Self-organizing Map Technique Research Articles

Synoptic-scale Meteorological Patterns Associated with Heavy Rainfall in the Minnesota Region

Abstract Situated in the Upper Midwest, Minnesota’s mid-continental location places it in a climate transition zone between eastern U.S. humid conditions and western semi-arid conditions as well as between warm, moist air from the Gulf of Mexico to the south and drier, polar air to the north. Potential adverse impacts on ecosystems due to changing climate and precipitation patterns, together with ongoing flash flooding risks, indicate that heavy rainfall occurrence and distribution are important considerations for Minnesota. This research used ERA5 reanalysis data with 0.25° grid spacing during May-September 1959-2021 to investigate the synoptic-scale drivers of Minnesota heavy rainfall. The study utilized a neural-network, self-organizing map (SOM) technique to identify sea-level pressure patterns and precipitation patterns associated with heavy rainfall and used composite analysis to explore the relationships between synoptic-scale conditions and environmental parameters during heavy rain hours. Six sea level pressure patterns were identified, three of which represented advancing surface cyclones and accounted for >70% of the heavy rain hours. The spatial distribution of heavy rainfall was represented by six precipitation patterns. The greatest frequency of heavy rain hours was associated with the northwest precipitation pattern, followed by the southwest and southeast patterns. Analysis of the frequency of pressure and heavy rain precipitation pattern pairs revealed that the top five most frequent pairs were associated with advancing surface cyclones and >26% of the total heavy rain hours. Composite analysis of environmental parameters showed favorable conditions related to moisture and lift were associated with heavy rainfall.

Characterization of Relativistic Electron Precipitation Events Observed by the CALET Experiment Using Self‐Organizing‐Maps

AbstractRelativistic electron precipitation (REP) is a relatively high‐latitude phenomenon where high‐energy electrons trapped in the outer radiation belt are lost into the Earth’s atmosphere. REP events observed at low Earth orbit show varying temporal profiles and global distributions. While the precipitation origin has been attributed to specific wave modes or scattering sources, the sorting of REP events by type or driver remains an unsolved challenge. In this study, we analyze the temporal profile of relativistic electron precipitation events observed by the CALorimetric Electron Telescope (CALET) experiment on board the International Space Station. We use an unsupervised machine learning technique called Self‐Organizing‐Maps (SOM) to automatically detect and then classify relativistic electron events observed by the two scintillator layers at the top of the apparatus, sensitive to electrons with energies >1.5 MeV and >3.4 MeV, respectively. We calculate the power spectral density (PSD) of the count rates observed by both sensors and use them as an input for the SOM. The SOM technique groups the PSDs by their similarity, resulting in a classification of relativistic electron events by the periodicity of the observed precipitation. We investigate the L‐shell and magnetic local time distribution of the resulting classification, and energy spectral index associated with the observations. Clear precipitation patterns are observed and compared to past precipitation categorization attempts as well as known distributions of various scattering mechanisms. The classification reveals features through the sorting of the variability of the rapid precipitation, allowing the identification of different precipitation populations with varying properties.

Predictive modeling of garlic quality in hybrid infrared-convective drying using artificial neural networks

Artificial Neural Networks (ANN) application for enhancing food drying processes has been gaining traction within the food industry, particularly because of its potential to optimize conditions while preserving quality. This study delves into the effects of varying convective temperatures (40, 50, 60 °C), air velocities (0.7, 1.0, and 1.5 m/s), and infrared radiation intensities (1500, 2000, 3000 W/m²) on the drying efficiency and quality of garlic slices. Additionally, it explores the capability of ANN to predict optimal drying conditions to balance time efficiency and quality retention. Experimental observations revealed that a combination of a 60°C air temperature, 1.0 m/s air velocity, and 3000 W/m² infrared radiation minimized the drying time to 4.5 h. However, this setting also resulted in a 13.4 % reduction in Allicin content and a decrease in flavor intensity to 4.09 mg/g, underscoring the complexity of optimizing drying conditions without compromising key quality attributes. The study highlights the intricate relationships between drying parameters and garlic quality through precise ANN modeling, which achieved an exceptional fit. Principal Component Analysis (PCA) further elucidated the inverse correlation between drying time and critical quality factors of color, Allicin content, and flavor. Utilizing the Self-Organizing Map (SOM) technique, the study identified five distinct optimization zones, suggesting that lower temperatures, intermediate infrared levels, and higher air velocities present an optimal balance for enhancing garlic slice quality while reducing drying time. This research underscores the potential of advanced computational tools in refining food drying processes, offering valuable insights for the food industry in its quest to improve efficiency without sacrificing product quality.

