Gaussian Mixture Model Research Articles

Low muscle density in children with osteogenesis imperfecta using opportunistic low-dose chest CT: a case-control study

BackgroundThe aim of the study was to investigate the muscle differences in children with osteogenesis imperfecta (OI) using opportunistic low-dose chest CT and to compare different methods for the segmentation of muscle in children.MethodsThis single center retrospective study enrolled children with OI and controls undergoing opportunistic low-dose chest CT obtained during the COVID pandemic. From the CT images, muscle size (cross-sectional area) and density (mean Hounsfield Units [HU]) of the trunk muscles were measured at the mid-T4 and the mid-T10 level using two methods, the fixed thresholds and the Gaussian mixture model. The Bland-Altman method was also used to compute the strength of agreement between two methods. Comparison of muscle results between OI and controls were analyzed with Student t tests.Results20 children with OI (mean age, 9.1 ± 3.3 years, 15 males) and 40 age- and sex-matched controls were enrolled. Mean differences between two methods were good. Children with OI had lower T4 and T10 muscle density than controls measured by the fixed thresholds (41.2 HU vs. 48.0 HU, p < 0.01; 37.3 HU vs. 45.9 HU, p < 0.01). However, children with OI had lower T4 muscle size, T4 muscle density, T10 muscle size and T10 muscle density than controls measured by the Gaussian mixture model (110.9 vs. 127.2 cm2, p = 0.03; 44.6 HU vs. 51.3 HU, p < 0.01; 72.6 vs. 88.0 cm2, p = 0.01; 41.6 HU vs. 50.3 HU, p < 0.01, respectively).ConclusionsChildren with OI had lower trunk muscle density indicating that OI might also impair muscle quality. Moreover, the fixed thresholds may not be suitable for segmentation of muscle in children.

Machine learning attack detection based-on stochastic classifier methods for enhancing of routing security in wireless sensor networks

Wireless Sensor Networks (WSNs) are vulnerable to attacks during data transmission, and many techniques have been proposed to detect and secure routing data. In this paper, we introduce a novel stochastic predictive machine learning approach designed to discern untrustworthy events and unreliable routing attributes, aiming to establish an artificial intelligence-based attack detection system for WSNs. Our methodology leverages real-time analysis of the features of simulated WSN routing data. By integrating Hidden Markov Models (HMM) with Gaussian Mixture Models (GMM), we develop a robust classification framework. This framework effectively identifies outliers, pinpoints malicious network behaviors from their origins, and categorizes them as either trusted or untrusted network activities. In addition, dimensionality reduction techniques are used to improve interpretability, reduce computation and processing time, extract uncorrelated features from network data, and optimize performances. The main advantage of our approach is to establish an efficient stochastic machine learning method capable of analyzing and filtering WSN traffic to prevent suspicious and unsafe data, reduce the large dissimilarity in the collected routing features, and rapidly detect attacks before they occur. In this work, we exploit a well-tuned data set that provides a lot of routing information without losing any data. The experimental results show that the proposed stochastic attack detection system can effectively identify and categorize anomalies in wireless sensor networks with high accuracy. The classification rates of the system were found to be around 83.65%, 84.94% and 94.55%, which is significantly better than the existing classification approaches. Furthermore, the proposed system showed a positive prediction value of 11.84% higher than the existing approaches.

Developing a quantitative multimodal and multi-scale, fully non-destructive technique for the study of iron archaeological artefacts

This article presents the methodology and initial findings of the SNSF Sinergia project CORINT. The project's objective is to elucidate the corrosion mechanisms affecting iron-based structures entrapped in various porous media. This paper focuses specifically on iron archaeological artefacts (IAAs) in soil. A novel multimodal quantitative imaging technique, which integrates neutron and X-ray computed tomography (NX-CT), is under development for non-destructive examination of corrosion processes. The method involves registering and fusing neutron and X-ray tomography data, followed by Gaussian mixture model (GMM) clustering for phase segmentation. Imaging was conducted on two IAAs, Vrac C and BdC1. Additionally, random cross-sections of these samples underwent analysis through optical microscopy, µRaman spectroscopy, and SEM-EDS to characterize and correlate corrosion layers with NX-CT results. This study yields valuable insights into the corrosion of IAAs, enabling the non-destructive investigation of corrosion processes in porous media. The implications extend beyond the preservation of cultural heritage, to the examination of long-term corrosion behaviors in contemporary iron structures, steel within concrete, and nuclear waste disposal plans.

Source-free domain adaptation for semantic image segmentation using internal representations.

Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance. Classic unsupervised domain adaptation (UDA) attempts to address a similar problem when there is target domain with no annotated data points through transferring knowledge from a source domain with annotated data. We develop an online UDA algorithm for semantic segmentation of images that improves model generalization on unannotated domains in scenarios where source data access is restricted during adaptation. We perform model adaptation by minimizing the distributional distance between the source latent features and the target features in a shared embedding space. Our solution promotes a shared domain-agnostic latent feature space between the two domains, which allows for classifier generalization on the target dataset. To alleviate the need of access to source samples during adaptation, we approximate the source latent feature distribution via an appropriate surrogate distribution, in this case a Gaussian mixture model (GMM).

Machine learning models and performance dependency on 2D chemical descriptor space for retention time prediction of pharmaceuticals

The predictive modeling of liquid chromatography methods can be an invaluable asset, potentially saving countless hours of labor while also reducing solvent consumption and waste. Tasks such as physicochemical screening and preliminary method screening systems where large amounts of chromatography data are collected from fast and routine operations are particularly well suited for both leveraging large datasets and benefiting from predictive models. Therefore, the generation of predictive models for retention time is an active area of development. However, for these predictive models to gain acceptance, researchers first must have confidence in model performance and the computational cost of building them should be minimal. In this study, a simple and cost-effective workflow for the development of machine learning models to predict retention time using only Molecular Operating Environment 2D descriptors as input for support vector regression is developed. Furthermore, we investigated the relative performance of models based on molecular descriptor space by utilizing uniform manifold approximation and projection and clustering with Gaussian mixture models to identify chemically distinct clusters. Results outlined herein demonstrate that local models trained on clusters in chemical space perform equivalently when compared to models trained on all data. Through 10-fold cross-validation on a comprehensive set containing 67,950 of our company's proprietary analytes, these models achieved coefficients of determination of 0.84 and 3 % error in terms of retention time. This promising statistical significance is found to translate from cross-validation to prospective prediction on an external test set of pharmaceutically relevant analytes. The observed equivalency of global and local modeling of large datasets is retained with METLIN's SMRT dataset, thereby confirming the wider applicability of the developed machine learning workflows for global models.

An oversampling method based on Gaussian Mixture Model for multi-bolt looseness monitoring using Lamb waves`

The imbalance in the number of healthy and faulty samples poses a significant hindrance to the successful implementation of multi-bolt looseness monitoring and fault classification in engineering applications. The Synthetic Minority Oversampling Technique (SMOTE) is widely used in addressing data imbalance issues. However, traditional SMOTE methods and their improvements have not taken into account the problem of sensor network signals with multiple paths. In this paper, an improved oversampling technique, namely Gaussian Mixture Model (GMM)-SMOTE, is introduced. The proposed SMOTE method is based on GMM and aims to solve the sample imbalance problem under different bolt states and different sensor paths in sensor networks. The GMM is utilized to cluster the minority classes in multi-bolt looseness data. The assignment of weights to different clusters is based on the clustering density function, which is subsequently followed by oversampling. The KL distance is utilized to screen the SMOTE sample data, which improves the quality of the data by achieving inter-class balance and intra-class balance. To verify the effectiveness of the method, a multi-bolt looseness monitoring procedure is implemented. The experimental results demonstrate that the proposed method can improve the accuracy of diagnosing early-stage bolt looseness.

Temporal dynamics unleashed: Elevating variational graph attention

This research introduces the Variational Graph Attention Dynamics (VarGATDyn), addressing the complexities of dynamic graph representation learning, where existing models, tailored for static graphs, prove inadequate. VarGATDyn melds attention mechanisms with a Markovian assumption to surpass the challenges of maintaining temporal consistency and the extensive dataset requirements typical of RNN-based frameworks. It harnesses the strengths of the Variational Graph Auto-Encoder (VGAE) framework, Graph Attention Networks (GAT), and Gaussian Mixture Models (GMM) to adeptly navigate the temporal and structural intricacies of dynamic graphs. Through the strategic application of GMMs, the model handles multimodal patterns, thereby rectifying misalignments between prior and estimated posterior distributions. An innovative multiple-learning methodology bolsters the model’s adaptability, leading to an encompassing and effective learning process. Empirical tests underscore VarGATDyn’s dominance in dynamic link prediction across various datasets, highlighting its proficiency in capturing multimodal distributions and temporal dynamics.

Size-based expectation maximization for characterizing nucleosome positions and subtypes.

