive performance when compared with the classical positive-negative (PN) classification approach, where there is access to both positive and negative examples.

Improving self-supervised learning model for audio spoofing detection with layer-conditioned embedding fusion

The application of voice recognition systems has increased by a great deal with technology. This has allowed adversaries to falsely claim access to these systems by spoofing the identity of a target speaker. The existing supervised learning (SL)-based countermeasures are yet to provide a complete solution against the newly evolving spoofing attacks. To tackle this problem, we explore self-supervised learning (SSL)-based frameworks. At first, we implement widely used SSL frameworks, where our target is identifying spoofed speech. We report a considerable performance improvement over the SL state-of-the-art baseline as a whole. Then, we perform an attack-wise comparative analysis between SL and SSL frameworks. While the SSL performs better in most cases, there are certain attacks where the SL outperforms it. Hence, we hypothesize that there is scope to jointly utilize information effectively included by both these models for better performance. To do that, we first perform conventional weighted score fusion between the SL and best-performing SSL models, which reduces the EER, outperforming both the state-of-the-art SL and best-performing SSL framework. Then, we propose an embedding fusion scheme that minimizes the embedding distribution between the selected SL and SSL representations. To select the appropriate layers, we perform a comprehensive statistical analysis. The proposed fusion scheme outperforms the score fusion method and shows that the SSL performance can be improved by effectively including learned knowledge from the SL framework. The final EER achieved on the ASVspoof 2019 logical access (LA) database is 0.177%, a significant improvement over our baseline. Using the ASVspoof 2021 LA as a blind evaluation dataset, our proposed embedding fusion scheme reduces the EER to 2.666%.

Knowledge evolution learning: A cost-free weakly supervised semantic segmentation framework for high-resolution land cover classification

Despite the success of deep learning in land cover classification, high-resolution (HR) land cover mapping remains challenging due to the time-consuming and labor-intensive process of collecting training samples. Many global land cover products (LCP) can reflect the low-level commonality (LLC) knowledge of land covers, such as basic shape and underlying semantic information. Therefore, we expect to use LCP as weakly supervised information to guide the semantic segmentation of HR images. We regard high-level specialty (HLS) knowledge as HR information unavailable in the LCP. We believe LLC knowledge can gradually evolve into HLS knowledge through self-active learning. Hence, we design a knowledge evolution learning strategy from LLC to HLS knowledge and correspondingly devise a knowledge evolution weakly supervised learning framework (KE-WESUP) based on LCP. KE-WESUP mainly includes three tasks: (1) Abstraction of LLC knowledge. KE-WESUP first adopts a training method based on superpixel to alleviate the inconsistency between LCP and HR images and directly learns the LLC knowledge from LCP according to the feature-fitting capacity of convolutional neural networks. (2) Automatic exploration of HLS knowledge. We propose a dynamic label optimization strategy to obtain a small number of point labels with high confidence and encourage the model to automatically mine HLS knowledge through the knowledge exploration mechanism, which prompts the model to adapt to complexHR scenes. (3) Dynamic interaction of LLC and HLS knowledge. We adopt the consistency regularization method to achieve further optimization and verification of LLC and HLS knowledge. To verify the effectiveness of KE-WESUP, we conduct experiments on USDA National Agriculture Imagery Program (1 m) and GaoFen-2 (1 m) data using WolrdCover (10 m) as labels. The results show that KE-WESUP achieves outstanding results in both experiments, which has significant advantages over existing weakly supervised methods. Therefore, the proposed method has great potential in utilizing the prior information of LCP and is expected to become a new paradigm for large-scale HR land cover classification.

Investigation of Monte Carlo trained CNNs for neutronics predictions of typical and atypical PWR assemblies

The use of Machine Learning (ML) has gained significant attention in recent years for use in the development of surrogate models capable of predicting various neutronics parameters in Pressurized Water Reactors (PWRs). These approaches aim to provide fast and accurate approximations of conventional model outputs which are typically both computationally expensive and time-consuming to run. A novel supervised learning framework LatticeNet, employing Artificial Neural Networks (ANNs) and computer vision techniques, has been shown to be particularly useful in the prediction of assembly and pin-level parameters such as multiplication factor or pin powers. This framework was validated using deterministically-generated training data for a standard fuel assembly, representing best-case input conditions. This paper investigates the performance of LatticeNet as well as the tools developed alongside when given Monte Carlo-generated inputs and assemblies of varying pin dimensions, assessing the network’s tolerance to training data uncertainty and atypical configurations.

Carbon emission analysis of precast concrete building Construction: A study on component transportation phase using Artificial Neural Network

Off-site construction has been widely adopted for its carbon reduction potential. However, the emissions from its transportation stage are not fully explored. Given the rising prominence of Battery Electric Vehicles (BEVs), this study explores their potential carbon reduction benefits during the transportation of prefabricated components by comparing emissions from Fossil Vehicles (FVs) and BEVs. An Artificial-Neural-Network-based emission model is developed to estimate the carbon emissions of both vehicle types. Specifically, the model collects the real-time carbon emission dynamics across varying external conditions, encompassing diverse transportation constraints, vehicle operational statuses, and road conditions. By employing a supervised learning framework, the transportation carbon emission coefficient of prefabricated components is determined. Comparative analysis reveals that BEVs consistently outperforms FVs, achieving a peak reduction rate of 47.76%. The negative correlation between the reduction rate of BEVs and factors like average speed and load rate underscores BEVs' advantage in urban transportation scenarios, where these factors tend to be low. Hence, the integration of BEVs in the transportation of prefabricated components is advocated. This study provides robust carbon emissions coefficients for BEVs in the transportation of prefabricated components, filling the gap in current estimation methods. These coefficients present a valuable tool for researchers, aiding in the accurate estimation of transportation carbon emissions and fostering the conceptualization of innovative carbon reduction tactics through BEV adoption.