Organizational changes and research performance: A multidimensional assessment

Abstract This paper analyzes the research performance evolution of a scientific institute, from its genesis through various stages of development. The main aim is to obtain, and visually represent, bibliometric evidence of the correlation of organizational changes on the development of its scientific performance; particularly, structural and leadership changes. The study involves six bibliometric indicators to multidimensionally assess the evolution of the institution’s performance profile. For a case study, we selected the Renewable Energy Institute at the National Autonomous University of Mexico, created 35 years ago as a small laboratory, then it evolved to a research center and finally to a formal institute, which over the last 8 years changed from the traditional departmental structure to a network-based structure. The evolution of the multidimensional performance profiles is analyzed, and graphically represented, using a novel artificial intelligence-based approach. We analyzed the performance profiles evolution yearly, using Principal Components Analysis, and a self-organizing neural network mapping technique. This approach, combining bibliometric and machine learning techniques, proved to be effective for the assessment of the institution’s evolution process. The results were represented with a series of graphs and maps that clearly reveal the magnitude and nature of the performance profile evolution, as well as its correlation with each of the structural and leadership transitions. These exploratory results have provided us data and insights into the probable effects of these transitions on academic performance, that have been useful to create a dynamical model.

Analyzing Wintertime Extreme Winds over Türkiye and Their Relationships with Synoptic Patterns Using Cluster Analysis

This study investigates the patterns of extreme winds and the correlation between synoptic patterns in Türkiye throughout the winter season, using the cluster analysis technique. We utilized the k-means algorithm to detect the surface patterns of extreme winds. Additionally, we deployed the Self-Organizing Map (SOM) technique to identify clusters of geopotential height at the 500 hPa level, average temperature at the 850 hPa level, and mean sea level pressure. We adopted the dataset from the New European Wind Atlas (NEWA) project for analyzing surface-level weather conditions and the ERA5 datasets for studying upper-level weather conditions. The k-means algorithm identifies six distinct clusters when applied to the ground-level data in Türkiye. These clusters are predominantly located around the Taurus Mountain ranges, which stretch in an east-west and northeastern direction along the Black Sea coast. The formation of these clusters is controlled by the characteristics of the land and its physical features. The higher-level clusters, consisting of nine SOM nodes, are unaffected by terrain and weather systems, which are characteristic of the macro-Mediterranean climate. These clusters are detected in the Eastern Mediterranean, Black Sea, and inner Aegean areas, emphasizing the impact of topography on surface patterns.

Future electricity production at Mutriku Wave Energy Plant estimated from CMIP6 wave climate projections (2015–2100)

Renewable marine energy sources are rapidly developing worldwide. With numerous operational marine power plants in existence, it is becoming increasingly important to explore their potential. Hence, this study aims to examine the impact of climate change on the future potential of wave energy. The case study was centred on the Mutriku Wave Energy Plant, situated in the Bay of Biscay in the northern region of the Iberian Peninsula.To accomplish this, this study investigated changes in wave energy from 2015 to 2100 by employing ERA5 data and an ensemble of CSIRO wave projections driven by six distinct models derived from CMIP6 model runs. Two were associated with the SSP1-2.6 pathway while the other four corresponded to the SSP5-8.5 pathway. The unidimensional wave variables were bias-corrected using the Quantile Matching (QM) technique, whereas the bidimensional variables were corrected using the Multivariate Bias Correction N-pdf (MBC N-pdf) technique. Subsequently, a self-organising map (SOM) technique was employed to classify daily sea type frequencies and power. Additionally, the Smirnov test was employed to determine whether the probability density functions derived from different datasets exhibited significant differences at a significance level of 0.05.The conclusions obtained indicate that energy production in the Bay of Biscay will remain stable in the late 21st Century. The daily frequencies of the sea type and power did not change significantly. This stability ensures consistent power generation, enabling the location to provide a reliable and consistent source of energy both currently and in the future.