Genome-wide nucleosome profiles are predominantly characterized using MNase-seq, which involves extensive MNase digestion and size selection to enrich for mononucleosome-sized fragments. Most available MNase-seq analysis packages assume that nucleosomes uniformly protect 147 bp DNA fragments. However, some nucleosomes with atypical histone or chemical compositions protect shorter lengths of DNA. The rigid assumptions imposed by current nucleosome analysis packages potentially prevent investigators from understanding the regulatory roles played by atypical nucleosomes. To enable the characterization of different nucleosome types from MNase-seq data, we introduce the size-based expectation maximization (SEM) nucleosome-calling package. SEM employs a hierarchical Gaussian mixture model to estimate nucleosome positions and subtypes. Nucleosome subtypes are automatically identified based on the distribution of protected DNA fragments. Benchmark analysis indicates that SEM is on par with existing packages in terms of standard nucleosome-calling accuracy metrics, while uniquely providing the ability to characterize nucleosome subtype identities. Applying SEM to a low-dose MNase-H2B-ChIP-seq data set from mouse embryonic stem cells, we identified three nucleosome types: short-fragment nucleosomes, canonical nucleosomes, and di-nucleosomes. Short-fragment nucleosomes can be divided further into two subtypes based on their chromatin accessibility. Short-fragment nucleosomes in accessible regions exhibit high MNase sensitivity and are enriched at transcription start sites (TSSs) and CTCF peaks, similar to previously reported "fragile nucleosomes." These SEM-defined accessible short-fragment nucleosomes are found not just in promoters but also in distal regulatory regions. Additional analyses reveal their colocalization with the chromatin remodelers CHD6, CHD8, and EP400. In summary, SEM provides an effective platform for exploration of nonstandard nucleosome subtypes.

Leveraging ML for Anomaly Detection in Healthcare Data Warehouses

The rapid emergence of digitalisation leads to unprecedented growth in the generation of the healthcare sector-particularly EHRs and medical equipment data. This extended the way for challenges for integrity in managing data and anomaly detection, including fraudulent transactions, medication errors, and many more system failures. Modern healthcare data poses a challenge to traditional methods of anomaly detection due to high and complex dimensionality. Machine learning provides a strong solution, using algorithms such as Gaussian Mixture Models, One-Class SVM and deep learning algorithms such as Autoencoders, and Recurrent Neural Networks in the detection of anomalies in healthcare data warehouse settings [1]. This study reports how ML can help advance care for patients, enable the validity of the data and reduce costs through real-time monitoring, fraud detection, and early detection of diseases. Applying anomaly detection through ML would most likely bring better operational performance, patient safety, and decision-making in health care for organizations as issues of poor data quality, lack of interpretability of models, and real-time detection would be addressed [2].

Resilient Factor Graph-Based GNSS/IMU/Vision/Odo Integrated Navigation Scheme Enhanced by Noise Approximate Gaussian Estimation in Challenging Environments

The signal blockage and multipath effects of the Global Navigation Satellite System (GNSS) caused by urban canyon scenarios have brought great technical challenges to the positioning and navigation of autonomous vehicles. In this paper, an improved factor graph optimization algorithm enhanced by a resilient noise model is proposed. The measurement noise is resilient and adjusted based on an approximate Gaussian distribution-based estimation. In estimating and adjusting the noise parameters of the measurement model, the error covariance matrix of the multi-sensor fusion positioning system is dynamically optimized to improve the system accuracy. Firstly, according to the approximate Gaussian statistical property of the GNSS/odometer velocity residual sequence, the measured data are divided into an approximate Gaussian fitting region and an approximate Gaussian convergence region. Secondly, the interval is divided according to the measured data, and the corresponding variational Bayesian network and Gaussian mixture model are used to estimate the innovation online. Further, the noise covariance matrix of the adaptive factor graph-based model is dynamically optimized using the estimated noise parameters. Finally, based on low-cost inertial navigation equipment, GNSS, odometer, and vision, the algorithm is implemented and verified using a simulation platform and real-vehicle road test. The experimental results show that in a complex urban road environment, compared with the traditional factor graph fusion localization algorithm, the maximum improvement in accuracy of the proposed algorithm can reach 65.63%, 39.52%, and 42.95% for heading, position, and velocity, respectively.

Exploitation of Bio-Inspired Classifiers for Performance Enhancement in Liver Cirrhosis Detection from Ultrasonic Images.

