Spatial Clustering Method Research Articles

Urban Green Space Assessment: Spatial Clustering Method Based on Multisource Data to Facilitate Zoning Planning

Urban Green Space Assessment: Spatial Clustering Method Based on Multisource Data to Facilitate Zoning Planning

Can digitalization improve the equality and equity of food environment? Evidence from greengrocers in central Shanghai.

Online food shopping has a profound impact on people's food acquisition behavior, the current study aims to understand how online food shopping may affect the accessibility of the local food environment and further influence the health equity among different populations. Taking 8512 traditional and online greengrocers in central Shanghai as an example, this paper uses Gini coefficient, location quotient and spatial clustering method to compare the equality and equity of food environment between physical and digital food outlets. It finds that spatial equality is more significantly improved as a result of online food stores than are population equality and social equity of the food environment; older populations are not disadvantaged in terms of healthy food access but lower-income people are; the impact of online stores varies for different regions and different types of stores; depot-based stores have the most positive impact on health equity. Policy implications are discussed to promote the environmental justice of healthy food accessibility.

GraphCVAE: Uncovering cell heterogeneity and therapeutic target discovery through residual and contrastive learning

Advancements in Spatial Transcriptomics (ST) technologies in recent years have transformed the analysis of tissue structure and function within spatial contexts. However, accurately identifying spatial domains remains challenging due to data sparsity and noise. Traditional clustering methods often fail to capture spatial dependencies, while spatial clustering methods struggle with batch effects and data integration. We introduce GraphCVAE, a model designed to enhance spatial domain identification by integrating spatial and morphological information, correcting batch effects, and managing heterogeneous data. GraphCVAE employs a multi-layer Graph Convolutional Network (GCN) and a variational autoencoder to improve the representation and integration of spatial information. Through contrastive learning, the model captures subtle differences between cell types and states. Extensive testing on various ST datasets demonstrates GraphCVAE's robustness and biological contributions. In the dorsolateral prefrontal cortex (DLPFC) dataset, it accurately delineates cortical layer boundaries. In glioblastoma, GraphCVAE reveals critical therapeutic targets such as TF and NFIB. In colorectal cancer, it explores the role of the extracellular matrix in colorectal cancer. The model's performance metrics consistently surpass existing methods, validating its effectiveness. GraphCVAE's advanced visualization capabilities further highlight its precision in resolving spatial structures, making it a powerful tool for spatial transcriptomics analysis and offering new insights into disease studies.

DGSIST: Clustering spatial transcriptome data based on deep graph structure Infomax

Although spatial transcriptomics data provide valuable insights into gene expression profiles and the spatial structure of tissues, most studies rely solely on gene expression information, underutilizing the spatial data. To fully leverage the potential of spatial transcriptomics and graph neural networks, the DGSI (Deep Graph Structure Infomax) model is proposed. This innovative graph data processing model uses graph convolutional neural networks and employs an unsupervised learning approach. It maximizes the mutual information between graph-level and node-level representations, emphasizing flexible sampling and aggregation of nodes and their neighbors. This effectively captures and incorporates local information from nodes into the overall graph structure. Additionally, this paper developed the DGSIST framework, an unsupervised cell clustering method that integrates the DGSI model, SVD dimensionality reduction algorithm, and k-means++ clustering algorithm. This aims to identify cell types accurately. DGSIST fully uses spatial transcriptomics data and outperforms existing methods in accuracy. Demonstrations of DGSIST’s capability across various tissue types and technological platforms have shown its effectiveness in accurately identifying spatial domains in multiple tissue sections. Compared to other spatial clustering methods, DGSIST excels in cell clustering and effectively eliminates batch effects without needing batch correction. DGSIST excels in spatial clustering analysis, spatial variation identification, and differential gene expression detection and directly applies to graph analysis tasks, such as node classification, link prediction, or graph clustering. Anticipation lies in the contribution of the DGSIST framework to a deeper understanding of the spatial organizational structures of diseases such as cancer.

BayeSMART: Bayesian clustering of multi-sample spatially resolved transcriptomics data.