Catch assemblages in the small-scale trap fishery with relation to hydrographic features of a tropical bay in the Gulf of Thailand.

Catches from the small-scale trap fishery in Bandon Bay, Suratthani, Thailand, were monitored from 14 sites around the Bay, then disturbance to aquatic communities and catch assemblage were examined. At the same time, the hydrographical features of the bay were surveyed. The study was conducted throughout 2019 except in December, when a tropical cyclone made sampling impossible. In total, 17,373 animals from 118 species or species groups of aquatic animals were collected. The main target of the fishery, blue swimming crab Portunus pelagicus, contributed about 10% of the total catch in terms of number; meanwhile, another crab, Charybdis affinis, was the most dominant species (41% of total). W-statistics of Abundance-Biomass Comparison curves ranged between -0.025 and 0.031, indicating light disturbance to the communities in this fishing ground. The catch assemblage, based on number in catch composition, were divided into three main clusters and six sub-clusters by using the self-organizing map (SOM) technique. The SOM results showed that the catch assemblages differed based largely on temporal variation. The hydrographic features of Bandon Bay at times exhibited a layered structure and had strong spatial variation. The bay's current system was governed by motion of tidal currents; meanwhile, the circulation was governed by monsoonal wind and freshwater discharges. Tidal current was strong and ranged between approximately 0.6 m to 2.2 m. Water within the bay was always warmer than the outer sea. High water temperature was observed two times during the year: during monsoon transition 1 (April to May) and transition 2 (October). Salinity showed great spatial and temporal variation, differing by more than 5-10 ppt horizontally. It was possible to use these dynamic hydrological features of Bandon Bay to explain assemblage patterns of the trap-net catches.

Extreme waves in the Caribbean Sea: spatial regionalization and long-term analysis

The extreme wave height distribution in the Caribbean Sea is studied using a new method based on the maximum basin-wide aggregate of significant wave height, Hs, values per month. Besides, by means of the Self-Organizing Maps (SOM) technique, we identify coherent geographical regions with similar extreme wave height variability in the Caribbean Sea. Our findings revealed three primary regions: the eastern side with comparatively lower values, the central region with intermediate values, and the western side with the highest extreme wave heights. The study also examines the wind forcing conditions driving the spatial and temporal variability of the extreme waves, highlighting the influence of the low-pressure belt dynamics as well as the role played by the Caribbean Low-Level Jet (CLLJ) index, and the impact of cold fronts and hurricanes on extreme wave heights. Additionally, we explore the relationship between the extreme wave height distribution and climatic indices, such as the Atlantic Multidecadal Oscillation (AMO), the Atlantic Meridional Mode (AMM), the North Atlantic Oscillation (NAO) and the Oceanic Niño (ONI). The results reveal that the spatial distribution of extreme wave heights in the Caribbean Sea is mostly ruled by the influence of the CLLJ, with correlations close to 80%. In addition, significant correlations were observed between the extreme wave heights and the ENSO in the central Caribbean, as well as positive correlations between the extreme wave heights and NAO in the eastern part of the basin, and significant values of correlation with the negative phases of AMO and AMM in the whole basin. We show that, unlike conventional (or broadly used) methods deployed to identify extreme wave height, such as percentile 99th, Hs99, our methodology allows a further assessment of the wind and climate forcing conditions associated with the extreme wave events. Although, we acknowledge that the method here presented has limitations to capture extreme wave height outliers, it has the advantage of being used concomitant with the wind forcing to develop multivariate wave climate analysis at basin scale, and could be extended to a more local scale when studying coastal processes.