In the current scenario, liver abnormalities are one of the most serious public health concerns. Cirrhosis of the liver is one of the foremost causes of demise from liver diseases. To accurately predict the status of liver cirrhosis, physicians frequently use automated computer-aided approaches. In this paper, through clustering techniques like fuzzy c-means (FCM), possibilistic fuzzy c-means (PFCM), and possibilistic c means (PCM) and sample entropy features are extracted from normal and cirrhotic liver ultrasonic images. The extracted features are classified as normal and cirrhotic through the Gaussian mixture model (GMM), Softmax discriminant classifier (SDC), harmonic search algorithm (HSA), SVM (linear), SVM (RBF), SVM (polynomial), artificial algae optimization (AAO), and hybrid classifier artificial algae optimization (AAO) with Gaussian mixture mode (GMM). The classifiers' performances are compared based on accuracy, F1 Score, MCC, F measure, error rate, and Jaccard metric (JM). The hybrid classifier AAO-GMM, with the PFCM feature, outperforms the other classifiers and attained an accuracy of 99.03% with an MCC of 0.90.

Coherent point drift with Skewed Distribution for accurate point cloud registration

Point cloud registration methods based on Gaussian Mixture Models (GMMs) exhibit high robustness. However, GMM cannot precisely depict point clouds, because the Gaussian distribution is spatially symmetric and local surfaces of point clouds are typically non-symmetric. In this paper, we propose a novel method for rigid point cloud registration, termed coherent point drift with Skewed Distribution (Skewed CPD). Our method employs an asymmetric distribution constructed from the local surface normals and curvature radii. Compared to the Gaussian distribution, this skewed distribution provides a more accurate spatial description of points on local surfaces. Additionally, we integrate an adaptive multiplier to the covariance, which reallocates the weight of the covariance for different components in the probabilistic mixture model. We employ the EM algorithm to address this maximum likelihood estimation (MLE) issue and leverage GPU acceleration. In the M-step, we adopt an unconstrained optimization technique rooted in a Lie group and Lie algebra to attain the optimal transformation. Experimental results indicate that our method outperforms state-of-the-art methods in both accuracy and robustness. Remarkably, even without loop closure detection, the cumulative error of our approach remains minimal.

Detection of open cluster members inside and beyond tidal radius by machine learning methods based on Gaia DR3

ABSTRACT In our previous work, we introduced a method that combines two unsupervised algorithms: Density-based spatial clustering of applications with noise (DBSCAN) and Gaussian mixture model (GMM). We applied this method to 12 open clusters based on Gaia Early Data Release 3 (EDR3) data, demonstrating its effectiveness in identifying reliable cluster members within the tidal radius. However, for studying cluster morphology, we need a method capable of detecting members both inside and outside the tidal radius. By incorporating a supervised algorithm into our approach, we successfully identified members beyond the tidal radius. In our current work, we initially applied DBSCAN and GMM to identify reliable members of cluster stars. Subsequently, we trained the random forest algorithm using DBSCAN- and GMM-selected data. Leveraging the random forest, we can identify cluster members outside the tidal radius and observe cluster morphology across a wide field of view. Our method was then applied to 15 open clusters based on Gaia DR3, which exhibit a wide range of metallicity, distances, members, and ages. Additionally, we calculated the tidal radius for each of the 15 clusters using the King profile and detected stars both inside and outside this radius. Finally, we investigated mass segregation and luminosity distribution within the clusters. Overall, our approach significantly improved the estimation of the tidal radius and detection of mass segregation compared to the previous work. We found that in Collinder 463, low-mass stars do not segregate in comparison to high-mass and intermediate-mass stars. Additionally, we detected a peak of luminosity in the clusters, some of which were located far from the centre, beyond the tidal radius.

Development of Ridge Ensemble Standardized Drought Index (RESDI) for improving drought characterization and future assessment.

