Self-organizing Map Research Articles

Study on the genesis and development trend of tropical depressions under different large-scale backgrounds

Based on self-organizing maps (SOM), large-scale backgrounds associated with tropical depression (TD) genesis over the western North Pacific (WNP) in 1949–2021 are classified into four circulation patterns, monsoon gyre (MG) pattern, monsoon confluence (MC) pattern, monsoon trough (MT) pattern and easterly wave (EW) pattern. TDs generated in the MC pattern has the southernmost average genesis location and the highest development probability, while TDs occurred in the EW pattern are averagely located northernmost and their probability of development is the lowest. TDs formed in the MG, MT and EW patterns are most active in August, whereas in the MC pattern, TD genesis number peaks in October. Advantageous conditions for TD genesis vary in different circulation patterns. The vigorous vorticity "embryo" provides stronger initial disturbances for MG pattern; The strong upper-level divergence and the weak deep-layer VWS provide sufficient dynamic conditions for the MC pattern; The MT pattern possess the highest SST, which supplies an ample supply of heat and moisture; The EW pattern has less beneficial conditions compared with other three patterns. The Extreme Gradient Boosting (XGBoost) method is applied to quantify the relative importance of individual factors to TD development trend. 500-hPa vorticity, 200-hPa divergence and SST are major dynamic and thermal affecting factors for TD development, the importance of which all ranked at top four in the four patterns; VWS plays an indispensable role in TD development for the MC and EW patterns; Comparely,850-hPa vorticity and vertically integrated water vapor flux are not as important as above environmental factors in deciding whether a TD develops.

CHARACTERIZATION OF A FLUVIAL DELTAIC SALT-INFLUENCED SYSTEM FOR CO2 STORAGE USING SEISMIC POST-STACK INVERSION AND SELF-ORGANIZING MAPS IN THE UPPER MIOCENE, ONSHORE LOUISIANA

Basins that have historically been explored for hydrocarbons are now seen through a new perspective for carbon capture and storage. Legacy hydrocarbon reservoirs may now have the potential to become carbon storage targets. The Miocene Sandstone in south Louisiana is a stratigraphic interval that contains favorable zones for carbon storage, and seismic interpretation is a critical tool for characterizing these sands and estimating the amount of possible carbon storage. New workflows leveraging machine learning and seismic inversion can be applied to legacy fields to generate a new estimate for pore space and carbon storage capacity. The study area contains a 3D seismic survey covering 310 mi2 (803 km2) and 16 wells. Using these data, the workflow leverages self-organized maps (SOM) to identify zones of interest both laterally and vertically for carbon storage. SOM provides an uplift in resolution for interpretation compared to single attributes. A model-based acoustic impedance inversion produces porosity information that is used in tandem with SOM outputs. The acoustic impedance results strongly correlate to porosity within the target sands, and the SOM and porosity maps delineate specific sand lobes for potential storage. Wellbore data within the sand lobe align with SOM and inversion results and show rock quality with 26% average porosity and 90 feet gross thickness. The research highlights a project sized target within the middle Miocene containing 10.3 Megatons of estimated CO2 storage. Using SOM and inversion maps in tandem is an effective way for screening an area for carbon storage targets.

Machine learning approach to flare-up detection and clustering in chronic obstructive pulmonary disease (COPD) patients.

Chronic obstructive pulmonary disease (COPD) is a prevalent and preventable condition that typically worsens over time. Acute exacerbations of COPD significantly impact disease progression, underscoring the importance of prevention efforts. This observational study aimed to achieve two main objectives: (1) identify patients at risk of exacerbations using an ensemble of clustering algorithms, and (2) classify patients into distinct clusters based on disease severity. Data from portable medical devices were analyzed post-hoc using hyperparameter optimization with Self-Organizing Maps (SOM), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Isolation Forest, and Support Vector Machine (SVM) algorithms, to detect flare-ups. Principal Component Analysis (PCA) followed by KMeans clustering was applied to categorize patients by severity. 25 patients were included within the study population, data from 17 patients had the required reliability. Five patients were identified in the highest deterioration group, with one clinically confirmed exacerbation accurately detected by our ensemble algorithm. Then, PCA and KMeans clustering grouped patients into three clusters based on severity: Cluster 0 started with the least severe characteristics but experienced decline, Cluster 1 consistently showed the most severe characteristics, and Cluster 2 showed slight improvement. Our approach effectively identified patients at risk of exacerbations and classified them by disease severity. Although promising, the approach would need to be verified on a larger sample with a larger number of recorded clinically verified exacerbations.