The field of spatially resolved transcriptomics (SRT) has greatly advanced our understanding of cellular microenvironments by integrating spatial information with molecular data collected from multiple tissue sections or individuals. However, methods for multi-sample spatial clustering are lacking, and existing methods primarily rely on molecular information alone. This paper introduces BayeSMART, a Bayesian statistical method designed to identify spatial domains across multiple samples. BayeSMART leverages artificial intelligence (AI)-reconstructed single-cell level information from the paired histology images of multi-sample SRT datasets while simultaneously considering the spatial context of gene expression. The AI integration enables BayeSMART to effectively interpret the spatial domains. We conducted case studies using four datasets from various tissue types and SRT platforms, and compared BayeSMART with alternative multi-sample spatial clustering approaches and a number of state-of-the-art methods for single-sample SRT analysis, demonstrating that it surpasses existing methods in terms of clustering accuracy, interpretability, and computational efficiency. BayeSMART offers new insights into the spatial organization of cells in multi-sample SRT data.

AFSC: A self-supervised augmentation-free spatial clustering method based on contrastive learning for identifying spatial domains

Recent research in spatial transcriptomics allows researchers to analyze gene expression without losing spatial information. Spatial information can assist in cell communication, identification of new cell subtypes, which provides important research methods for multiple fields such as microenvironment interactions and pathological processes of diseases. Identifying spatial domains is an important step in spatial transcriptomics analysis, and improving spatial clustering methods can benefit for identifying spatial domains. In addition to eliminating noise in original gene expression, how to use spatial information to assist clustering has also become a new problem. A variety of calculating methods have been applied to spatial clustering, including contrastive learning methods. However, existing spatial clustering methods based on contrastive learning use data augmentation to generate positive and negative pairs, which will inevitably destroy the biological meaning of the data. We propose a new self-supervised spatial clustering method based on contrastive learning, Augmentation-Free Spatial Clustering (AFSC), which integrates spatial information and gene expression to learn latent representations. We construct a contrastive learning module without negative pairs or data augmentation by designing Teacher and Student Encoder. We also design an unsupervised clustering module to make clustering and contrastive learning be trained together. Experiments on multiple spatial transcriptomics datasets at different resolutions demonstrate that our method performs well in self-supervised spatial clustering tasks. Furthermore, the learned representations can be used for various downstream tasks including visualization and trajectory inference.

Leveraging Crowdsourcing for Mapping Mobility Restrictions in Data-Limited Regions

This paper introduces a novel methodology for the real-time mapping of mobility restrictions, utilizing spatial crowdsourcing and Telegram as a traffic event data source. This approach is efficient in regions suffering from limitations in traditional data-capturing devices. The methodology employs ArcGIS Online (AGOL) for data collection, storage, and analysis, and develops a 3W (what, where, when) model for analyzing mined Arabic text from Telegram. Data quality validation methods, including spatial clustering, cross-referencing, and ground-truth methods, support the reliability of this approach. Applied to the Palestinian territory, the proposed methodology ensures the accurate, timely, and comprehensive mapping of traffic events, including checkpoints, road gates, settler violence, and traffic congestion. The validation results indicate that using spatial crowdsourcing to report restrictions yields promising validation rates ranging from 67% to 100%. Additionally, the developed methodology utilizing Telegram achieves a precision value of 73%. These results demonstrate that this methodology constitutes a promising solution, enhancing traffic management and informed decision-making, and providing a scalable model for regions with limited traditional data collection infrastructure.

Constrained Density-Based Spatial Clustering of Applications with Noise (DBSCAN) using hyperparameter optimization

This article proposes a hyperparameter optimization method for density-based spatial clustering of applications with noise (DBSCAN) with constraints, termed HC-DBSCAN. While DBSCAN is effective at creating non-convex clusters, it cannot limit the number of clusters. This limitation is difficult to address with simple adjustments or heuristic methods. We approach constrained DBSCAN as an optimization problem and solve it using a customized alternating direction method of multipliers Bayesian optimization (ADMMBO). Our custom ADMMBO enables HC-DBSCAN to reuse clustering results for enhanced computational efficiency, handle integer-valued parameters, and incorporate constraint functions that account for the degree of violations to improve clustering performance. Furthermore, we propose an evaluation metric, penalized Davies–Bouldin score, with a computational cost of O(N). This metric aims to mitigate the high computational cost associated with existing metrics and efficiently manage noise instances in DBSCAN. Numerical experiments demonstrate that HC-DBSCAN, equipped with the proposed metric, generates high-quality non-convex clusters and outperforms benchmark methods on both simulated and real datasets.