Global warming upsets the environmental balance and leads to more frequent and severe climatic events. These extreme events include floods, droughts, and heatwaves. These widespread extreme events disrupt various sectors of ecosystems directly. However, among all these events, drought is one of the most prolonged climatic events that significantly destroys the ecosystem. Therefore, accurate and efficient assessment of droughts is necessary to mitigate their detrimental impacts. In recent years, several drought indices based on global climate models (GCMs) of Coupled Model Intercomparison Project Phase 6 (CMIP6) have been proposed to quantify and monitor droughts. However, each index has its advantages and limitations. As each index ensembles different models by using different statistical approaches, it is well known that the margin of error is always a part of statistics. Therefore, this study proposed a new drought index to reduce the uncertainty involved in the assessment of droughts. The proposed index named the Ridge Ensemble Standardized Drought Index (RESDI) is based on the innovative ensemble approach termed ridge parameters and distance-based weighting (RDW) scheme. And the development of this RDW scheme is based on two types of methods i.e., ridge regression and divergence-based method. In this research, we ensemble 18 different GCMs of CMIP6 using the RDW scheme. A comparative analysis of the RDW scheme is performed against the simple model average (SMA) and Bayesian model averaging (BMA) schemes at 32 locations on the Tibetan plateau. The comparison revealed that RDW has less mean absolute error (MAE) and root-mean-square error (RMSE). Therefore, the developed RESDI based on RDW is used to project drought properties under three distinct shared socioeconomic pathway (SSP) scenarios: SSP1-2.6, SSP2-4.5, and SSP5-8.5, across seven different time scales (1, 3, 7, 9, 12, 24, and 48). The projected data is then standardized by using the K-components Gaussian mixture model (K-CGMM). In addition, the study employs steady-state probabilities (SSPs) to determine the long-term behavior of drought. The outcome of this research shows that "normal drought (ND)" has the highest probability of occurrence under all scenarios and time scales.

Exploring the effective implementation of population-based SHM in existing buildings. Part II: Damage-feature classification for decision-making

In the context of structural condition assessment, transfer learning methods overcome some of the difficulties associated with the paucity of information on the actual structural condition of a target structure. This study aims to associate the building’s response with a population of nominally identical buildings for which a form is derived from existing empirical models relating certain basic characteristics (e.g., structure height) with the fundamental resonance period. This paper presents a structural condition classification based on the measured resonance period of the target structure, presented as the Build’Health™ solution. First, damage thresholds are defined by the shift of the fundamental period, which is considered to be a damage-sensitive characteristic for a given building population form, derived from almost thirty published references. The implicit period variation due to certain weather conditions is also included. Multinomial logistic regression and Gaussian mixture models are then used to classify damage according to the performance levels used in earthquake engineering (i.e., Operational Condition, Immediate Occupancy, Life Safety and Collapse Prevention). A performance-based probabilistic framework using a traffic-light system (green-orange-red classification) is finally used to classify structural condition. The method is tested and validated on several buildings surveyed after weak to strong earthquakes with different structural conditions. We show the complementarity of combining transfer learning, which gives the actual state of the target specimen with respect to a nominally identical population form of buildings, with multinomial logistic regressions and Gaussian mixture models for operational condition-based decision-making defined by the measured resonance period. This manuscript is the second in a series aimed at developing the Build’Health™ operational method for assessing the condition of real buildings (Part I on damage detection using transfer learning and Part II on classification using Gaussian mixture models and multinomial logistic regressions) based on basic building information.

Advancing Predictive Maintenance with PHM-ML Modeling: Optimal Covariate Weight Estimation and State Band Definition under Multi-Condition Scenarios

The proportional hazards model (PHM) is a vital statistical procedure for condition-based maintenance that integrates age and covariates monitoring to estimate asset health and predict failure risks. However, when dealing with multi-covariate scenarios, the PHM faces interpretability challenges when it lacks coherent criteria for defining each covariate’s influence degree on the hazard rate. Hence, we proposed a comprehensive machine learning (ML) formulation with Interior Point Optimizer and gradient boosting to maximize and converge the logarithmic likelihood for estimating covariate weights, and a K-means and Gaussian mixture model (GMM) for condition state bands. Using real industrial data, this paper evaluates both clustering techniques to determine their suitability regarding reliability, remaining useful life, and asset intervention decision rules. By developing models differing in the selected covariates, the results show that although K-means and GMM produce comparable policies, GMM stands out for its robustness in cluster definition and intuitive interpretation in generating the state bands. Ultimately, as the evaluated models suggest similar policies, the novel PHM-ML demonstrates the robustness of its covariate weight estimation process, thereby strengthening the guidance for predictive maintenance decisions.

Deep learning-based acoustic emission data clustering for crack evaluation of welded joints in field bridges

To advance the intelligent operation and maintenance of bridges, a deep learning-based acoustic emission (AE) data clustering framework was developed for evaluating fatigue cracks in welded joints under conditions of operational noise interference and complex damage mechanisms. Specifically, a convolutional autoencoder (CAE) model was implemented to extract damage-sensitive features from AE wavelet images. Additionally, a physics-guided single-and-cross-case strategy using Gaussian mixture models (GMMs) was presented to diagnose overlapping microscopic noise and damage mechanisms across different cases with various crack lengths. Field tests demonstrated the efficiency of the proposed framework to distinguish AE data induced by noise, crack propagation, surface fretting, and impact, enabling accurate identification of no-damage, minor-damage, and serious-damage cases according to their characteristic mechanisms. Future work will incorporate long-term monitoring data from additional cases to further refine the damage quantification and enhance the overall robustness.