Analyzing Sentiment with Self-Organizing Map and Long Short-Term Memory Algorithms

This research delves into the impact of Chat Generative Pre-trained Transformer, one of Open Artificial Intelligence Generative Pretrained Transformer models. This model underwent extensive training on a vast corpus of internet text to gain insights into the mechanics of human language and its role in forming phrases, sentences, and paragraphs. The urgency of this inquiry arises from Chat Generative Pre-trained Transformer emergence, which has stirred significant debate and captured widespread attention in both research and educational circles. Since its debut in November 2022, Chat Generative Pre-trained Transformer has demonstrated substantial potential across numerous domains. However, concerns voiced on Twitter have centered on potential negative consequences, such as increasedforgery and misinformation. Consequently, understanding public sentiment toward Chat Generative Pre-trained Transformer technology through sentiment analysis has become crucial. The research’s primary objective is to conduct Sentiment Analysis Classification of Chat Generative Pre-trained Transformer regarding public opinions on Twitter in Indonesia. This goal involves quantifying and categorizing public sentiment from Twitter’s vast data pool into three clusters: positive, negative, or neutral. In the data clustering stage, the Self-Organizing Map technique is used. After the text data has been weighted and clustered, the next step involves using the classification technique with LongShort-Term Memory to determine the public sentiment outcomes resulting from the presence of Chat Generative Pre-trained Transformer technology. Rigorous testing has demonstrated the robust performance of the model, with optimal parameters: relu activation function, som size of 5, num epoch som and num epoch lstm both at 128, yielding an impressive 95.07% accuracy rate.

Observations of the Chromospheric Evershed Flow of Sunspot Penumbra with the Application of the Self-organizing Map Technique

The sunspot penumbra is usually observed in the photosphere and it is of particular interest for its magnetoconvection, which seems to transport the heat from the top of the convection zone into the solar atmosphere. It is well known that the penumbra magnetic field extends into the upper layers of the solar atmosphere forming the so-called superpenumbra. Thanks to the application of the Self-organizing Map technique to a spectral data set containing monochromatic images acquired along the Ca ii 854.2 nm and Hα 656.28 nm lines, we were able to segment the penumbra and to measure the plasma velocity along the chromospheric portions of penumbral filaments. We found that the head, body, and tail of penumbral filaments show vertical flows compatible with the persistence of the Evershed flow. Instead, the inverse Evershed flow has been observed only in the outer portion of the superpenumbra. We found that two opposite Evershed regimes work next to each other, without overlapping, and both contribute to the downflow around sunspots. These results confirm the uncombed model of the sunspot penumbra and provide some hints that the downflow around sunspots may be ascribed to the magnetic field dragging the plasma down.

Identifying fisheries operations in tropical multispecies fisheries: A comparative analysis of multivariate approaches and neural networks

Efforts to assess and manage mixed fisheries started a shift from monospecific to multispecies approaches in European countries; this transition, however, is still far from being applied in other regions. Given the operational heterogeneity and diversity of species targeted, disentangling the complexity of those fisheries' complexities is the first step to understanding, monitoring, and managing them. Multivariate analytical tools supported by the métiers approach offer alternatives to untangle the fishing operations and identify management units. Among the analytical techniques used for this purpose, self-organizing maps (SOM) and different multivariate methods have been reported. The usage of the former has been less common, and there is limited information regarding its performance compared with the latter. In this study, we aimed to evaluate the performance of the SOM and multivariate techniques to identify the operational units of a mixed fishery from the southeast coast of Mexico. Five métiers or management units were identified using both analytical tools matching the groups; however, some differences were observed. We discuss the strengths and caveats of those techniques and examine the management implications of the findings in the context of the analyzed fishery.