Genetic structure and climate niche differentiation among populations of Leopardus geoffroyi.

Geoffroy's cat (Leopardus geoffroyi) is a small-sized felid native to South America. Given the species' distribution covering a wide variety of habitats, and the presence of high levels of anthropization in part of its range, it is possible that genetically differentiated groups exist and that they occupy different climatic niches. We assessed patterns of contemporary genetic diversity and structure in the species across most of its range, characterizing each inferred genetic group based on ecological niche models. We genotyped 11 microsatellites for 142 samples covering most of Geoffroy's cat distribution, and investigated patterns of genetic structure and diversity, applying spatial and nonspatial Bayesian clustering methods and a spatial principal component analysis. We created ecological niche models for each genetic cluster, evaluating whether these clusters occupy different climatic spaces and display differences in the suitability of different values of the climatic variables analyzed. We identified two genetic clusters, one in the north-northeast and the other in the south-southwest of the species' distribution. These clusters showed moderate FST values between them and differences in dispersal/genetic diversity. We found isolation-by-distance patterns globally and within each cluster. We observed lower expected heterozygosity compared with other studies and a north-south gradient in allelic richness. The southern cluster showed lower genetic variability and a more restricted climatic niche suggesting that this group is more vulnerable to the effects of the current context of climate change. Individuals from the southern genetic cluster are under different pressures, likely a product of the particularly dry habitat they occupy. Climatic variables associated with habitat suitability suggest the southern cluster has affinity for the arid and semiarid conditions present in its distribution. Conservation measures should consider the genetic structure observed and differences in climatic spaces to maintain the evolutionary potential of the species.

Unified Spatial Clustering of Territory Risk to Uncover Impact of COVID-19 Pandemic on Major Coverages of Auto Insurance

This research delves into the fusion of spatial clustering and predictive modeling within auto insurance data analytics. The primary focus of this research is on addressing challenges stemming from the dynamic nature of spatial patterns in multiple accident year claim data, by using spatially constrained clustering. The spatially constrained clustering is implemented under hierarchical clustering with a soft contiguity constraint. It is highly desirable for insurance companies and insurance regulators to be able to make meaningful comparisons of loss patterns obtained from multiple reporting years that summarize multiple accident year loss metrics. By integrating spatial clustering techniques, the study not only improves the credibility of predictive models but also introduces a strategic dimension reduction method that concurrently enhances the interpretability of predictive models used. The evolving nature of spatial patterns over time poses a significant barrier to a better understanding of complex insurance systems as these patterns transform due to various factors. While spatial clustering effectively identifies regions with similar loss data characteristics, maintaining up-to-date clusters is an ongoing challenge. This research underscores the importance of studying spatial patterns of auto insurance claim data across major insurance coverage types, including Accident Benefits (AB), Collision (CL), and Third-Party Liability (TPL). The research offers regulators valuable insights into distinct risk profiles associated with different coverage categories and territories. By leveraging spatial loss data from pre-pandemic and pandemic periods, this study also aims to uncover the impact of the COVID-19 pandemic on auto insurance claims of major coverage types. From this perspective, we observe a statistically significant increase in insurance premiums for CL coverage after the pandemic. The proposed unified spatial clustering method incorporates a relabeling strategy to standardize comparisons across different accident years, contributing to a more robust understanding of the pandemic effects on auto insurance claims. This innovative approach has the potential to significantly influence data visualization and pattern recognition, thereby improving the reliability and interpretability of clustering methods.

Unraveling Spatial Domain Characterization in Spatially Resolved Transcriptomics with Robust Graph Contrastive Clustering.