Research on the Short-Term Prediction of Offshore Wind Power Based on Unit Classification

The traditional power prediction methods cannot fully take into account the differences and similarities between units. In the face of the complex and changeable sea climate, the strong coupling effect of atmospheric circulation, ocean current movement, and wave fluctuation, the characteristics of wind processes under different incoming currents and different weather are very different, and the spatio-temporal correlation law of offshore wind processes is highly complex, which leads to traditional power prediction not being able to accurately predict the short-term power of offshore wind farms. Therefore, aiming at the characteristics and complexity of offshore wind power, this paper proposes an innovative short-term power prediction method for offshore wind farms based on a Gaussian mixture model (GMM). This method considers the correlation between units according to the characteristics of the measured data of units, and it divides units with high correlation into a category. The Bayesian information criterion (BIC) and contour coefficient method (SC) were used to obtain the optimal number of groups. The average intra-group correlation coefficient (AICC) was used to evaluate the reliability of measurements for the same quantized feature to select the representative units for each classification. Practical examples show that the short-term power prediction accuracy of the model after unit classification is 2.12% and 1.1% higher than that without group processing, and the mean square error and average absolute error of the short-term power prediction accuracy are reduced, respectively, which provides a basis for the optimization of prediction accuracy and economic operation of offshore wind farms.

Quantitative Assessment and Analysis of Fish Behavior in Closed Systems Using Information Entropy

This study introduces a method for quantitatively assessing the complexity and predictability of fish behavior in closed systems through the application of information entropy, offering a novel lens through which to understand how fish adapt to environmental changes. Utilizing simulations rooted in a random walk model for fish movement, we delve into entropy fluctuations under varying environmental conditions, including responses to feeding and external stimuli. Our findings underscore the utility of information entropy in capturing the intricacies of fish behavior, particularly highlighting the synchrony in collective actions and adaptations to environmental shifts. This research not only broadens our comprehension of fish behavior but also paves the way for its application in fields like aquaculture and resource management. Through our analysis, we discovered that smaller grid sizes in simulations capture detailed local fluctuations, while larger grids elucidate general trends, pinpointing a 2.5 grid as optimal for our study. Moreover, changes in swimming speeds and behavioral adaptations during feeding were quantitatively analyzed, with results illustrating significant behavior modifications. Additionally, employing a Gaussian mixture model helped to clarify the nuanced changes in fish behavior in response to altered light conditions, demonstrating the layered complexity of fish responses to environmental stimuli. This investigation confirms the efficacy of information entropy as a robust metric for evaluating fish shoal behavior, offering a fresh methodology for ecological and environmental studies, with promising implications for sustainable management practices.

Large structural estuaries: Their global distribution and morphology

Estuaries are marine-flooded topographic depressions that receive sediment from both marine and fluvial sources. The morphology of the underlying drainage basin acts as a boundary condition for the spatial distribution of hydrodynamic energy within an estuary, and by extension the resultant depositional environment. In some large estuaries, bedrock structures at the mouth restrict oceanographic forcing, which has impacts on sedimentary infill. Such estuaries are termed here as Large Structural Estuaries (LSEs). For LSEs, the shape of the basin and associated bedrock morphology is fixed on the millennial scale having been formed by geological processes operating over timescales greater than that of the Holocene. However, the distribution and abundance of these LSEs are poorly understood. In this study, a global survey of large estuaries was conducted to identify and characterize LSEs from the worldwide population to understand regional drivers of coastal geomorphology. A total of 271 large (>50 km2) estuaries were identified, and these were clustered into 5 classes using Gaussian Mixture Modelling. These clusters were interpreted as Barrier Estuaries, Rocky Bays, Sandy Bays, Funnelled Estuaries, and LSEs. LSEs comprised 28.04 % of all large estuaries identified and were spatially heterogenous, associated with collision coastlines, and predominantly located at higher latitudes except for the Malay Archipelago. The global distribution of LSEs suggests that regional distribution of tectonic processes strongly influences their formation. LSEs are important global features comprising many of the major ports in the world and this work indicates they are unique landforms and traditional approaches to understanding sedimentation in these settings require adjustment to their unique geomorphology.