Correlation between Different Factors of Non-point Source Pollution in Yangtze River Basin

This research used the improved export coefficient model to estimate non-point source load in sub-watersheds and a self-organizing map model to identify the correlation relationship of factors, that can be affected by non-point source load in Yangtze River Basin. Research results indicate that total nitrogen load is 4.87 - 15.53 kg/ha; total phosphorus load is 0.18 - 0.51 kg/ha; Dong Ting Lake sub-basin has the lowest contribution value of total nitrogen and phosphorus; Tai Lake sub-basin has the highest contribution load of total nitrogen and total phosphorus; Jinsha River sub-basin reveals the highest value of total nitrogen and phosphorus contribution on grassy land and desert land; Tai Lake sub-basin has the highest total nitrogen and total phosphorus load on forest, agricultural land, and urban construction land. The correlation relationship of factors reveals a very close correlation with each other as precipitation, total nitrogen load, and total phosphorus load factors have correlation in the highest value, in which total nitrogen load and total phosphorus load factors have a close correlation with each other from the lowest value to highest value; wetland and barren land factors correlate with the lowest value and the highest value; agricultural land, forestland, and grassy land factors correlate with one another in the high value and the highest value. The forest cover rate factor, as well as the population factor, does not correlate with other factors.

Development of an evaluation method for precipitation particle types by using disdrometer data

Abstract A method for evaluating precipitation particle types from the size-fall velocity data observed by disdrometers by combining an expectation-maximization (EM) algorithm and a self-organizing map (SOM) was developed. An EM algorithm was used to estimate the particle size-fall velocity relationships according to previous work, and the SOM map was used to classify the relationships into graupel or snow categories. The method was applied for snowfall data observed by the volume scanning video disdrometer at a site in Sapporo, Japan, and the daily graupel-to-solid precipitation ratio (G/S ratio) from 1 December, 2017 to 28 February, 2018 was obtained. The sensitivity of the results to different SOM configurations, SOM node groupings, and training datasets was also tested. The G/S ratio obtained from the simulation data of a meteorological model was compared as an example of the application of the product created by the new method.

A self-organizing map clustering adaptive artificial neural network model for analysis critical success factors in different phases of MTO projects case study: electrical equipment manufacturer and supplier in Iran

PurposeThe purpose of this paper is to investigate the benefit of critical success factors (CSFs) clustering in different phases of make-to-order (MTO) projects and develop standards for management.Design/methodology/approachThis study is based on a questionnaire survey. First of all, collecting data by structured interviews, relying on a questionnaire and second from leader contractors who are active in the engineering and steel industry (in Iran). So, the requirements and objective of the research are presented to the top management of MTO projects to gain their support in data collection. Then 20 CSFs were identified by the literature review so a questionnaire survey was prepared for the CSFs assessment and interview with the experts. Finally analyzing the importance and performance of CSFs in project phases and cluster them in different project phases with self-organizing map as one of the artificial neural network (ANN) approaches due to high predictive accuracy. Review the research result with the top management of MTO project and examine the results obtained from neural networks and validation indices.FindingsCluster analysis shows that the implementation phase is the most important stage in MTO organizations and the other phases like feasibility and start-up, design and planning, delivery and end-phase should be also considered as effective phases in determining the level of organization performance. Different industries with additional data at different periodic times will verify the result. Furthermore, testing the other ANN model will improve risk analysis and could shift this classification approach to a regression type.Research limitations/implicationsThe main limitation of the research is related to the sample. Research findings are limited to the time of data collection so validity is limited to the mentioned time. Different industries with additional data will verify the result. Furthermore, testing different ANN models such as K-MEANS, non-negative matrix factorization (NMF) analyses will improve risk analysis and could meet different classification results to find gaps.Practical implicationsIn this paper, CSF and project phase dimensions are viewed together which is necessary to meet better results for simplifying social and economic benefits. Merge the new findings and latest technologies could prepare the best results and enable managers to create a better framework or implement key factors for minimizing waste.Originality/valueThis paper moves the definition of MTO organizations beyond measuring cost, complexity and financial variables by clustering CSFs in different phases of projects. So, the results enable managers to use this concept in their daily production to minimize waste and could be implemented to efficiently choose factors.

Application of intelligent self-organizing algorithms in UAV cooperative inspection of power distribution networks

In the rapidly evolving technological landscape, the advent of collaborative Unmanned Aerial Vehicle (UAV) inspections represents a revolutionary leap forward in the monitoring and maintenance of power distribution networks. This innovative approach harnesses the synergy of UAVs working together, marking a significant milestone in enhancing the reliability and efficiency of infrastructure management. Despite its promise, current research in this domain frequently grapples with challenges related to efficient coordination, data processing, and adaptive decision-making under complex and dynamic conditions. Intelligent self-organizing algorithms emerge as pivotal in addressing these gaps, offering sophisticated methods to enhance the autonomy, efficiency, and reliability of UAV collaborative inspections. In response to these challenges, we propose the MARL-SOM-GNNs network model, an innovative integration of Multi-Agent Reinforcement Learning, Self-Organizing Maps, and Graph Neural Networks, designed to optimize UAV cooperative behavior, data interpretation, and network analysis. Experimental results demonstrate that our model significantly outperforms existing approaches in terms of inspection accuracy, operational efficiency, and adaptability to environmental changes. The significance of our research lies in its potential to revolutionize the way power distribution networks are inspected and maintained, paving the way for more resilient and intelligent infrastructure systems. By leveraging the capabilities of MARL for dynamic decision-making, SOM for efficient data clustering, and GNNs for intricate network topology understanding, our model not only addresses current shortcomings in UAV collaborative inspection strategies but also sets a new benchmark for future developments in autonomous infrastructure monitoring, highlighting the crucial role of intelligent algorithms in advancing UAV technologies.

Application of Linear Mixed-Effects Model, Principal Component Analysis, and Clustering to Direct Energy Deposition Fabricated Parts Using FEM Simulation Data.

The purpose of this study is to investigate the effects of toolpath patterns, geometry types, and layering effects on the mechanical properties of parts manufactured by direct energy deposition (DED) additive manufacturing using data analysis and machine learning methods. A total of twelve case studies were conducted, involving four distinct geometries, each paired with three different toolpath patterns based on finite element method (FEM) simulations. These simulations focused on residual stresses, strains, and maximum principal stresses at various nodes. A comprehensive analysis was performed using a linear mixed-effects (LME) model, principal component analysis (PCA), and self-organizing map (SOM) clustering. The LME model quantified the contributions of geometry, toolpath, and layer number to mechanical properties, while PCA identified key variables with high variance. SOM clustering was used to classify the data, revealing patterns related to stress and strain distributions across different geometries and toolpaths. In conclusion, LME, PCA, and SOM offer valuable insights into the final mechanical properties of DED-fabricated parts.

Mapping the technological landscape of green smart buildings: A patent analytics of key topics, leading companies, and technology gaps

In this study, we investigate the technological landscape of green smart buildings, using patent data from the European Patent Office (EPO) from 2007 onwards. Latent Dirichlet Allocation identified five key technology topics, with the HVAC system (Topic 4) emerging as particularly promising. Technology life cycle analysis revealed a growth phase for leading companies' patents after the Kyoto Protocol's second commitment period, with a predicted shift towards maturity after the Paris Agreement. Self-Organizing Maps and Social Network Analysis further pinpointed eight vacant technology nodes and 39 high-centrality patents within them, predominantly held by Japanese companies. This research provides valuable insights into the current state and future trajectory of green smart building technologies, facilitating informed decision-making for industry stakeholders and contributing to a more sustainable built environment. The novelty lies in the combined application of topic modeling, technology life cycle analysis, and network analysis to comprehensively explore the green smart building patent landscape, offering a unique perspective on its evolution and potential future directions.

Influence of Carbon-Nitride Dot-Emitting Species and Evolution on Fluorescence-Based Sensing and Differentiation.

Carbon dots have attracted widespread interest for sensing applications based on their low cost, ease of synthesis, and robust optical properties. We investigate structure-function evolution on multiemitter fluorescence patterns for model carbon-nitride dots (CNDs) and their implications on trace-level sensing. Hydrothermally synthesized CNDs with different reaction times were used to determine how specific functionalities and their corresponding fluorescence signatures respond upon the addition of trace-level analytes. Archetype explosives molecules were chosen as a testbed due to similarities in substituent groups or inductive properties (i.e., electron withdrawing), and solution-based assays were performed using ratiometric fluorescence excitation-emission mapping (EEM). Analyte-specific quenching and enhancement responses were observed in EEM landscapes that varied with the CND reaction time. We then used self-organizing map models to examine EEM feature clustering with specific analytes. The results reveal that interactions between carbon-nitride frameworks and molecular-like species dictate response characteristics that may be harnessed to tailor sensor development for specific applications.

A Method for Predicting the Impact of Labor Education at Institutions of Higher Education Based on a Two-Stage Clustering Algorithm

In order to develop more accurate teaching plans and methods based on students’ characteristics and needs, and improve the effectiveness of labor education, a two-stage clustering algorithm based method for predicting the effectiveness of labor education in universities is studied. A two-stage clustering algorithm-based method for predicting the effectiveness of labor education in universities has been proposed. Through in-depth analysis of labor education data in universities, principal component analysis (PCA) was used to select 16 most representative variables from the original features. Subsequently, self-organizing map (SOM) neural network was used for preliminary clustering, and the optimal number of clusters was determined to be 8. Furthermore, the K-means clustering algorithm performs fine clustering based on the initial centers provided by SOM, significantly improving the stability and accuracy of clustering. At the same time, processing the outliers in the clustering results has reduced their impact on the clustering effect. Finally, the processed data was input into an improved XGBoost prediction model, which achieved a true positive rate (TPR) of over 85% on the ROC curve when predicting the effectiveness of labor education in universities. While maintaining a low false positive rate (FPR), the model outperformed other comparison methods significantly. This achievement not only validates the effectiveness of the proposed method in feature selection, clustering optimization, and prediction model construction, but also confirms its ability to accurately predict the labor education effectiveness of students in different grades, providing strong support for higher education institutions to optimize teaching plans and improve educational outcomes.

Data-driven machine learning approaches for precise lithofacies identification in complex geological environments

ABSTRACT Reservoir characterization is a vital task within the oil and gas industry, with the identification of lithofacies in subsurface formations being a fundamental aspect of this process. However, lithofacies identification in complex geological environments with high dimensions, such as the Lower Indus Basin in Pakistan, poses a notable challenge, especially when dealing with limited data. To address this issue, we propose four common data-driven machine learning approaches: multi-resolution graph-based clustering (MRGC), artificial neural networks (ANN), K-nearest neighbors (KNN), and self-organizing map (SOM). We utilized these proposed approaches to assess their performance in scenarios with varying core sample availability, specifically evaluating their effectiveness in identifying lithofacies within the Lower Goru formation of the middle Indus Basin. The study reveals that in scenarios with a limited number of core samples, MRGC is the preferred choice, while KNN or MRGC is more suitable for larger datasets. The results demonstrate the superior performance of MRGC and KNN in lithofacies identification within the specified geological environment, with SOM following closely behind, and ANN exhibiting comparatively lower efficacy. The accurate identification of lithofacies from the selected model is complemented by the application of the truncated Gaussian simulation method for facies modeling. Comparative results confirm the excellent agreement between the model identification of lithofacies from well logs and electro-facies obtained from the truncated Gaussian simulation electro-facies volume. This study highlights the crucial role of selecting the right machine learning approach for precise lithofacies identification and modeling in complex geological environments. The comparative analysis provides practitioners in the petroleum industry with insights into the strengths and limitations of each method, enhancing existing knowledge. In conclusion, this research emphasizes the significance of comprehensive research and method selection for advancing lithofacies identification in diverse formations or study areas, ultimately benefiting the broader field of subsurface characterization in the petroleum industry.

Exploring spatial and seasonal water quality variations in Kelani River, Sri Lanka: a latent variable approach.

Water quality degradation poses a significant challenge globally, especially in developing nations like Sri Lanka. Extensive monitoring programs designed to address escalating river pollution collect multiple water quality parameters over extended periods and varied locations. However, the sheer volume of data can be overwhelming, making it difficult to process effectively and interpret accurately using conventional methods. In this study, latent variable (LV) and unsupervised machine learning techniques were used to investigate spatial and seasonal variations of surface water quality for 17 parameters across 17 locations along the Kelani River, Sri Lanka, using monthly water quality parameters from 2016 to 2020. Pearson's correlation matrix identified 10 parameters significantly affecting water quality variations and factor analysis (FA) generated five LVs, accounting for 77% of the total variance in the dataset. The identified LVs showed multiple methods of river pollution.Hierarchical clustering analysis and self-organizing mapping methods clustered stations in a closely analogous manner. Stations near industrial zones and the river mouth showed higher water quality variance, often exceeding national guidelines. Correlation testing revealed strong relationships between water quality and catchment hydrometeorological variations during monsoonal seasons. Spatial analyses showed increased LV variance in the Lower Kelani River Basin, indicating higher pollutant levels in different seasons. Industrial effluents (LV-2 and LV-4) and domestic and municipal sewage (LV-3 and LV-5) exhibit greater seasonal fluctuations. The results showed that the proposed LV approach has the potential to assist authorities in addressing water pollution amidst the complexity of multiple water quality parameters.

Dynamic patterns and potential drivers of river water quality in a coastal city: Insights from a machine-learning-based framework and water management

River water quality continues to deteriorate under the coupled effects of climate change and human activities. Machine learning (ML) is a promising approach for analyzing water quality. Nevertheless, the spatiotemporal dynamics of river water quality and their potential mechanisms in changing environments remain incomprehensively understood through available ML-based researches. Here, we developed a ML-based framework integrating a self-organizing map (SOM) model with a random forest (RF) model. This framework was applied to simultaneously investigate the spatiotemporal patterns and potential drivers of river permanganate (CODMn), ammonia nitrogen (NH3-N), and total phosphorus (TP) dynamics across 34 sites from 2010 to 2020 in a coastal city threatened by deteriorating water environment in southeastern China. The sites were divided into two clusters in the spatial context with different water quality conditions. The year of 2015 for NH3-N and 2018 for CODMn and TP were identified as the key turning points of water quality variations. Features including sewage discharge, population dynamics, percentage of cultivated land, and fertilizer application contributed greatly to water quality deterioration. The increase in forest vegetation reflected by percentage of forest and leaf area index may improve water quality. The ML-based modeling framework demonstrated a promising way to address the spatiotemporal dynamics of river water quality, and provided insights for water management in a coastal city with intensifying human-nature interactions.

Deep self-organizing map neural networks improve the segmentation for inadequate plantar pressure imaging data set

ABSTRACT This study introduces a deep self-organizing map neural network based on level-set (LS-SOM) for the customization of a shoe-last defined from plantar pressure imaging data. To alleviate the over-segmentation problem of images, which refers to segmenting images into more subcomponents, a domain-based segmentation model of plantar pressure images was constructed. The domain growth algorithm was subsequently modified by optimizing its parameters. A SOM with 10, 15, 20, and 30 hidden layers was compared and validated according to domain growth characteristics by using merging and splitting algorithms. Furthermore, we incorporated a level set segmentation method into the plantar pressure image algorithm to enhance its efficiency. Compared to the literature, this proposed method has significantly improved pixel accuracy, average cross-combination ratio, frequency-weighted cross-combination ratio, and boundary F1 index comparison. Using the proposed methods, shoe lasts can be designed optimally, and wearing comfort is enhanced, particularly for people with high blood pressure.

Relationship between Tibetan Plateau Surface Heat Fluxes and Daily Heavy Precipitation in the Middle and Lower Yangtze River Basins (1980–2022)

Variable heat fluxes over the Tibetan Plateau (TP) interact thermally with the atmosphere, affecting weather in surrounding areas, particularly in the Middle and Lower Yangtze River (MLYR). However, the circulation patterns and time-lag effects between TP heat fluxes and MLYR precipitation remain unclear. This study identified 577 large-scale daily heavy precipitation events (LSDHPEs) in the MLYR from 1980 to 2022. We analyzed the weather causation and spatiotemporal correlations between the TP surface heat fluxes and MLYR LSDHPEs using self-organizing map clustering, singular value decomposition, and harmonic analysis of time series. The results found two dominant synoptic patterns of LSDHPEs at 500 hPa: one, driven by anticyclonic and cyclonic circulations coinciding with shifts in the West Pacific subtropical high and South Asian high, increased from 2000 to 2022; the other, influenced by MLYR cyclonic circulation, showed a significant decrease. For the first time, we revealed lagged effects of the latent heat anomalies (with a lag time of 1–10 d and 130–200 d) and sensible heat anomalies (with a lag time of 2–4 months) over the TP during LSDHPEs in the MLYR. The results may enhance our understanding of TP heat flux anomalies as precursor signals for early warning of heavy rainfall and flooding in the MLYR.

Effects of meteorology on bike-sharing: Cases of 13 cities using non-linear analyses

Bike-sharing system (BSS) provides bicycle rental services for short-term use. The association of BSS with meteorological factors has not been studied sufficiently using nonlinear analysis. To bridge these gaps, this study explored the impact of meteorological conditions on bike-sharing system (BSS) usage in 13 cities in Europe and North America, using a combination of nonlinear analyses to avoid the limitations of linear analyses used traditionally. Specifically, self-organizing map (SOM) and decision tree analyses were used. The SOM results revealed six meteorological profiles (clusters). Kruskal–Wallis test was applied to determine the main effect of the cluster on the input variables. The decision tree indicated temperature (34.4 %), followed by clusters (23.3 %), and cities (17.5 %) as the most influential factors on BSS usage. These findings demonstrated the need to generate nonlinear analyses to understand the dynamic interaction of meteorological variables and BSS usage, providing insights for developing sustainable urban transportation policies.

Vgasom: community detection based on self-organizing map clustering of graph’s embeddings

Vgasom: community detection based on self-organizing map clustering of graph’s embeddings

Self-organizing maps of unbiased ligand-target binding pathways and kinetics.

The interpretation of ligand-target interactions at atomistic resolution is central to most efforts in computational drug discovery and optimization. However, the highly dynamic nature of protein targets, as well as possible induced fit effects, makes difficult to sample many interactions effectively with docking studies or even with large-scale molecular dynamics (MD) simulations. We propose a novel application of Self-Organizing Maps (SOMs) to address the sampling and dynamic mapping tasks, particularly in cases involving ligand flexibility and induced fit. The SOM approach offers a data-driven strategy to create a map of the interaction process and pathways based on unbiased MD. Furthermore, we show how the preliminary SOM mapping is complementary to kinetic analysis, with the employment of both network-based approaches and Markov state models. We demonstrate the method by comprehensively mapping a large dataset of 640 μs of unbiased trajectories sampling the recognition process between the phosphorylated YEEI peptide and its high-specificity target lck-SH2. The integration of SOM into unbiased simulation protocols significantly advances our understanding of the ligand binding mechanism. This approach serves as a potent tool for mapping intricate ligand-target interactions with unprecedented detail, thereby enhancing the characterization of kinetic properties crucial to drug design.

The influence of specific weather types on stroke occurrence: an analysis of 23,000 patients from Augsburg, Germany

ABSTRACT For the first time, the relationships between large-scale weather types and local stroke events in the urban area of Augsburg, Germany are analyzed. Over 23,000 stroke cases (2006 – 2020) were standardized to account for long-term trends and seasonality. Using ERA5 reanalysis data, a composite analysis identified stroke-related atmospheric variables, while seasonal weather types were classified via the neural network algorithm of self-organizing maps. Cyclonic westerlies during the cold season, which transport warm air masses from the Atlantic Ocean to Germany, were a major risk factor for ischemic stroke, while colder easterly conditions reduced stroke incidence. In the warm season, both anticyclonic conditions and westerly/northerly air advection, leading to slightly warmer or distinctly colder temperatures, were linked to increased ischemic stroke risk. Additionally, hemorrhagic strokes in the cold season were triggered by weather conditions contrary to those associated with ischemic strokes and transitory ischemic attacks.