Spatial transcriptomics can quantify gene expression and its spatial distribution in tissues, thus revealing molecular mechanisms of cellular interactions underlying tissue heterogeneity, tissue regeneration, and spatially localized disease mechanisms. However, existing spatial clustering methods often fail to exploit the full potential of spatial information, resulting in inaccurate identification of spatial domains. In this paper, we develop a deep graph contrastive clustering framework, stDGCC, that accurately uncovers underlying spatial domains via explicitly modeling spatial information and gene expression profiles from spatial transcriptomics data. The stDGCC framework proposes a spatially informed graph node embedding model to preserve the topological information of spots and to learn the informative and discriminative characterization of spatial transcriptomics data through self-supervised contrastive learning. By simultaneously optimizing the contrastive learning loss, reconstruction loss, and Kullback-Leibler (KL) divergence loss, stDGCC achieves joint optimization of feature learning and topology structure preservation in an end-to-end manner. We validate the effectiveness of stDGCC on various spatial transcriptomics datasets acquired from different platforms, each with varying spatial resolutions. Our extensive experiments demonstrate the superiority of stDGCC over various state-of-the-art clustering methods in accurately identifying cellular-level biological structures. Code and data are available from https://github.com/TimE9527/stDGCC and https://figshare.com/projects/stDGCC/186525. Supplementary data are available at Bioinformatics online.

Mapping the impact of age and APOE risk factors for late onset Alzheimer's disease on long range brain connections through multiscale bundle analysis.

Alzheimer's disease currently has no cure and is usually detected too late for interventions to be effective. In this study we have focused on cognitively normal subjects to study the impact of risk factors on their long-range brain connections. To detect vulnerable connections, we devised a multiscale, hierarchical method for spatial clustering of the whole brain tractogram and examined the impact of age and APOE allelic variation on cognitive abilities and bundle properties including texture e.g., mean fractional anisotropy, variability, and geometric properties including streamline length, volume, and shape, as well as asymmetry. We found that the third level subdivision in the bundle hierarchy provided the most sensitive ability to detect age and genotype differences associated with risk factors. Our results indicate that frontal bundles were a major age predictor, while the occipital cortex and cerebellar connections were important risk predictors that were heavily genotype dependent, and showed accelerated decline in fractional anisotropy, shape similarity, and increased asymmetry. Cognitive metrics related to olfactory memory were mapped to bundles, providing possible early markers of neurodegeneration. In addition, physiological metrics such as diastolic blood pressure were associated with changes in white matter tracts. Our novel method for a data driven analysis of sensitive changes in tractography may differentiate populations at risk for AD and isolate specific vulnerable networks.

Multidimensional statistical analysis of social inequalities in Italy

The analysis of social inequalities is a topic of current interest and is studied as a factor in the evolution and measurement of the level of well-being. A fundamental prerequisite for a correct statistical analysis of this phenomenon is the need to share a univocal definition of the concept of social inequalities. This work starts from the need to identify territorial areas and/or population subgroups characterized by situations of hardship or strong social exclusion through the construction of indicators that can estimate situations of social inequalities in small areas. Scientific research options have been oriented towards the establishment of a multidimensional approach, sometimes renouncing dichotomous logic to go as far as fuzzy classifications in which each unit simultaneously belongs and does not belong to the selected category. Multidimensional statistical analysis methodologies (TFR method) and Density Based Spatial Clustering methods (DBSCAN) will therefore be used to aggregate adjacent spatial units with high intensity of social inequalities.

HSeq2Seq: Hierarchical graph neural network for accurate mobile traffic forecasting

Hierarchical graph neural networks (HGNNs) provide a feasible method for modeling complex spatiotemporal dependencies during mobile traffic forecasting. However, most existing studies have adopted spatial node clustering methods to construct a coarsened graph that overlooks the temporal correlation within the original station graph. Furthermore, existing state-of-the-art methods fail to fully exploit the cross-regional feature impacts on stations, which limits their ability to model nonlocal spatial dependency.To overcome these limitations, we proposed a hierarchical sequence-to-sequence (HSeq2Seq) approach that combines HGNNs with a sequence-to-sequence architecture (Seq2Seq) for mobile traffic forecasting. First, a spatiotemporal node clustering method was designed to construct the hierarchical structure. Second, a convolution encoder was employed to extract the local spatiotemporal features from a hierarchical perspective, and a novel attention-based feature fusion module was built to capture the nonlocal spatiotemporal features by identifying both the intra- and cross-regional feature impacts on the stations. Finally, a recurrent decoder is introduced to reweight the spatiotemporal features and recursively produce the final prediction.Extensive experiments on two real-world datasets demonstrate that our model outperforms state-of-the-art methods, while the ablation study also verifies the effectiveness of the spatiotemporal node clustering and the attention-based feature fusion module.

Evaluating the spatiotemporal dynamics of ecosystem service supply-demand risk from the perspective of service flow to support regional ecosystem management: A case study of yangtze river delta urban agglomeration

The inappropriate spatio-temporal distribution of natural capital during rapid urbanization has increased ecosystem service supply-demand (ESSD) risks, posing great challenges to the sustainable growth of human well-being, especially in urban agglomerations. Although methods focusing on the spatial match or temporal dynamics of ESSD in risk assessment have been established, a comprehensive understanding of the spatial dynamics underlying ecosystem service flows (ESF) is still missing. Due to the spatiotemporal heterogeneity of various ESSD risks within urban agglomerations, incorporating these elements into a unified spatial planning framework is still difficult. This study integrated the spatio-temporal analysis method of ESSD considering ESF and the spatial clustering method to propose an ESSD risk assessment and management framework: evaluating ES supply, demand and flow, incorporating ESF to quantify ESSD across various timeframes, assessing ESSD risks based on the current status and dynamic trends, and using Self-Organizing Map to identify optimal ESSD risk bundles (ESSDR_Bs). The results showed high ESSD risks of high temperature regulation, nitrogen purification, phosphorus purification, and food production in Yangtze River Delta urban agglomeration. While the ESSD risks of biodiversity conservation, carbon sequestration, soil retention, water yield, and tourism culture were relatively low, a concerning trend of decreasing surpluses was observed in general. In addition, six ESSDR_Bs were identified, and differentiated ecological management strategies were proposed for each bundle. This study provided a novel perspective for efficiently understanding and regulating the ESSD risks in urban agglomerations.

Identifying spatial domains from spatial transcriptome by graph attention network

Due to the high dimensionality and complexity of the data, the analysis of spatial transcriptome data has been a challenging problem. Meanwhile, cluster analysis is the core issue of the analysis of spatial transcriptome data. In this article, a deep learning approach is proposed based on graph attention networks for clustering analysis of spatial transcriptome data. Our method first enhances the spatial transcriptome data, then uses graph attention networks to extract features from nodes, and finally uses the Leiden algorithm for clustering analysis. Compared with the traditional non-spatial and spatial clustering methods, our method has better performance in data analysis through the clustering evaluation index. The experimental results show that the proposed method can effectively cluster spatial transcriptome data and identify different spatial domains, which provides a new tool for studying spatial transcriptome data.

Residential urban heritage space identification, delimitation, and potential assessment model based on space syntax

In the era of post-modernization, profound transformations in urban spaces have led to significant shifts in the spatial composition paradigms of contemporary urban heritage. Research on this process is crucial for elucidating the spatial pathways and compositional changes in the modernization transformation of urban heritage. This study aims to establish identification indicators and assessment systems for the spatial structure of urban residential environments exhibiting historical characteristics and heritage potential through a comparative analysis of residential urban heritage spatial paradigms in historic cities in China and Japan. First, grounded in space syntax theory, this study selected residential urban heritage in Suzhou’s Pingjiang Historic District and Uji’s Nakauji District as research cases. Utilizing road network data, this study analyzed the Life Integration (Int.VR1000) and Global Integration (Int.VR5000) of urban heritage spaces, thereby constructing a spatial topology system for heritage spaces. Second, the study employed urban spatial entropy indicators, such as architectural density entropy, spatial morphology entropy, and function mixing entropy, to quantitatively describe the spatial structure, consequently establishing a heritage space morphological structure indicator system. Finally, spatial clustering methods are used to integrate the spatial topology system with the morphological structure indicator system, resulting in a feature model for residential urban heritage spaces. The research results indicate that the transformation path of residential space paradigms is mainly influenced by spatial topology, affecting the structure of residential heritage spaces in three aspects: functional layout, building density, and spatial form. This phenomenon, in turn, impacts population distribution and the migration of living spaces. However, at the same time, the “resistance effect” of street and lane spaces and the limitations of architectural forms on spatial functions have protected the integrity and authenticity of the internal space.

High genetic connectivity of two pollinating flies despite urban disturbance

AbstractHoverflies (Syrphidae) are essential pollinators, and their severe decline jeopardizes their invaluable contribution to plant diversity and agricultural production. However, we know little about the dispersal abilities of hoverflies in urbanized landscapes, limiting our understanding of the spatiotemporal dynamics of plant–pollinator systems and reducing our ability to preserve biodiversity in the context of global change. Previous work has not addressed how urbanization affects the functional connectivity of hoverflies and whether dispersal is a limiting factor in their population dynamics. In this study, we investigated the spatial genetic structure of two nonmigratory species of hoverflies in two urban areas. We collected more than a thousand specimens of each Syritta pipiens and Myathropa florea, each, by hand netting in two western European urbanized study areas of 490 and 460 km2 in 2021, and we genotyped them at 14 and 24 microsatellite loci, respectively. Based on spatial and nonspatial Bayesian clustering methods, we failed to reject the null hypothesis of panmixia, suggesting that both species exhibited high genetic connectivity despite urbanization. The distribution of allele frequencies was not correlated with geographic distance, implying that isolation‐by‐distance was negligible at the investigated spatial scale in both species. Although anthropogenic land cover changes generally have dramatic consequences on biodiversity, these hoverfly species retain high connectivity, which suggests that dispersal is not a strong limiting factor in their metapopulational dynamics. However, high effective population size and its confounding effect on signals of genetic drift may limit our ability to conclude confidently about landscape effects on gene flow in those two species. Provided we maintain or restore habitat, recolonization may be prompt even in urban areas.

Benchmarking spatial clustering methods with spatially resolved transcriptomics data.

Spatial clustering, which shares an analogy with single-cell clustering, has expanded the scope of tissue physiology studies from cell-centroid to structure-centroid with spatially resolved transcriptomics (SRT) data. Computational methods have undergone remarkable development in recent years, but a comprehensive benchmark study is still lacking. Here we present a benchmark study of 13 computational methods on 34 SRT data (7 datasets). The performance was evaluated on the basis of accuracy, spatial continuity, marker genes detection, scalability, and robustness. We found existing methods were complementary in terms of their performance and functionality, and we provide guidance for selecting appropriate methods for given scenarios. On testing additional 22 challenging datasets, we identified challenges in identifying noncontinuous spatial domains and limitations of existing methods, highlighting their inadequacies in handling recent large-scale tasks. Furthermore, with 145 simulated data, we examined the robustness of these methods against four different factors, and assessed the impact of pre- and postprocessing approaches. Our study offers a comprehensive evaluation of existing spatial clustering methods with SRT data, paving the way for future advancements in this rapidly evolving field.

A New Approach for Discontinuity Extraction Based on an Improved Naive Bayes Classifier

An increasing number of methods are being used to extract rock discontinuities from 3D point cloud data of rock surfaces. In this paper, a new method for automatic extraction of rock discontinuity based on an improved Naive Bayes classifier is proposed. The method first uses principal component analysis to find the normal vectors of the points, and then generates a certain number of random point sets around the selected training points for training the classifier. The trained, improved Naive Bayes classifier is based on point normal vectors and is able to automatically remove noise points due to various reasons in conjunction with the knee point algorithm, realizing high-precision extraction of the discontinuity sets. Subsequently, the individual discontinuities are segmented using a hierarchical density-based spatial clustering method with noise application. Finally, the PCA algorithm is used to complete the orientation by plane fitting the individual discontinuities. The method was applied in two cases, Kingston and Colorado, and the reliability and advantages of the new method were verified by comparing the results with those of previous research, and the discussion and analysis determined the optimal values of the relevant parameters in the algorithm.