Combination Of Principal Component Analysis Research Articles

A grey target performance evaluation model for aeroengine pressure test bench

PurposeThis paper aims to optimize the air pressure regulation scheme of the aeroengine pressure test bench.Design/methodology/approachBased on the requirements of pressure regulation process and the operating mechanism of aeroengine pressure test bench, a grey performance evaluation index system is constructed. The combination of principal component analysis and grey theory is employed to assign weights to grey indexes. The grey target evaluation model is introduced to evaluate the performance of historical regulation processes, and the evaluation results are analyzed to derive optimization mechanism for pressure regulating schemes.FindingsA case study based on monitoring data from nearly 300 regulation processes verifies the feasibility of the proposed method. On the one hand, the improved principal component analysis method can achieve rational weighting for grey indexes. On the other hand, the method comparison intuitively shows that the proposed method performs better.Originality/valueThe pressure test bench is a fundamental technical equipment in the aviation industry, serving the development and testing of aircraft engines. Due to the complex system composition, the pressure and flow adjustment of the test bench heavily rely on manual experience, leading to issues such as slow adjustment speed and insufficient accuracy. This paper proposes a performance evaluation method for the regulation process of pressure test bench, which can draw knowledge from historical regulation processes, provide guidance for the pressure regulation of test benches, and ultimately achieve the goal of reducing equipment operating costs.

Peridynamics-fueled convolutional neural network for predicting mechanical constitutive behaviors of fiber reinforced composites

Despite advancements in predicting the constitutive relationships of composite materials, characterizing the effects of microstructural randomness on their mechanical behaviors remains challenging. In this study, we propose a data-driven convolutional neural network (CNN) to efficiently predict the stress-strain curves containing three key material features (Tensile strength, modulus, and toughness) of fiber reinforced composites. Firstly, stress-strain curves for composites with arbitrary fiber distributions were generated using experimentally validated peridynamics (PD) model. Principal component analysis (PCA) was then employed to learn these curves in a lower-dimensional space, reducing computational costs. Subsequently, these reduced data, along with randomly distributed microstructural features, were used to train, validate, and evaluate the CNN models. The combined CNN and PCA model accurately predicted stress-strain curves with maximum errors of 2.5 % for tensile strength, 10% for modulus, and 20 % for toughness. Furthermore, data augmentation and Mean Squared Error (MSE) as a loss function significantly enhanced the model's prediction accuracy. Our findings indicated that DenseNet121 outperformed other CNN models in predicting the properties of fiber-reinforced materials, further demonstrating the effectiveness of the proposed model. This work successfully demonstrates the applicability of a data-driven CNN approach to predict stress-strain relations for engineering materials with intricate heterogeneous microstructures, paving the way for data-driven computational mechanics applied in composites.

Electrochemical Quantification of Enkephalin Peptides Using Fast-Scan Cyclic Voltammetry.

Endogenous opioid neuropeptides serve as important chemical signaling molecules in both the central and peripheral nervous systems, but there are few analytical tools for directly monitoring these molecules in situ. The opioid peptides share the amino acid motif, Tyr-Gly-Gly-Phe-, at the N-terminus. Met-enkephalin is a small opioid peptide comprised of only five amino acids with methionine (Met) incorporated at the C-terminus. Tyrosine (Tyr) and Met are electroactive, and their distinct electrochemical signatures can be utilized for quantitative molecular monitoring. This work encompasses a thorough voltammetric characterization of Tyr and Met redox chemistry as individual amino acids and when incorporated into small peptide fragments containing the shared Tyr-Gly-Gly-Phe- motif. NMR spectroscopy was used to determine the structure and conformation at near-physiological conditions. Voltammetric data demonstrate how the peak oxidation potential and the rate of electron transfer are dependent on the local chemical environment. Both the proximity of the electroactive residue to the C- or N-terminus and the hydrophobicity of the additional nonelectroactive amino acids profoundly affect sensitivity. Finally, the work uses the electrochemical signal for individual amino acids in a "training set", with a combination of principal component analysis and least-squares regression to accurately predict the voltammetric signal for short peptides comprising different combinations of those amino acids. Overall, this study demonstrates how fast-scan cyclic voltammetry can be utilized to discriminate between peptides with small differences in the chemical structure, thus establishing a framework for reliable quantification of small peptides in a complex signal, broadly speaking.

Estimation of Regional Background Ozone in Henan Province from 2019 to 2021

Clarifying the regional transmission and local generation contributions of ozone （O3） is important for controlling O3 pollution. To quantify the regional background and spatial-temporal variations of O3, a comprehensive study was conducted using multiple methods including principal component analysis （PCA） and TCEQ, with Henan Province as a case study. Based on monitoring data from 59 national sites in Henan Province during 2019-2021, four methods were employed to estimate the regional background of O3. Method 1 was the traditional method, performing O3 univariate-multisite PCA analysis. Method 2 was a multivariate-single-site PCA analysis considering nitrogen dioxide and meteorological conditions as constraints. Method 3 combined PCA and multiple linear regression （MLR） to determine regional background contributions, drawing on the idea of source apportionment. Method 4 was the TCEQ method that used the lowest measured O3-8h concentration as the regional background. The estimation results showed that Methods 1 and 2 were basically equal, and Methods 3 and 4 were approximately 37-60 μg·m-3 lower than Method 1. From 2019 to 2021, the changes in regional background ρ（O3-8h） estimated by Methods 1-4 were 1.6, -13.4, 5.9, and -3.5 μg·m-3, respectively. The average estimations derived from multiple methods showed that the regional background ρ（O3-8h） in Henan Province from 2019 to 2021 concentrations were 82.0, 79.0, and 79.7 μg·m-3, accounting for 75.9%, 76.4%, and 78.7% of the total regional O3-8h, respectively. The regional background O3-8h estimated by the four methods showed obvious seasonal changes, characterized by summer > spring > fall > winter.

Real-time prediction of postoperative spinal shape with machine learning models trained on finite element biomechanical simulations.

Adolescent idiopathic scoliosis is a chronic disease that may require correction surgery. The finite element method (FEM) is a popular option to plan the outcome of surgery on a patient-based model. However, it requires considerable computing power and time, which may discourage its use. Machine learning (ML) models can be a helpful surrogate to the FEM, providing accurate real-time responses. This work implements ML algorithms to estimate post-operative spinal shapes. The algorithms are trained using features from 6400 simulations generated using the FEM from spine geometries of 64 patients. The features are selected using an autoencoder and principal component analysis. The accuracy of the results is evaluated by calculating the root-mean-squared error and the angle between the reference and predicted position of each vertebra. The processing times are also reported. A combination of principal component analysis for dimensionality reduction, followed by the linear regression model, generated accurate results in real-time, with an average position error of 3.75 mm and orientation angle error below 2.74 degrees in all main 3D axes, within 3 ms. The prediction time is considerably faster than simulations based on the FEM alone, which require seconds to minutes. It is possible to predict post-operative spinal shapes of patients with AIS in real-time by using ML algorithms as a surrogate to the FEM. Clinicians can compare the response of the initial spine shape of a patient with AIS to various target shapes, which can be modified interactively. These benefits can encourage clinicians to use software tools for surgical planning of scoliosis.

Difference in Gastrointestinal Cancer Risk and Mortality by Dietary Pattern Analysis: A Systematic Review and Meta-Analysis.

Several studies have demonstrated that dietary patterns identified by a posteriori and hybrid methods are associated with gastrointestinal (GI) cancer risk and mortality. These studies applied different methods for analyzing dietary data and reported inconsistent findings. This systematic review and meta-analysis were aimed to determine the association between dietary patterns, derived using principal component analysis (PCA) and reduced rank regression (RRR), and GI cancer risk and GI cancer-caused mortality. Articles published up to June 2023 in English were eligible for inclusion. The Medline, SCOPUS, Cochrane Library, CINHAL, PsycINFO, ProQuest, and Web of Sciences databases were used to identify prospective studies. The Preferred Reporting Item for Systematic Review and Meta-analysis Protocol 2020 was used to report results. A total of 28 studies were eligible for inclusion. Varied approaches to deriving dietary patterns were used, including PCA (n = 22), RRR (n = 2), combined PCA and RRR (n = 1), cluster analysis (CA; n = 2) and combined PCA and CA (n = 1). Two dietary patterns, "healthy" and "unhealthy," were derived using PCA and RRR. The healthy dietary pattern was characterized by a higher intake of fruits, whole grains, legumes, vegetables, milk, and other dairy products, whereas the unhealthy dietary pattern was characterized by a higher intake of red and processed meat, alcohol, and both refined and sugar-sweetened beverages. The findings indicated that the PCA-derived healthy dietary pattern was associated with an 8% reduced risk (relative risk [RR], 0.92; 95% CI, 0.87-0.98), and the unhealthy dietary pattern was associated with a 14% increased risk (RR, 1.14; 95% CI, 1.07-1.22) of GI cancers. Similarly, the RRR-derived healthy dietary pattern (RR, 0.83; 95% CI, 0.61-1.12) may be associated with reduced risk of GI cancers. In contrast, the RRR-derived unhealthy dietary pattern (RR, 0.93; 95% CI, 0.57-1.52) had no association with a reduced risk of GI cancers. Similarly, evidence suggested that PCA-derived healthy dietary patterns may reduce the risk of death from GI cancers, whereas PCA-derived unhealthy dietary patterns may increase the risk. Findings from prospective studies on the association of PCA-derived dietary patterns and the risk of GI cancers support the evidence of healthy and unhealthy dietary patterns as either protective or risk-increasing factors for GI cancers and for survivorship, respectively. The findings also suggest that the RRR-derived healthy dietary pattern reduces the risk of GI cancers (albeit with low precision), but no association was found for the RRR-derived unhealthy dietary pattern. Prospective studies are required to further clarify disparities in the association between PCA- and RRR-derived dietary patterns and the risk of GI cancers. Systematic review registration: PROSPERO registration no. CRD42022321644.

Analysis of flavor substances changes during fermentation of Chinese spicy cabbage based on GC-IMS and PCA

This study employed a combination of principal component analysis (PCA) and gas chromatography-ion mobility spectrometry (GC-IMS) to examine the distinctive taste mixtures produced by Chinese spicy cabbage (CSC) fermented at varying temperatures. As the fermentation progressed, the pH gradually decreased and stabilized after the 11 days of fermentation, and the total content of organic acids and short-chain fatty acids increased. A total of 49 volatile mixtures were detected during CSC fermentation and storage for 21 days. These included 7 aldehydes, 6 alcohols, 7 esters, 6 ketones, 5 pyrazines, 4 sulfides, 4 phenols, 2 ethers, 2 olefins, and 1 acid. With time, the content of most volatile flavor substances decreased. PCA of the signal intensities of the volatile chemicals in the samples showed significant differences in the flavor of CSC fermented at different temperatures; consequently, the samples fermented at different temperatures were effectively separated in relatively independent regions of CSC. Therefore, low-temperature fermentation and storage at 4 °C were more suitable for CSC. Based on the identified volatile chemicals, HS-GC-IMS and PCA could effectively construct the flavour fingerprints of CSC samples. This study provided a theoretical basis for improving the fermentation quality of CSC.

Analysis of lard in cod liver oil emulsion using FTIR spectroscopy combined principal component analysis

Cod liver oil (CLO) contains essential fatty acids and has a high price in the market. Therefore, CLO can be targeted for adulteration to increase economic profits. One of the substances used for adulteration of CLO is lard. This study aimed to analyze the spectral profile of lard and CLO in cod liver oil emulsion using Fourier transform infrared (FTIR) spectroscopy combined with principal component analysis (PCA). Lard and CLO were mixed with a range of concentrations of 0-100% used as the control. CLO emulsions were made with a composition of lard and CLO in concentrations similar to those of the control. To analyze the lard and CLO spectrum, lard and CLO were extracted from the emulsion using liquid-liquid extraction, and then the oil extracted from the emulsion was analyzed using FTIR spectroscopy and PCA. Fourier transform infrared spectrum absorption at region 1117–1098 cm-1 is specific to identifying the different spectrums of CLO and lard. The results of PCA showed that clustering between similar oil content and a combination of FTIR and PCA is effective in distinguishing the spectrum of lard and CLO in cod liver oil emulsion.

Advanced chemometric methodologies on single shot hyphenated LIBS data for rapid and reliable characterization of plastic classes

BackgroundPlastic Solid Waste (PSW) sorting is a procedure of paramount importance in the mechanical recycling process of plastics waste. The major limitation of the techniques relying on physical properties of plastics is the time taken for analysis and poor accuracy. Spectroscopy has been shown to be a suitable method in plastic sorting due to its atomic and molecular characterization capabilities, and ability to give results in very short time scales. However, for practical applications it is essential to translate this technique into an automatic technology, by combining it with advanced chemometric tools which can give observer independent judgement. ResultsThe indigenously developed bi-model Laser Induced Breakdown Spectroscopy (LIBS)-Raman system with single source and single detector can record the LIBS-Raman spectral signals in single-shot mode in a total time frame of 20 ms. Out of the combinations of Principal Component Analysis (PCA) and Partial Least Squares (PLS) with Logistic Regression (LR), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and Partial Least Squares-Discriminant Analysis (PLS-DA) based classifiers, the PLS-DA based model showed the maximum classification accuracy with 95 % based on LIBS data and 100 % based on Raman data. The reliability of the model was assessed using 4-fold cross-validation which showed a sensitivity of 90.28 % and specificity of 98.29 % for predictions based on LIBS data, and 99 % sensitivity and 99.82 % specificity for predictions relying on Raman data. SignificanceThe results show how the combination of multimodal spectroscopy with chemometric analysis enhances the applicability of spectroscopic techniques for plastic sorting. The classification model successfully classified seven types of post-consumer plastic samples based on combined LIBS and Raman data. With the home-built software for automated prediction, the system takes less than a second to predict the plastic type illustrating the potential of the method for translation to regular routine industrial applications.

Modulation of prey capture kinematics in relation to prey distance helps predict success.

Predators are not perfect, as some of their prey capture attempts result in failure. Successful attempts may be partly due to predators modulating their capture kinematics in relation to variation in the visual cues of the prey to increase the probability of success. In praying mantises, which have been suggested to possess stereoscopic vision, variation in prey distance has been shown to elicit variation in the probability of an attempt. However, it remains to be examined whether variation in prey distance results in mantises modulating their attempt to successfully capture prey. The goals of this study were to examine these relationships using the praying mantis system. Using 11 adult female Sphodromantis lineola, we recorded 192 prey capture attempts at 1000 Hz with two cameras to examine the 3D kinematics of successful and unsuccessful prey capture attempts. Using a combination of principal component analysis (PCA) and logistic regression, our results show that as prey distance increases, mantises adjust through greater and faster expansion of the forelegs and body (PC1), which significantly predicts capture success. However, PC1 only explains 22% of the variation in all prey capture attempts, suggesting that the other components may be related to additional aspects of the prey. Our results suggest that the distances at which mantises prefer to attempt to capture prey may be the result of their greater probability of successfully capturing the prey. These results highlight the range of motions mantises use when attempting to capture prey, suggesting flexibility in their prey capture attempts in relation to prey position.

Exploring Drivers of Wildfires in Spain

Wildfires play a dual role in ecosystems by providing ecological benefits while posing catastrophic events; they also inflict non-catastrophic damage and yield long-term effects on biodiversity, soil quality, and air quality, among other factors, including public health. This study analysed the key determinants of wildland fires in Spain using openly available spatial data from 2008 to 2021, including fire perimeters, bioclimatic variables, topography, and socioeconomic datasets, at a resolution of 1 km2. Our methodology combined principal component analysis (PCA), linear regression analysis, and one-way analysis of variance (ANOVA). Our findings show that scrub/herbaceous vegetation (average 63 ± 1.45% SE) and forests (average 19 ± 0.76% SE) have been highly susceptible to wildfires. The population density exhibited a robust positive correlation with wildfire frequency (R2 = 0.88, p < 0.0001). Although the study provides insights into some fire-related climatic drivers over Spain, it includes only temperature and precipitation-based variables and does not explicitly consider fuel dynamics. Therefore, a more advanced methodology should be applied in the future to understand the local specifics of regional wildfire dynamics. Our study identified that scrub/herbaceous areas and forests near densely populated regions should be prioritised for wildfire management in Spain, particularly under changing climate conditions.

Calculation of power transformer health index using the combination of principal component analysis and mass-spring-damper model

Calculation of power transformer health index using the combination of principal component analysis and mass-spring-damper model

Principal Components and Assortativity-based Assessment of the Similarity of Crime Metrics across Coterminous Wards in the City of Chicago

The City of Chicago (with 50 wards) has one of the highest crime rates in the US. We seek to quantitatively assess the similarity of crime metrics across coterminous wards using a combination of Principal Component Analysis (PCA) and Assortativity analysis. We first build a ward network (nodes are the wards and edges connect coterminous wards) of the city using the ward map. We parse through the 2022 crime dataset for the city and build a matrix whose entries correspond to the number of occurrences of a crime type in a ward. We conduct PCA of this ward-crime type matrix and determine a weighted average PC_crime_score (using the entries in the high-variance principal components and their variances as weights) for each ward. We observe the coterminous wards to exhibit moderate-strong assortativity with respect to three different crime metrics: hotspot classification, PC_crime_scores and the crime counts of the individual crime types.

Prediction of technological properties of wheat flour by combination of UV-VIS-NIR spectroscopy and multivariate analysis methods

Over the last decades, optical spectroscopy methods that do not require complex sample preparation have been widely used to identify and control the composition of food products. In the present study, the possibility of using UV-VIS-NIR spectroscopy combined with multivariate analysis for grading wheat flour into groups differing in technological properties was analyzed. UV-VIS-NIR spectra contain information on the combination and intensity of absorption bands assigned to functional groups of the composition components and determining the technological properties of wheat flour. The database of UV-VIS-NIR spectra of wheat flour samples differing by technological properties was formed into three groups: the first group — wheat flour samples with good baking properties, the second group — with reduced baking properties, the third group — with low baking properties. The visible range of UV-VIS-NIR diffuse reflectance spectrum was used to calculate the color coordinates in the CIE colorimetric system L*a*b*. The greatest difference among the groups in the color coordinates of the samples was found for the coordinate b*, which is associated with the different content of coloring pigments. The spectra database was used to build a classification model for grading wheat flour into quality groups using a combination of principal component analysis and linear discriminant analysis (PCA-LDA) methods. The achieved results indicate that the classification model built on the training sample is able to distinguish wheat flour spectra by quality groups with an accuracy of 96.49%. The effective- ness of the model is verified using a test set of spectra of wheat flour samples. The present study confirms that the combina- tion of UV-VIS-NIR spectroscopy in conjunction with the PCA-LDA method has significant potential for determining a quality group of wheat flour based on technological properties.

Determinants of Household Extreme Poverty Among Female-Headed Households in Indonesia: Does Disability Matter?

ABSTRACT This paper investigates factors contributing to extreme poverty among female-headed households in Indonesia, with a specific focus on the impact of disabilities. Analyzing data from the 2021 National Socio-Economic Survey, this research combined both principal component and path analysis to uncover the link between poverty dimensions (isolation, physical weakness, powerlessness, and vulnerability) and extreme poverty. The study revealed that various dimensions influence extreme poverty, and the presence of disabilities within a household exacerbates the risk of extreme poverty and can alter the significance of initially insignificant variables. These findings underscore the critical role of disabilities in shaping extreme poverty outcomes.

How different can smart cities be? A typology of smart cities in China

China, renowned for being one of the world's largest smart city testing fields, has witnessed the emergence of numerous smart cities. Existing publications highlight the diversity in smart city development, wherein cities with different contexts and institutional factors exhibit distinct characteristics. To delve deeper into this subject, we employed a mixed methods approach to classify 49 Chinese smart cities and subsequently developed a typology for Chinese smart cities in this study. Our methodology involved three steps. Initially, we devised a classification framework based on the input-throughput-output model and conducted content analysis to identify the characteristics of the 49 cities. Subsequently, we utilized a combination of principal component analysis (PCA) and K-means clustering analysis to categorize these cases. Finally, we formulated a typology consisting of five types of Chinese smart cities: knowledge-technocratic smart cities, holistic smart cities, green smart cities, equipment-technocratic smart cities, and emerging smart cities. The findings reveal that different smart city types are characterized by distinct features and priorities in input, throughput, and output. The development of smart cities should comprehensively consider and respect the local urban contexts and the challenges they present. The insights from this study hold relevance for both policymakers and academic researchers.

Automated classification pipeline for real-time in vivo examination of colorectal tissue using Raman spectroscopy

Colorectal cancer is the third most common malignancy worldwide and one of the leading causes of death in oncological patients with its diagnosis typically involving confirmation by tissue biopsy. In vivo Raman spectroscopy, an experimental diagnostic method less invasive than a biopsy, has shown great potential to discriminate between normal and cancerous tissue. However, the complex and often manual processing of Raman spectra along with the absence of a suitable instant classifier are the main obstacles to its adoption in clinical practice. This study aims to address these issues by developing a real-time automated classification pipeline coupled with a user-friendly application tailored for non-spectroscopists. First, in addition to routine colonoscopy, 377 subjects underwent in vivo acquisitions of Raman spectra of healthy tissue, adenomatous polyps, or cancerous tissue, which were conducted using a custom-made microprobe. The spectra were then loaded into the pipeline and pre-processed in several steps, including standard normal variate transformation and finite impulse response filtration. The quality of the pre-processed spectral data was checked based on their signal-to-noise ratio before the suitable spectra were decomposed and classified using a combination of principal component analysis and a support vector machine, respectively. After five-fold cross-validation, the developed classifier exhibited 100% sensitivity toward adenocarcinoma and adenomatous polyps. The overall accuracy was 96.9% and 79.2% for adenocarcinoma and adenomatous polyps respectively. In addition, an application with a graphical user interface was developed to facilitate the use of our data pipeline by medical professionals in a clinical environment. Overall, the combination of supervised and unsupervised machine learning with algorithmic pre-processing of in vivo Raman spectra appears to be a viable way of reducing the relatively large number of biopsies currently needed to definitively diagnose colorectal cancer.

Geochemical Signatures of Mafic Volcanic Rocks in Modern Oceanic Settings and Implications for Archean Mafic Magmatism

Abstract Greenstone belts are dominated by mafic volcanic rocks with geochemical characteristics that indicate a range of possible geodynamic influences. Many analogies with modern tectonic settings have been suggested. Increasing exploration of the modern oceans and comprehensive sampling of volcanic rocks from the sea floor are now providing unique opportunities to characterize different melt sources and petrogenesis that can be more closely compared to greenstone belts. In this study, we have compiled high-quality geochemical analyses of more than 2,850 unique samples of submarine mafic volcanic rocks (<60 wt % SiO2) from a wide range of settings, including mid-ocean ridges, ridge-hotspot intersections, intraoceanic arc and back-arc spreading centers, and ocean islands. The compiled data show significant geochemical variability spanning the full range of compositions of basalts found in greenstone belts. This diversity is interpreted to be due to variable crustal thickness, dry melting versus wet melting conditions, mantle mixing, and contamination. In particular, different melting conditions have been linked to mantle heterogeneity, complex mantle flow regimes, and short-lived tectonic domains, such as those associated with diffuse spreading, overlapping spreading centers, and triple junctions. These are well documented in the microplate mosaics of the Western Pacific. Systematic differences in mafic volcanic rock compositions in modern oceanic settings are revealed by a combination of principal components analysis and unsupervised hierarchical clustering of the compiled data. Mafic volcanic rocks from most arc-back arc systems have strongly depleted mantle signatures and well-known subduction-related chemistry such as large ion lithophile element (LILE) enrichment in combination with strong negative Nb-Ta anomalies and low heavy rare earth elements (HREEs). This contrasts with mafic volcanic rocks in Archean greenstone belts, which show no, or at least weaker, subduction-related chemistry, a less depleted mantle, less wet melting, and variable crustal contamination. The differences are interpreted to be the result of the lower mantle temperatures, thinner crust, and subduction-related processes of present-day settings. However, mafic rocks that are geochemically identical to those in Archean greenstone belts occur in many modern back-arc basins, including the Lau basin, East Scotia ridge, Bransfield Strait, and Manus basin, which are characterized by fertile mantle sources, high heat flow, and complex spreading regimes typical of small-scale microplate mosaics. These types of settings are recognized as favorable for volcanogenic massive sulfide (VMS) deposits in modern and ancient greenstone belts, and therefore the particular geochemical signatures of the mafic volcanic rocks are potentially important for area selection in base metal exploration.

Tracking element-mineral associations with unsupervised learning and dimensionality reduction in chemical and optical image stacks of thin sections

In-situ chemical analysis on thin sections is a cornerstone of geochemical research. