Search

Non-invasive load monitoring (NILM) deduces changes in energy consumption patterns and operational statuses of electrical equipment from power signals in the feed line. With the emergence of fine-grained power load distribution, the importance of utilizing this technology for implementing demand-side energy management in smart grid development has become increasingly prominent. To address the issue of low load identification accuracy stemming from complex and diverse load types, this paper introduces a NILM method based on uniform manifold approximation and projection (UMAP) reduction and enhanced density-based spatial clustering of applications with noise (DBSCAN). Firstly, this paper combines the characteristics of user load under transient and steady-state conditions and selects data with significant differences to construct a load-characteristic database. Additionally, UMAP is employed to reduce the dimensionality of high-dimensional load features and rebuild a load feature database. Subsequently, DBSCAN is utilized to categorize typical user loads, followed by a correlation analysis with the load-characteristic database to determine the types or classes of loads that involve switching actions. Finally, this paper simulates and analyzes the proposed method using the electricity consumption data of industrial users from the CER–Electricity–Data dataset. It identifies the electricity load data commonly utilized by users in a specific area of Zhejiang Province in China. The experimental results indicate that the accuracy of the proposed non-invasive load identification method reaches 95%. Compared to the wavelet transform, decision tree, and backpropagation network methods, the improvement is approximately 5%. [ABSTRACT FROM AUTHOR]

We propose a Bayesian nonparametric clustering approach to study the spatial heterogeneity effect for functional data observed at spatially correlated locations. We consider a geographically weighted Chinese restaurant process equipped with a conditional autoregressive prior to capture fully the spatial correlation of function curves. To sample efficiently from our model, we customize a prior called Quadratic Gamma, which ensures conjugacy. We design a Markov chain Monte Carlo algorithm to infer simultaneously the posterior distributions of the number of groups and the grouping configurations. The superior numerical performance of the proposed method over competing methods is demonstrated using simulated examples and a U.S. annual precipitation study. [ABSTRACT FROM AUTHOR]

Background: Music training facilitates the development of individual cognitive functions and influences brain plasticity. A comprehensive understanding of the pathways and processes through which music affects the human brain, as well as the neurobiological mechanisms underlying human brain perception of music, is necessary to fully harness the plasticity that music offers for brain development. Aims: To investigate the resting-state electroencephalogram (EEG) activity of individuals with and without music training experience, and explore the microstate patterns of EEG signals. Method: In this study, an analysis of electroencephalogram (EEG) microstates from 57 participants yielded temporal parameters(mean duration, time coverage, occurrence, and transition probability)of four classic microstate categories (Categories A, B, C, and D) for two groups: those with music training experience and those without. Statistical analysis was conducted on these parameters between groups. Results: The results indicate that compared to individuals without music training experience, participants with music training experience exhibit significantly longer mean durations of microstate A, which is associated with speech processing. Additionally, they show a greater time coverage of microstate B, which is associated with visual processing. Transition probabilities from microstate A to microstate B were greater in participants with music training experience compared to those without. Conversely, transition probabilities from microstate A to microstate C and from microstate C to microstate D were greater in participants without music training experience. Conclusion: Our study found differences in characteristic parameters of certain microstates between individuals with and without music training experience. This suggests distinct brain activity patterns during tasks related to speech, vision, and attention regulation among individuals with varying levels of music training experience. These findings support an association between music training experience and specific neural activities. Furthermore, they endorse the hypothesis of music training experience influencing brain activity during resting states. Additionally, they imply a facilitative role of music training in tasks related to speech, vision, and attention regulation, providing initial evidence for further empirical investigation into the cognitive processes influenced by music training. [ABSTRACT FROM AUTHOR]

In recent years, the geographical factor has been increasingly studied in electoral processes. The purpose of this study is to identify and explore the spatial pattern of votes in the first round of Afghanistan's presidential election in 2019. The votes of 14 election candidates at the district level was collected from Independent Election Commission (IEC). To measure spatial autocorrelation and identify spatial patterns, global and local Moran Index were used. The results of Moran's index are positive for the votes of all candidates, which indicates the spatial cluster pattern. Then clusters and outliers were investigated according to the ethnic map. The results show that the ethnicity factor is important in the formation of spatial clusters of electoral votes in Afghanistan. Spatial approach increases our understanding of the important processes that can be caused by the context conditions in each area. Thus, this research provides an accurate scientific support for further research in the field of political science, political and social geography of Afghanistan. [ABSTRACT FROM AUTHOR]

The diversified innovative strategies adopted by the new retail format in urban spaces have significantly driven retail transformation and innovation. The combination of online platforms and physical stores provides a substantial advantage in market competition. This paper takes "Freshippo", a typical representative of China's new retail, as an example. Based on multi-source data and using tools such as GIS spatial analysis, statistical analysis, and geographical detectors, this study comprehensively examines the spatial clustering characteristics and influencing factors of Freshippo physical stores in Shanghai. The findings show that Freshippo has significantly expanded in the Shanghai fresh food market by innovatively opening various types of stores. However, there are substantial differences in the proportions of different types of stores, with 94% of the stores having online retail capabilities. Each offline store in the new retail format presents a multi-level "complementary" spatial distribution feature across the urban space, with distinctive clusters in the urban central districts, urban periphery areas, and outer suburban districts. The radiation range of logistics and distribution services exhibits characteristics of "central agglomeration and multi-point distribution", providing residents with diverse and accurate services. Additionally, the comparison of multiple model results shows that the location selection of various types of new retail stores is significantly influenced by multiple factors, especially the nonlinear amplification effect of factor interactions on store agglomeration. These findings provide an important scientific reference for understanding the development of new retail formats and offer new ideas that promote the transformation and innovation of the retail industry, thereby achieving sustainable development. [ABSTRACT FROM AUTHOR]

Declining levels of social welfare caused by climate warming and air pollution place increasing constraints on high-quality, sustainable global development. To achieve global climate-governance goals, it is essential to accelerate the process of peaking carbon emissions and meeting air-quality standards. Despite growing awareness of the impact of low-carbon city policies on the environment, few studies have focused on their impact on urban air quality. Based on panel data drawn from 275 cities between 2011 and 2017, the present study evaluates the effects of a low-carbon city policy on urban sulfur-dioxide emissions, using the low-carbon city policy as a quasi-natural experiment. The findings reveal that urban sulfur-dioxide emissions have obvious spatial-autocorrelation characteristics, showing obvious spatial clustering. The low-carbon city policy not only significantly reduced urban sulfur-dioxide emissions in pilot cities, but also suppressed sulfur-dioxide emissions in surrounding cities through an indirect rebound effect. This paper provides a theoretical reference for collaborative governance, which can help to achieve peak carbon emissions and air-quality standards. To reach those goals, nations must abandon territorial prevention-and-control methods based on administrative divisions and to fully activate cross-city regional joint prevention-and-control measures. This study proposes key policies, including promoting inter-city regional coordination mechanisms, strengthening the collaborative governance in relation to carbon-dioxide and sulfur-dioxide emissions, and promoting the construction of inner-city green facilities. [ABSTRACT FROM AUTHOR]

Objective To understand the epidemiological characteristics of genital Chlamydial infection in Haizhu district of Guangzhou from 2014 to 2023, and to provide a rationale for the development of intervention measures. Methods The epidemic data of genital Chlamydial infection in Haizhu district of Guangzhou from 2014 to 2023 were obtained from the infectious disease surveillance module of Chinese Disease Prevention and Control Information System. Descriptive epidemiological methods and spatial clustering analysis were used in this study. Results The reported incidence rate of genital Chlamydial infection in Haizhu district of Guangzhou decreased from 90.02/100, 000 in 2014 to 51.55/100, 000 in 2023, with an average annual decrease of 6.01% (Z = -11.44, P < 0.001) . The reported incidence rates were stable in males and a tendency of decrease in females (Z = -13.38, P<0.001). The highest incidence was in the age group of 20-39 years, accounting for 82.48%. Majority of the patients were household workers, unemployed, commercial service personnel, and unknown occupations. A positive correlation in the number of reported cases was observed in 2017, 2019 to 2022 (all Moran's I index >0, Z > 1.960, P < 0.05), among which the highest spatial clustering was found in 2020 and the lowest in 2017. The "high-high" clustering areas were mainly in Chigang Street and Fengyang Street, consistent with the cumulative distribution of reported cases. The "low-high" clustering area was Pazhou Street. Conclusions The incidence of genital Chlamydial infection in Haizhu district of Guangzhou displays a downward trend from 2014 to 2023, but there is significant clustering in population and spatial distribution. Thus, it is necessary to strengthen the prevention and treatment program for key populations in order to control the prevalence of genital Chlamydial infection. [ABSTRACT FROM AUTHOR]

The built environment plays a key role in everyday wellbeing, as well-designed and accessible environments help fulfil people's daily needs and activities. Of special relevance is the urban vitality concept of Jane Jacobs, a core principle of local planning strategies worldwide, which is used as an indicator of street vibrancy and quality of life among city residents. However, the promotion of her ideas on dense, lively, and diverse neighbourhoods coexists with increasing urban inequalities. The present study aims to examine if, and how, vital places are related with different levels of social vulnerability. To do so, we use Exploratory Spatial Data Analysis (ESDA) of synthetic indicators of both vitality and vulnerability. Our results provide evidence of local associations between urban vitality and urban vulnerability, and identify four main scenarios that can be helpful for policy intervention. The findings of this study have the potential to guide urban planning strategies to promote vital environments while preventing situations of social vulnerability. We identify four scenarios for policy based on the relationship between vitality and vulnerability. Scenario-specific policies should be designed to address vitality with equity lens. In Low vitality – High vulnerability areas need to ameliorate physical infrastructure for vitality while also developing social policies. In High vitality – High vulnerability areas, policies should prevent residents' displacement. In High vitality – Low vulnerability areas, policies should promote diversity of residents. In Low vitality – Low vulnerability areas, policies should promote dense and diverse developments in terms of uses and population while promoting car-free mobility. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Objective To understand the epidemiological characteristics of genital Chlamydial infection in Haizhu district of Guangzhou from 2014 to 2023, and to provide a rationale for the development of intervention measures. Methods The epidemic data of genital Chlamydial infection in Haizhu district of Guangzhou from 2014 to 2023 were obtained from the infectious disease surveillance module of Chinese Disease Prevention and Control Information System. Descriptive epidemiological methods and spatial clustering analysis were used in this study. Results The reported incidence rate of genital Chlamydial infection in Haizhu district of Guangzhou decreased from 90.02/100,000 in 2014 to 51.55/100,000 in 2023, with an average annual decrease of 6.01% (Z=-11.44, P0, Z>1.960, P

The performance of Power Domain Non-Orthogonal Multiple Access (PD-NOMA) is affected by the performance of Successive Interference Cancellation (SIC) in decoding user data. The large number of users will cause error propagation in SIC, which results in decreased SIC performance. This research aims to optimize the performance of SIC in PD-NOMA by applying spatial concepts to classify users. This research applies various supervised machine learning classification algorithms, including Decision Tree, K-Nearest Neighbors (K-NN), Support Vector Machine (SVM), Random Forest, Logistic Regression, and Naive Bayes. The experimental results show that Random Forest achieves the highest accuracy in classifying users, followed by Decision Tree. In addition, in performance measurement using ROC (Receiver Operating characteristic) and AUC (Area under the Curve) curves, the Random Forest method achieved the best results. In terms of experimentation process time, a decision tree has a faster time compared to a random forest. Overall, the Random Forest algorithm is suitable for the task of user clustering in the context of PD-NOMA, which utilizes the spatial concept from user to base station (BS).

Abstract Background The escalating trend of obesity in Malaysia is surmounting, and the lack of evidence on the environmental influence on obesity is untenable. Obesogenic environmental factors often emerge as a result of shared environmental, demographic, or cultural effects among neighbouring regions that impact lifestyle. Employing spatial clustering can effectively elucidate the geographical distribution of obesity and pinpoint regions with potential obesogenic environments, thereby informing public health interventions and further exploration on the local environments. This study aimed to determine the spatial clustering of body mass index (BMI) among adults in Malaysia. Method This study utilized information of respondents aged 18 to 59 years old from the National Health and Morbidity Survey (NHMS) 2014 and 2015 at Peninsular Malaysia and East Malaysia. Fast food restaurant proximity, district population density, and district median household income were determined from other sources. The analysis was conducted for total respondents and stratified by sex. Multilevel regression was used to produce the BMI estimates on a set of variables, adjusted for data clustering at enumeration blocks. Global Moran’s I and Local Indicator of Spatial Association statistics were applied to assess the general clustering and location of spatial clusters of BMI, respectively using point locations of respondents and spatial weights of 8 km Euclidean radius or 5 nearest neighbours. Results Spatial clustering of BMI independent of individual sociodemographic was significant (p

The wind power industry is increasing worldwide every year. Thus, obtaining timely and detailed information on wind farms’ number and spatial distribution is critical for quantitatively estimating wind energy utilization and for planning the construction of new wind farms. Therefore, this study proposes a method for quickly identifying wind farms in a large-scale area. Given that wind farms mainly comprise individual objects such as wind turbines and substations, we labeled sample images of wind turbines and substations on a global scale. Then, these sample images are used to train a target recognition model and an object classification model and detect the specific locations of wind turbines and substations in the study area. Additionally, we deeply analyzed the location features of the wind turbines and further improved the recognition accuracy based on these known features using geographic constraints. Based on the location information of wind turbines and substations, a clustering model organizes them effectively into complete wind farms. A comprehensive evaluation of the clustering model verifies its scientific validity and reliability. Specifically, this framework was systematically tested throughout Vietnam with remarkable results, using high-resolution historical images provided by Google Earth. Indeed, our framework achieved 90.45% recall and 95.73% accuracy for wind turbines and 81.37% recall and 78.96% accuracy for substations. Finally, we successfully obtained the spatial location and distribution of 15 completed wind farms, demonstrating that the proposed scheme can quickly and accurately identify wind power plants in a large-scale area, which supports wind power management and energy utilization planning.

Abstract Current clustering analysis of spatial transcriptomics data primarily relies on molecular information and fails to fully exploit the morphological features present in histology images, leading to compromised accuracy and interpretability. To overcome these limitations, we have developed a multi-stage statistical method called iIMPACT. It identifies and defines histology-based spatial domains based on AI-reconstructed histology images and spatial context of gene expression measurements, and detects domain-specific differentially expressed genes. Through multiple case studies, we demonstrate iIMPACT outperforms existing methods in accuracy and interpretability and provides insights into the cellular spatial organization and landscape of functional genes within spatial transcriptomics data.

Abstract Recent technologies such as spatial transcriptomics, enable the measurement of gene expressions at the single-cell level along with the spatial locations of these cells in the tissue. Spatial clustering of the cells provides valuable insights into the understanding of the functional organization of the tissue. However, most such clustering methods involve some dimension reduction that leads to a loss of the inherent dependency structure among genes at any spatial location in the tissue. This destroys valuable insights of gene co-expression patterns apart from possibly impacting spatial clustering performance. In spatial transcriptomics, the matrix-variate gene expression data, along with spatial coordinates of the single cells, provides information on both gene expression dependencies and cell spatial dependencies through its row and column covariances. In this work, we propose a joint Bayesian approach to simultaneously estimate these gene and spatial cell correlations. These estimates provide data summaries for downstream analyses. We illustrate our method with simulations and analysis of several real spatial transcriptomic datasets. Our work elucidates gene co-expression networks as well as clear spatial clustering patterns of the cells. Furthermore, our analysis reveals that downstream spatial-differential analysis may aid in the discovery of unknown cell types from known marker genes.

Background: The escalating trend of obesity in Malaysia is surmounting, and the lack of evidence on the environmental influence on obesity is untenable. Obesogenic environmental factors often emerge as a result of shared environmental, demographic, or cultural effects among neighbouring regions that impact lifestyle. Employing spatial clustering can effectively elucidate the geographical distribution of obesity and pinpoint regions with potential obesogenic environments, thereby informing public health interventions and further exploration on the local environments. This study aimed to determine the spatial clustering of body mass index (BMI) among adults in Malaysia. Method: This study utilized information of respondents aged 18 to 59 years old from the National Health and Morbidity Survey (NHMS) 2014 and 2015 at Peninsular Malaysia and East Malaysia. Fast food restaurant proximity, district population density, and district median household income were determined from other sources. The analysis was conducted for total respondents and stratified by sex. Multilevel regression was used to produce the BMI estimates on a set of variables, adjusted for data clustering at enumeration blocks. Global Moran's I and Local Indicator of Spatial Association statistics were applied to assess the general clustering and location of spatial clusters of BMI, respectively using point locations of respondents and spatial weights of 8 km Euclidean radius or 5 nearest neighbours. Results: Spatial clustering of BMI independent of individual sociodemographic was significant (p < 0.001) in Peninsular and East Malaysia with Global Moran's index of 0.12 and 0.15, respectively. High-BMI clusters (hotspots) were in suburban districts, whilst the urban districts were low-BMI clusters (cold spots). Spatial clustering was greater among males with hotspots located closer to urban areas, whereas hotspots for females were in less urbanized areas. Conclusion: Obesogenic environment was identified in suburban districts, where spatial clusters differ between males and females in certain districts. Future studies and interventions on creating a healthier environment should be geographically targeted and consider gender differences. [ABSTRACT FROM AUTHOR]

In this research, we propose a novel technique for visualizing nonstationarity in geostatistics, particularly when confronted with a single realization of data at irregularly spaced locations. Our method hinges on formulating a statistic that tracks a stable microergodic parameter of the exponential covariance function, allowing us to address the intricate challenges of nonstationary processes that lack repeated measurements. We implement the fused lasso technique to elucidate nonstationary patterns at various resolutions. For prediction purposes, we segment the spatial domain into stationary sub-regions via Voronoi tessellations. Additionally, we devise a robust test for stationarity based on contrasting the sample means of our proposed statistics between two selected Voronoi subregions. The effectiveness of our method is demonstrated through simulation studies and its application to a precipitation dataset in Colorado. Supplementary materials accompanying this paper appear online. [ABSTRACT FROM AUTHOR]

Cultural and creative clusters (CCCs) have been a crucial driving force to generate economic, cultural, and social impacts. However, few studies have investigated theories about how the spatial clustering of CCCs differs from that of traditional technology-based clusters (TBCs). To address this gap, we adopted the systematic literature review methodology to conduct a comprehensive comparison between CCCs and TBCs by drawing on the knowledge-based view (KBV). Based on our review of the literature, we argue that, as a boundary-specific resource, the local cultural knowledge (LCK) plays a central role in the development of CCCs. The paper explores the creation, diffusion, and utilization of LCK, facilitating the development of CCCs through three dimensions: urban regeneration, cultural preservation, and well-being promotion. Moreover, we further propose a triple-helix model of three interactive mechanisms among these three dimensions, namely gentrification, identification, and holistic sustainability. Three research propositions for developing successful CCCs are proposed. The paper concludes that the creation, diffusion, and utilization of LCK foster regional economic renewal, cultural preservation, and social welfare in a harmonious way. Some policy implications are suggested. [ABSTRACT FROM AUTHOR]

Scientifically identifying the spatial-temporal evolution characteristics of production-living-ecological space (PLES) and their inherent interrelationships is of great significance for achieving optimized spatial layout and sustainable development of national territory. In this study, multi-source spatial-temporal data were integrated to evaluate the heterogeneity and analyze the spatio-temporal evolution of PLES functions in China from 2000 to 2020. The authors identified the spatial clustering and coordination characteristics of PLES at the city level in China and proposed corresponding zoning and regulatory schemes accordingly. The results are as follows. (1) The overall spatial pattern of production space exhibited a trend of "high in the east and low in the west, with significant clustering and minimal dispersal," and overall expansion outweighed contraction during the study period. Along the Hu Huanyong Line living space generally followed a spatial pattern of "high in the east and low in the west" and remained relatively stable over the study period. Overall, ecological space in China exhibited a spatial pattern of being "higher in the hinterland and lower along the coast," displaying a trend of expansion throughout the study period. (2) During the period from 2000 to 2020, the spatial functions of PLES at the city level in China exhibited strong clustering characteristics. Among them, the positively correlated clustering areas of production space continued to expand, while the living space remained relatively stable. The positively correlated clustering areas of ecological space showed a pattern of "expansion in the northeast and contraction in the west." Based on this analysis, corresponding zoning and regulatory schemes were proposed in 2020 for different spatial clustering types at the city level in China. Production space was divided into agricultural development zone, urban development zone, potential development zone, and optimization and transformation zone. Living space was categorized into core living zone, potential residential zone, and moderate development zone. Ecological space was designated as ecological protection zone, function enhancement zone, and low-carbon development zone. (3) During the period from 2000 to 2020, the coupling and coordination degree of the spatial functions of PLES at the city level in China exhibited a spatial progression from west to east with the Hu Huanyong Line as the boundary. Its evolution exhibited waveform characteristics. Cities with high degrees of coupling and coordination primarily expanded outwards from the North China Plain and coastal areas of South China, whereas low-value areas gradually contracted towards the interior of northwestern regions. Based on this analysis, corresponding zoning and regulatory schemes were proposed in 2020 for the coordination degree of PLES at the city level in China. Specifically, they were categorized into production development zone, life gathering zone, collaborative development zone, living optimization zone, and living transformation zone. This comprehensive study meticulously discerns the multifaceted functions of PLES across diverse land plots of the same land type, and proposes zoning schemes and differentiated regulatory measures based on the clustering and coordination patterns characteristics in China. The diverse and meticulous analytical outcomes herein serve as invaluable scientific references for the meticulous development of China's territorial space. [ABSTRACT FROM AUTHOR]

The latest breakthroughs in spatially resolved transcriptomics technology offer comprehensive opportunities to delve into gene expression patterns within the tissue microenvironment. However, the precise identification of spatial domains within tissues remains challenging. In this study, we introduce AttentionVGAE (AVGN), which integrates slice images, spatial information and raw gene expression while calibrating low-quality gene expression. By combining the variational graph autoencoder with multi-head attention blocks (MHA blocks), AVGN captures spatial relationships in tissue gene expression, adaptively focusing on key features and alleviating the need for prior knowledge of cluster numbers, thereby achieving superior clustering performance. Particularly, AVGN attempts to balance the model's attention focus on local and global structures by utilizing MHA blocks, an aspect that current graph neural networks have not extensively addressed. Benchmark testing demonstrates its significant efficacy in elucidating tissue anatomy and interpreting tumor heterogeneity, indicating its potential in advancing spatial transcriptomics research and understanding complex biological phenomena. [ABSTRACT FROM AUTHOR]

The modeling and mapping of hotspots and coldspots ecosystem services (ESs) is an essential factor in the decision-making process for ESs conservation. Moreover, spatial prioritization is a serious stage in conservation planning. In the present research, based on the InVEST software, Getis–Ord statistics (Gi*), and a set of GIS methods, we quantified and mapped the variation and overlapping among three ESs (carbon storage, soil retention, and habitat quality). Furthermore, an approach was proffered for detecting priority areas to protect multiple ecosystem services. Hotspots recognized via the Gi* statistics technique contain a higher capacity for supplying ESs than other areas. This means that protecting these areas with a bigger number of overlapped hotspots can provide more services. Results indicated that population growth accompanied by the increase in construction sites and low-yield agricultural lands in the Zayanderood dam watershed basin has resulted in ES losses. This situation is represented by increasing soil erosion, reduced carbon storage, reduced biodiversity, and fragmented habitat distribution due to land-use change. The statistically significant carbon storage, soil retention, and habitat quality hotspots with above 95% confidence level account for 21.5%, 39.3%, and 16.9% of the study area, respectively. Therefore, a clear framework was presented in this study for setting ES-based conservation priority. Decision makers and land-use planners can also combine this technique into their framework to identify and conserve ES hotspots to support their targeted ecosystem policies. [ABSTRACT FROM AUTHOR]

This research introduces a novel framework for enhancing soybean cultivation in North America by categorizing growing environments into distinct ecological and maturity-based zones. Using an integrated analysis of long-term climatic data and records of soybean varietal trials, this research generates a zonal environmental characterization which captures major components of the growing environment which affect the range of adaptation of soybean varieties. These findings have immediate applications for optimizing multi-environment soybean trials. This characterization allows breeders to assess the environmental representation of a multi-environmental trial of soybean varieties, and to strategize the distribution of testing and the placement of test sites accordingly. This application is demonstrated with a historical scenario of a soybean multi-environment trial, using two resource allocation models: one targeted towards improving the general adaptation of soybean varieties, which focuses on widely cultivated areas, and one targeted towards specific adaptation, which captures diverse environmental conditions. Ultimately, the study aims to improve the efficiency and impact of soybean breeding programs, leading to the development of cultivars resilient to variable and changing climates. [ABSTRACT FROM AUTHOR]

Objectives: The mining of building cluster features in topographic maps is of great significance to realize automatic cartographic synthesis and spatial knowledge mining, but it is difficult to identify building polygon communities with different distribution densities and morphological characteristics in cities. Methods: A clustering method combining local outlier factor (LOF) is proposed. Based on the adjacency map of buildings, feature vectors are constructed according to the differences of form factors and proximity distances between adjacent buildings. LOF algorithm is used to dynamically calculate the anomaly degree of feature vectors and eliminate the abnormal vectors. And the building cluster is obtained. Results: By adjusting the upper limit of LOF local anomaly factor and proximity number, the final clustering results are obtained. The experimental results show that the proposed method can effectively identify and distinguish densely distributed building groups in the city. Conclusions: We provide a new way to solve the clustering problem of urban dense buildings, verify the importance of Gestalt criteria, and the clustering results are consistent with human visual cognition. [ABSTRACT FROM AUTHOR]

This paper explores the synergies between collective intelligence and edge computing, presenting a novel paradigm that harnesses decentralized processing power for collaborative problem-solving. Edge devices, such as sensors and IoT devices, collect spatial data in real time from their local environments. They can incorporate machine learning algorithms to analyze spatial data, enabling quicker and more context-aware decision-making. Spatial clustering, a pivotal strategy in IoT edge computing, is examined to optimize localized data processing, enhance resource efficiency, and enable real-time analytics in decentralized environments. By leveraging the physical proximity of devices, spatial clustering contributes to the effectiveness and sustainability of IoT deployments at the edge. The paper introduces an innovative approach to adaptive spatial clustering by adopting swarm intelligence, drawing inspiration from the collective behavior of a flock of birds. Building upon the classical flock model of Reynolds, our extended model incorporates movement in a multi-dimensional space and introduces different types of birds. In this context, the birds serve as agents for discovering points with specific characteristics in a multidimensional space. The integration of swarm intelligence into spatial clustering presents a promising avenue for addressing the challenges of decentralized processing in edge computing environments, paving the way for more efficient and responsive IoT deployments. [ABSTRACT FROM AUTHOR]

Clustering methods aim to categorize data or samples into distinct groups based on their similarity. When applying clustering methods to earthquake events, it is crucial to establish a metric for quantifying the similarity between these events. Directly applying this clustering method to a catalog of mining-induced seismicity may lead to clustering earthquake events induced by different mining activities or accidents into the same group. To address this issue, a two-step clustering method has been proposed and applied for analyzing a catalog of mining-induced seismicity. The first step involves spatial distance-based clustering of seismic events, while the second step focuses on moment tensor analysis-based clustering of these events. The results obtained from the MT-based clustering method are visualized using Hudson Graphs, and box plots serve as an evaluation tool for assessing the quality of MT clustering. Most box plots demonstrate desirable quality in terms of MT cluster results, indicating successful outcomes. By the proposed two-step clustering method combined with actual mining activities, the potential accident locations and categories can be hypothesized while valuable recommendations provided for mining operations. [ABSTRACT FROM AUTHOR]

Live-cell imaging of fluorescent biosensors has demonstrated that space-time correlations in signalling of cell collectives play an important organisational role in morphogenesis, wound healing, regeneration, and maintaining epithelial homeostasis. Here, we demonstrate how to quantify one such phenomenon, namely apoptosis-induced ERK activity waves in the MCF10A epithelium. We present a protocol that starts from raw time-lapse fluorescence microscopy images and, through a sequence of image manipulations, ends with ARCOS, our computational method to detect and quantify collective signalling. We also describe the same workflow in the interactive napari image viewer to quantify collective phenomena for users without prior programming experience. Our approach can be applied to space-time correlations in cells, cell collectives, or communities of multicellular organisms, in 2D and 3D geometries. [ABSTRACT FROM AUTHOR]

Lake sturgeon (Acipenser fulvescens), a potamodromous species, have been impacted by habitat fragmentation. Understanding the variation in population structure and spatial distribution in regulated and unimpeded rivers is valuable for recovery or rehabilitation purposes. The objectives of this study were to assess the relative abundance and spatial distribution of lake sturgeon in Rainy River and ascertain demographics of inhabitant juveniles. A standardized, index-netting study was conducted in the Rainy River to target juvenile and adult lake sturgeon. A total of 472 juvenile and 56 adult lake sturgeon were sampled. Juvenile and adult lake sturgeon were found throughout the river; however, juvenile relative abundance was greatest in the lowest river section close to the confluence with Lake of the Woods. Spatial clustering of juveniles and to lesser extent adults was also evident but adults were not necessarily segregated from juveniles. Juvenile annual survival rates were estimated to be approximately 75% and recruitment within this population was detected in all years but was variable in size. There were strong and weak year classes produced; however, they could not be explained by any of the environmental variables assessed. [ABSTRACT FROM AUTHOR]

Cardiovascular Disease (CVD) is currently the major challenge to people’s health and the world’s top cause of death. In Tanzania, deaths due to CVD account for about 13% of the total deaths caused by the non-communicable diseases. This study examined the spatio-temporal clustering of CVDs from 2010 to 2019 in Tanzania for retrospective spatio-temporal analysis using the Bernoulli probability model on data sampled from four selected hospitals. Spatial scan statistics was performed to identify CVD clusters and the effect of covariates on the CVD incidences was examined using multiple logistic regression. It was found that there was a comparatively high risk of CVD during 2011-2015 followed by a decline during 2015-2019. The spatio-temporal analysis detected two high-risk disease clusters in the coastal and lake zones from 2012 to 2016 (p

Abstract Both developed and developing countries carry a large burden of pediatric intussusception. Sentinel site surveillance-based studies have highlighted the difference in the regional incidence of intussusception. The objectives of this manuscript were to geospatially map the locations of hospital-confirmed childhood intussusception cases reported from sentinel hospitals, identify clustering and dispersion, and reveal the potential causes of the underlying pattern. Geospatial analysis revealed positive clustering patterns, i.e., a Moran’s I of 0.071 at a statistically significant (p value

Abstract Marine heatwaves are causing recurring coral bleaching events on tropical reefs that are driving ecosystem change. Yet, little is known about how bleaching and subsequent coral mortality impacts the spatial properties of tropical seascapes, such as patterns of organism spatial clustering and heterogeneity across scales. Changes in these spatial properties can offer insight into ecosystem recovery potential following disturbance. Here we repeatedly quantified coral reef benthic spatial properties around the circumference of an uninhabited tropical island in the central Pacific over a 9‐year period that included a minor and subsequent severe marine heatwave. Benthic communities showed increased biotic homogenisation following both minor and mass bleaching, becoming more taxonomically similar with less diverse intra‐island community composition. Hard coral cover, which was highly spatially clustered around the island prior to bleaching, became less spatially clustered following minor bleaching and was indiscernible from a random distribution across all scales (100–2000 m) following mass bleaching. Interestingly, the reduced degree of hard coral cover spatial clustering was already evident by the onset of mass bleaching and before any dramatic wholesale loss in island‐mean coral cover occurred. Reductions in hard coral spatial clustering may therefore offer an early indication of the ecosystem becoming degraded prior to mass coral mortality. In contrast, the spatial clustering of competitive fleshy macroalgae remained unchanged through both bleaching events, while crustose coralline algae and fleshy turf algae became more spatially clustered at larger scales (200–700 m) following mass bleaching. Overall, benthic community spatial patterning became less predictable following bleaching and was no longer reflective of gradients in long‐term environmental drivers that typically structure these remote reefs. Our findings provide novel insights into how climate‐driven marine heatwaves can impact the spatial properties of coral reef communities over multiple scales.

This paper addresses the challenge of identifying the paths for vessels with operating routes of repetitive paths, partially repetitive paths, and new paths. We propose a spatial clustering approach for labeling the vessel paths by using only position information. We develop a path clustering framework employing two methods: a distance-based path modeling and a likelihood estimation method. The former enhances the accuracy of path clustering through the integration of unsupervised machine learning techniques, while the latter focuses on likelihood-based path modeling and introduces segmentation for a more detailed analysis. The result findings highlight the superior performance and efficiency of the developed approach, as both methods for clustering vessel paths into five clusters achieve a perfect F1-score. The approach aims to offer valuable insights for route planning, ultimately contributing to improving safety and efficiency in maritime transportation.

This research proposes a dam deformation prediction model based on clustering partitioning and Bidirectional Long Short-Term Memory (BiLSTM) networks to address the limitations of traditional monitoring models in characterizing the distribution characteristics of deformation zones in concrete gravity dams. The model takes into account the intrinsic correlations among monitoring points and achieves more comprehensive deformation monitoring by integrating multiple feature information. Firstly, the improved K-Shape algorithm, which takes into account the time series features and spatial coordinate relationships, is used to cluster and partition the spatial measurement points to better capture the spatial distribution characteristics of the deformation region. Following that, the model hyperparameters undergo iterative optimization using the ZOA optimization algorithm to enhance overall model performance. Finally, a ZOA-BiLSTM modelling process incorporating the correlation characteristics of multiple measurement points is proposed. After validation by engineering examples, the clustering results coincide with the spatial distribution characteristics of dam deformation. Meanwhile, the prediction model has high accuracy and robustness, and predicts the dam deformation from the multi-measurement point correlation dimension, which provides a new and effective method to monitor the overall safety state of the dam.

Abstract Optimal integration of transcriptomics data and associated spatial information is essential towards fully exploiting spatial transcriptomics to dissect tissue heterogeneity and map out inter-cellular communications. We present SEDR, which uses a deep autoencoder coupled with a masked self-supervised learning mechanism to construct a low-dimensional latent representation of gene expression, which is then simultaneously embedded with the corresponding spatial information through a variational graph autoencoder. SEDR achieved higher clustering performance on manually annotated 10 × Visium datasets and better scalability on high-resolution spatial transcriptomics datasets than existing methods. Additionally, we show SEDR’s ability to impute and denoise gene expression (URL: https://github.com/JinmiaoChenLab/SEDR/ ).

The spatial variation in seasonal sea ice in Hudson Bay is examined using spatial clustering analyses. For the period 1971 to 2018, a time series of sea-ice breakup and freeze-up dates and ice-free season length at thirty-six grid locations is generated from sea-ice charts derived from satellites and other data. These data are analyzed spatially using three different clustering techniques. Overall, the three methods revealed a northeast/southwest axis in sea-ice behavior consistent with a well-documented cyclonic current flow and wind regime in Hudson Bay. The methods did differ in assigning grid locations to clusters with the greatest consistency for breakup behavior and in the northern region of the Bay across all three metrics. The greatest variability occurred with the central sea-ice platform likely the response to only subtle variations among these locations, leading to varying clusters. Missing data especially with freeze-up and ice-free season played a role in the clustering.

Improving nitrogen (N) management are crucial for food security and ecological protection in China and globally. Assessing the contribution and influence characteristics of N input components on crop growth is a key component. There are challenges in conducting such assessments at large regional scales, particularly in developing models that fit regional N inputs and crop N uptake. An improved scheme that fit regional N inputs and crop N uptake with consideration of spatial heterogeneity of cultivation conditions was proposed. Based on the division of homogeneous cultivation conditions zones, linear models and Random Forest models were developed to assess the contribution and influence characteristics of N input components on crop growth at the provincial scale in mainland China. And synthetic N contribution rate (SNCR) and soil fertility N contribution (SFNC) were innovatively proposed to represent the contribution of fertilizer and soil fertility to crop growth. The results showed that the overall N use efficiency ranged from 35 % to 55 % in 1985–2020, and higher NUE could be seen in major grain producing provinces. The SNCR generally declined, with a spatial pattern higher in the southwest, northwest, and northeast regions. The SFNC showed an increasing trend, with a spatial pattern higher in the northeast than southeast than west. For each N input component, Synthetic N input was critical in the northwest, southwest regions and north China, positively affecting crop N uptake. The improved scheme, which incorporated considerations for spatial heterogeneity, demonstrated superior accuracy compared to the model fitted by year, increasing from 0.27 (0.11) to 0.42 (0.47). Over the past 35 years, the crop N uptake and N surplus of mainland China had experienced a process of extensive-unsustainable-sustainable-conservative pattern changes. The response of crop N uptake and N use efficiency to the regulation of N inputs in typical regions was simulated, providing reference for provincial N inputs regulation in China. This study can provide support for the design of N management strategies in China to reduce N pollution, and the method can provide guidance for other regions to assess N use in different scales.

Background: During the past two decades, research on high-intensity interval exercise (HIIE) in children and adolescents has steadily accumulated, especially on the subthemes of improving cardiometabolic and cardiovascular health. However, there is still little scientific understanding of using scientometric analysis to establish knowledge maps. Exploring the relationship between known and new emerging ideas and their potential value has theoretical and practical implications in the context of a researcher's limited ability to read, analyze, and synthesize all published works. Objective: First, this study aims to provide extensive information on HIIE research in children and adolescents, including authors, institutions, countries, journals, and references. Second, the objective is to use co-occurrence, burst, and cocitation analyses based on hybrid node types to reveal hotspots and forecast frontiers for HIIE research in children and adolescents. Methods: Using the bibliographic data of the Web of Science Core Collection (WoSCC) as the data source, publications, authors, and journals were analyzed with the help of bibliometric methods and visualization tools such as CiteSpace, VOSviewer, Pajek, and Bibliometrix R package. Authorial, institutional, and national collaboration networks were plotted, along with research hotspots and research frontiers based on keyword bursts and document co-citations. Results: This study found that executive function, high-intensity interval training, heart rate variability, and insulin resistance are emerging research topics; highintensity training, mental health, exercise intensity, and cardiometabolic risk factors are continual frontier research areas in the subthemes. Conclusion: Our study has three novel contributions. First, it explicitly and directly reflects the research history and current situation of the HIIE intervention strategy in children and adolescents. This approach makes it clear and easy to trace the origin and development of this strategy in specific groups of children and adolescents. Second, it analyzes the research hotspots of HIIE in the field and predicts the research frontiers and development trends, which will help researchers get a deeper understanding of HIIE and pediatric health research. Third, the findings will enable researchers to pinpoint the most influential scholars, institutions, journals, and references in the field, increasing the possibility of future collaborations between authors, institutions, and countries. [ABSTRACT FROM AUTHOR]

Camera traps or acoustic recorders are often used to sample wildlife populations. When animals can be individually identified, these data can be used with spatial capture-recapture (SCR) methods to assess populations. However, obtaining animal identities is often labor-intensive and not always possible for all detected animals. To address this problem, we formulate SCR, including acoustic SCR, as a marked Poisson process, comprising a single counting process for the detections of all animals and a mark distribution for what is observed (eg, animal identity, detector location). The counting process applies equally when it is animals appearing in front of camera traps and when vocalizations are captured by microphones, although the definition of a mark changes. When animals cannot be uniquely identified, the observed marks arise from a mixture of mark distributions defined by the animal activity centers and additional characteristics. Our method generalizes existing latent identity SCR models and provides an integrated framework that includes acoustic SCR. We apply our method to estimate density from a camera trap study of fisher (Pekania pennanti) and an acoustic survey of Cape Peninsula moss frog (Arthroleptella lightfooti). We also test it through simulation. We find latent identity SCR with additional marks such as sex or time of arrival to be a reliable method for estimating animal density. [ABSTRACT FROM AUTHOR]

The study of carbon budget and carbon compensation zoning is of great significance in formulating strategies to adapt to the low-carbon development of each region, promoting synergistic management of regional ecological environment, and realizing high-quality develop‐ ment. This paper takes 56 municipal units in the Yellow River Basin as the study area, and by constructing a conceptual structure of carbon income and expenditure as well as carbon compensation zoning of the cities in the basin, it studies the spatio-temporal differentiation law of carbon income and expenditure as well as carbon compensation zoning of the urban agglomerations in the Yellow River Basin by using methods such as the centralization index and the location-con‐ strained multivariate spatial clustering, and then it provides constructive theoretical solutions for the low-carbon development strategy in the process of urbanization. The study shows that: (1) the cities in the Yellow River Basin from 2000 to 2020 are characterized by obvious geographical differentiation of carbon expenditure and revenue, specifically, the carbon expenditure and revenue centralization index of the study area fluctuates up and down around the warning line of 0. 4, and the overall curve shows an obvious fluctuating upward trend. (2) The spatial and temporal variation of carbon income and expenditure among cities in the Yellow River Basin is remarkable, and the data show that carbon emissions in the Yellow River Basin show a structure of "low in the west and high in the east and central parts of the country", with the high-value centres in Gansu, Shaanxi and Shandong provinces in 2000, and then the number of high-value areas of carbon emissions has increased year by year, while at the same time, the absorptive capacity of carbon sinks in each city is roughly equal. (3) Based on the framework of carbon offset zoning, the study area is divided into five types of carbon offset spatial optimization zones, and suggestions are made for green and low-carbon development planning in different types of zones. (4) In the future, the study will refine the spatial scale of the study area, explore the balance of carbon budget and carbon compensation of smaller units, and strive to explore the optimization of the green and low-carbon development mode of small areas, so that the energy conservation and emission reduction and green development of small areas can lead the cities in the region to achieve the dual-carbon goal. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Xi'an Jiaotong University is the property of Editorial Office of Journal of Xi'an Jiaotong University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: A heterogeneous geographic distribution of childhood acute lymphoblastic leukemia (ALL) cases has been described, possibly, related to the presence of different environmental factors. The aim of the present study was to explore the geographical distribution of childhood ALL cases in Greater Mexico City (GMC). Methods: A population-based case-control study was conducted. Children <18 years old, newly diagnosed with ALL and residents of GMC were included. Controls were patients without leukemia recruited from second-level public hospitals, frequency-matched by sex, age, and health institution with the cases. The residence address where the patients lived during the last year before diagnosis (cases) or the interview (controls) was used for geolocation. Kulldorff's spatial scan statistic was used to detect spatial clusters (SCs). Relative risks (RR), associated p-value and number of cases included for each cluster were obtained. Results: A total of 1054 cases with ALL were analyzed. Of these, 408 (38.7%) were distributed across eight SCs detected. A relative risk of 1.61 (p<0.0001) was observed for the main cluster. Similar results were noted for the remaining seven ones. Additionally, a proximity between SCs, electrical installations and petrochemical facilities was observed. Conclusions: The identification of SCs in certain regions of GMC suggest the possible role of environmental factors in the etiology of childhood ALL. [ABSTRACT FROM AUTHOR]

This paper proposes a novel unsupervised classification method to solve the problem of mechanical fault diagnosis under the condition of unknown number of fault types. The proposed method combining the three data processing stage. First, the deep encoding neural networks is used to complete the abstract signal feature representation under the unsupervised conditions. Second, the feature dimensionality reduction technique based on manifold learning is used to complete the low-dimensional mapping of the feature space. Third, the spatial clustering based on density criterion is introduced to classify the different fault samples. This paper uses two fault signals dataset to complete the performance verification experiment. The experimental results show that the DMDUC method respectively achieves the classification accuracy of 99.7 % and 100 % on the two datasets. [ABSTRACT FROM AUTHOR]

This research aims to explore the spatiotemporal distribution patterns of negative emotions in mainland China during different stages of the COVID-19 pandemic and the external factors influencing this clustering. Using Baidu Index data for 91 negative emotion keywords, a retrospective geographic analysis was conducted across Chinese provinces from 14 October 2019 to 7 July 2022. Four spatial analysis methods (Global Moran's Index, Local Moran's Index, Bivariate Global Moran's Index, and Bivariate Local Moran's Index) are employed to identify potential clustering patterns and influencing factors of negative emotions at different stages. The results indicate that the COVID-19 pandemic significantly intensified the clustering effect of negative emotions in China, particularly with a more pronounced radiation effect in northwestern provinces. Spatial positive correlations are observed between pandemic-related Baidu indices (pandemic Baidu index, government Baidu index, nucleic acid Baidu index) and negative emotions. These findings contribute to understanding the spatiotemporal distribution characteristics of negative emotions in China post the COVID-19 outbreak and can guide the allocation of psychological resources during emergencies, thereby promoting social stability. [ABSTRACT FROM AUTHOR]

The study examined the impact of eco-environmental quality conditions, spatial configurations and landscape connectivity of urban vegetation on seasonal land surface temperature (LST) in Harare, Zimbabwe between May and October 2018. The results showed that densely built-up areas with sparse vegetation experienced extremely poor eco-environmental conditions. Clustered and highly connected were more beneficial in decreasing LST. These findings have important urban and landscape planning implications regarding how the spatial configuration and landscape connectivity patterns of urban vegetation can be optimized to mitigate Urban Heat Island (UHI) effects and to improve the thermal comfort conditions in rapidly urbanizing cities. [ABSTRACT FROM AUTHOR]

Marine heatwaves are causing recurring coral bleaching events on tropical reefs that are driving ecosystem change. Yet, little is known about how bleaching and subsequent coral mortality impacts the spatial properties of tropical seascapes, such as patterns of organism spatial clustering and heterogeneity across scales. Changes in these spatial properties can offer insight into ecosystem recovery potential following disturbance. Here we repeatedly quantified coral reef benthic spatial properties around the circumference of an uninhabited tropical island in the central Pacific over a 9‐year period that included a minor and subsequent severe marine heatwave. Benthic communities showed increased biotic homogenisation following both minor and mass bleaching, becoming more taxonomically similar with less diverse intra‐island community composition. Hard coral cover, which was highly spatially clustered around the island prior to bleaching, became less spatially clustered following minor bleaching and was indiscernible from a random distribution across all scales (100–2000 m) following mass bleaching. Interestingly, the reduced degree of hard coral cover spatial clustering was already evident by the onset of mass bleaching and before any dramatic wholesale loss in island‐mean coral cover occurred. Reductions in hard coral spatial clustering may therefore offer an early indication of the ecosystem becoming degraded prior to mass coral mortality. In contrast, the spatial clustering of competitive fleshy macroalgae remained unchanged through both bleaching events, while crustose coralline algae and fleshy turf algae became more spatially clustered at larger scales (200–700 m) following mass bleaching. Overall, benthic community spatial patterning became less predictable following bleaching and was no longer reflective of gradients in long‐term environmental drivers that typically structure these remote reefs. Our findings provide novel insights into how climate‐driven marine heatwaves can impact the spatial properties of coral reef communities over multiple scales. [ABSTRACT FROM AUTHOR]

Optimal integration of transcriptomics data and associated spatial information is essential towards fully exploiting spatial transcriptomics to dissect tissue heterogeneity and map out inter-cellular communications. We present SEDR, which uses a deep autoencoder coupled with a masked self-supervised learning mechanism to construct a low-dimensional latent representation of gene expression, which is then simultaneously embedded with the corresponding spatial information through a variational graph autoencoder. SEDR achieved higher clustering performance on manually annotated 10 × Visium datasets and better scalability on high-resolution spatial transcriptomics datasets than existing methods. Additionally, we show SEDR's ability to impute and denoise gene expression (URL: https://github.com/JinmiaoChenLab/SEDR/). [ABSTRACT FROM AUTHOR]

Geological modeling is essential for the characterization of natural phenomena and can be done in two steps: (1) clustering the data into consistent groups and (2) modeling the extent of these groups in space to define domains, honoring the labels defined in the previous step. The clustering step can be based on the information of continuous multivariate data in space instead of relying on the geological logging provided. However, extracting coherent spatial multivariate information is challenging when the variables show complex relationships, such as nonlinear correlation, heteroscedastic behavior, or spatial trends. In this work, we propose a method for clustering data, valid for domaining when multiple continuous variables are available and robust enough to deal with cases where complex relationships are found. The method looks at the local correlation matrix between variables at sample locations inferred in a local neighborhood. Changes in the local correlation between these attributes in space can be used to characterize the domains. By endowing the space of correlation matrices with a manifold structure, matrices are then clustered by adapting the K-means algorithm to this manifold context, using Riemannian geometry tools. A real case study illustrates the methodology. This example demonstrates how the clustering methodology proposed honors the spatial configuration of data delivering spatially connected clusters even when complex nonlinear relationships in the attribute space are shown. [ABSTRACT FROM AUTHOR]