Classification of reservoir quality using unsupervised machine learning and cluster analysis: Example from Kadanwari gas field, SE Pakistan

• Applying SOM approach to interpret electrical well logging data from KGF. • Distinguishing different types of facies using SOM approach. • Deriving the lithological cross section of the interpreted well. • Employing cluster analysis approach for reservoir rock typing. Understanding geological variance in a proved reservoir requires accurate as well as exact characterization of lithological facies. In the Kadanwari gas field, machine learning (ML) classification algorithms have been used to forecast facies on such an accessible dataset. The goal is to increase the reliability of facies categorization using a rigorous application of machine learning. In the current study to identify lithofacies, we have used the self-organizing map (SOM) and crossplot techniques. In the classification of the reservoir, recognition of lithofacies is the main piece of work. It is expensive to identify lithofacies with conventional methods from core data, and it is challenging to extend this application to non-cored wells. This research provides a less expensive method for the systematic and objective recognition of lithofacies through well-log data by Kohonen SOM. The SOMs are human-made neural networks that do not need surveillance and map the input space into groups in the structure as topology is arranged according to the input data changes. The results of SOM and crossplot indicates that the zone of interest is mainly composed of sandstone, shaly sandstone, shale with diminutive amount of carbonates. The cluster analysis approach has been utilized to categorize the reservoir rock groups in the Cretaceous reservoir for the Kadanwari gas field by analyzing the variance of reservoir properties data that are forecast by examining well log dimensions. Four groups of reservoirs were concluded, each of which was internally identical in petrophysical properties but distinct from the others. The reservoir mainly composed of sandstone is graded as excellent reservoir, while shale is graded as poor reservoir.

An artificial intelligence approach for identifying efficient urban forest indicators on ecosystem service assessment

Urban trees provide multiple ecosystem services (ES) to city residents and are used as environmentally friendly solutions to ameliorate problems in cities worldwide. Effective urban forestry management is essential for enhancing ES, but challenging to develop in densely populated cities where tradeoffs between high ES provision and issues of periodic disaster-caused risks or maintenance costs must be balanced. With the aim of providing practical guidelines to promote green cities, this study developed an AI-based analytical approach to systematically evaluate tree conditions and detect management problems. By using a self-organizing map technique with a big dataset of Taipei street trees, we integrated the ES values estimated by i-Tree Eco to tree attributes of DBH, height, leaf area, and leaf area index (LAI) to comprehensively assess their complex relationship and interlinkage. We found that DBH and leaf area are good indicators for the provision of ES, allowing us to quantify the potential loss and tradeoffs by cross-checking with tree height and the correspondent ES values. In contrast, LAI is less effective in estimating ES than DBH and leaf area, but is useful as a supplementary one. We developed a detailed lookup table by compiling the tree datasets to assist the practitioners with a rapid assessment of tree conditions and associated loss of ES values. This analytical approach provides accessible, science-based information to appraise the right species, criteria, and place for landscape design. It gives explicit references and guidelines to help detect problems and guide directions for improving the ES and the sustainability of urban forests.

Variations of Summer Extreme and Total Precipitation over Southeast Asia and Associated Atmospheric and Oceanic Features

Abstract Southeast Asia lies at the heart of heavy precipitation on Earth, and a large amount of latent heat released here provides substantial energy for the global atmospheric circulation. Utilizing gauge-based daily precipitation and the self-organizing map technique, the summertime extreme and total precipitation over Southeast Asia during 1979–2019 are classified into three and five distinct patterns, respectively. The three extreme precipitation clusters are characterized by southern dry and northern wet (C1_extreme), overall wet (C2_extreme), and northern dry and southern wet (C3_extreme) structures. The frequencies of these patterns exhibit increasing trends during the analysis, although they are not statistically significant for C1_extreme. The C1_extreme pattern is accompanied by an anomalous cyclone over the South China Sea in response to negative Indian Ocean sea surface temperature anomalies (SSTAs). The C2_extreme and C3_extreme clusters are characterized by a westward extension of the western Pacific subtropical high, regulated by cool SSTAs over the tropical central-eastern Pacific that are induced by the tropical North Atlantic warming and the tropical Pacific and Atlantic SSTAs, respectively. For total precipitation, the first and second clusters show overall dry distributions, which are mainly composed of nonextreme precipitation. The spatial patterns and atmospheric and oceanic features associated with the other three clusters of total precipitation bear large resemblances to those of C1_extreme, C2_extreme, and C3_extreme, respectively, but their trends exhibit smaller similarities. Comparing the differences between extreme and total precipitation over Southeast Asia could improve our understanding of their regional variabilities and relationships, and potentially their global impacts. Significance Statement We explore the atmospheric and oceanic processes associated with extreme precipitation, and compare them with those for total precipitation over Southeast Asia. The three key modes of summertime extreme precipitation over Southeast Asia are characterized by southern drought and northern flood, overall flood, and northern drought and southern flood structures. Each pattern is closely linked to tropical sea surface temperature anomalies, but in different regions. Total precipitation can be classified into five distinct patterns. The first two modes are largely determined by nonextreme precipitation, while the other three bear large resemblances to the three extreme precipitation modes. These findings provide guidance on what is the key factor in driving each extreme precipitation mode over Southeast Asia, allowing better prediction.

Optimization method for hierarchical space reduction method and its application in hull form optimization

Hull form optimization can be considered a typical “black-box” problem owing to the large number of design variables controlling the hull form, the time required to evaluate the hull form performance, and the unknown hull form performance space structure. Therefore, problems such as low optimization efficiency and difficulty in obtaining the optimal solution persist. Therefore, in this study, a novel optimization method that uses SOM (Self-Organizing Maps) and MARS (Model-based Annealing Random Search) to stratify the design space is proposed. In the proposed method, the design space is divided into an initial global space, a potential subspace, and a significant subspace during the optimization process. The SOM and MARS techniques are used for data mining to reduce the search domain of the subspaces and determine the global optimal solution. The proposed hierarchical space reduction method (HSRM) was validated using multiple functions as examples and one hull form optimization design problem. The proposed method could improve the optimization efficiency and accuracy of the solution.

A faster dynamic convergency approach for self-organizing maps

This paper proposes a novel variable learning rate to address two main challenges of the conventional Self-Organizing Maps (SOM) termed VLRSOM: high accuracy with fast convergence and low topological error. We empirically showed that the proposed method exhibits faster convergence behavior. It is also more robust in topology preservation as it maintains an optimal topology until the end of the maximum iterations. Since the learning rate adaption and the misadjustment parameter depends on the calculated error, the VLRSOM will avoid the undesired results by exploiting the error response during the weight updation. Then the learning rate is updated adaptively after the random initialization at the beginning of the training process. Experimental results show that it eliminates the tradeoff between the rate of convergence and accuracy and maintains the data's topological relationship. Extensive experiments were conducted on different types of datasets to evaluate the performance of the proposed method. First, we experimented with synthetic data and handwritten digits. For each data set, two experiments with a different number of iterations (200 and 500) were performed to test the stability of the network. The proposed method was further evaluated using four benchmark data sets. These datasets include Balance, Wisconsin Breast, Dermatology, and Ionosphere. In addition, a comprehensive comparative analysis was performed between the proposed method and three other SOM techniques: conventional SOM, parameter-less self-organizing map (PLSOM2), and RA-SOM in terms of accuracy, quantization error (QE), and topology error (TE). The results indicated the proposed approach produced superior results to the other three methods.

Mechanisms and influencing factors of yttrium sorption on paddy soil: Experiments and modeling

High-technology rare earth elements (REEs) as emerging contaminants have potentially hazardous risks for human health and the environment. Investigating the sorption of REEs on soils is crucial for understanding their migration and transformation. This study evaluated the sorption mechanisms and influencing factors of the rare earth element yttrium (Y) on paddy soil via integrated batch sorption experiments and theoretical modeling analysis. Site energy distribution theory (SEDT) combined with kinetics, thermodynamics, and isotherm sorption models were applied to illustrate the sorption mechanism. In addition, the effects of phosphorus (P), solution pH, particle size of soil microaggregates, and initial Y content on the sorption processes were evaluated by self-organizing map (SOM) and Boruta algorithm. The sorption kinetic behavior of Y on paddy soil was more consistent with the pseudo-second-order model. Thermodynamic results showed that the Y sorption was a spontaneous endothermic reaction. The generalized Langmuir model well described the isotherm data of Y sorption on heterogeneous paddy soil and soil microaggregates surface. The maximum sorption capacity of Y decreased with increasing soil particle size, which may be related to the number of sorption sites for Y on paddy soil and soil microaggregates, as confirmed by SEDT. The heterogeneity of sorption site energy for Y was the highest in the original paddy soil compared with the separated soil microaggregates. The SOM technique and Boruta algorithm highlighted that the initial concentration of Y and coexisting phosphorus played essential roles in the sorption process of Y, indicating that the addition of phosphate fertilizer may be an effective way to reduce the Y bioavailability in paddy soil in practice. These results can provide a scientific basis for the sustainable management of soil REEs and a theoretical foundation for the remediation of REEs-contaminated soils.

Predicting Rare Earth Element Potential in Produced and Geothermal Waters of the United States via Emergent Self-Organizing Maps

This work applies emergent self-organizing map (ESOM) techniques, a form of machine learning, in the multidimensional interpretation and prediction of rare earth element (REE) abundance in produced and geothermal waters in the United States. Visualization of the variables in the ESOM trained using the input data shows that each REE, with the exception of Eu, follows the same distribution patterns and that no single parameter appears to control their distribution. Cross-validation, using a random subsample of the starting data and only using major ions, shows that predictions are generally accurate to within an order of magnitude. Using the same approach, an abridged version of the U.S. Geological Survey Produced Waters Database, Version 2.3 (which includes both data from produced and geothermal waters) was mapped to the ESOM and predicted values were generated for samples that contained enough variables to be effectively mapped. Results show that in general, produced and geothermal waters are predicted to be enriched in REEs by an order of magnitude or more relative to seawater, with maximum predicted enrichments in excess of 1000-fold. Cartographic mapping of the resulting predictions indicates that maximum REE concentrations exceed values in seawater across the majority of geologic basins investigated and that REEs are typically spatially co-associated. The factors causing this co-association were not determined from ESOM analysis, but based on the information currently available, REE content in produced and geothermal waters is not directly controlled by lithology, reservoir temperature, or salinity.

Application of Machine Learning for Lithofacies Prediction and Cluster Analysis Approach to Identify Rock Type

Nowadays, there are significant issues in the classification of lithofacies and the identification of rock types in particular. Zamzama gas field demonstrates the complex nature of lithofacies due to the heterogeneous nature of the reservoir formation, while it is quite challenging to identify the lithofacies. Using our machine learning approach and cluster analysis, we can not only resolve these difficulties, but also minimize their time-consuming aspects and provide an accurate result even when the user is inexperienced. To constrain accurate reservoir models, rock type identification is a critical step in reservoir characterization. Many empirical and statistical methodologies have been established based on the effect of rock type on reservoir performance. Only well-logged data are provided, and no cores are sampled. Given these circumstances, and the fact that traditional methods such as regression are intractable, we have chosen to apply three strategies: (1) using a self-organizing map (SOM) to arrange depth intervals with similar facies into clusters; (2) clustering to split various facies into specific zones; and (3) the cluster analysis technique is used to identify rock type. In the Zamzama gas field, SOM and cluster analysis techniques discovered four group of facies, each of which was internally comparable in petrophysical properties but distinct from the others. Gamma Ray (GR), Effective Porosity(eff), Permeability (Perm) and Water Saturation (Sw) are used to generate these results. The findings and behavior of four facies shows that facies-01 and facies-02 have good characteristics for acting as gas-bearing sediments, whereas facies-03 and facies-04 are non-reservoir sediments. The outcomes of this study stated that facies-01 is an excellent rock-type zone in the reservoir of the Zamzama gas field.

Designing an Energy Efficient Network Using Integration of KSOM, ANN and Data Fusion Techniques

Energy in a wireless sensor network (WSN) is rendered as the major constraint that affects the overall feasibility and performance of a network. With the dynamic and demanding requirements of diverse applications, the need for an energy efficient network persists. Therefore, this paper proposes a mechanism for optimizing the energy consumption in WSN through the integration of artificial neural networks (ANN) and Kohonen self-organizing map (KSOM) techniques. The clusters are formed and re-located after iteration for effective distribution of energy and reduction of energy depletion at individual nodes. Furthermore, back propagation algorithm is used as a supervised learning method for optimizing the approach and reducing the loss function. The simulation results show the effectiveness of the proposed energy efficient network.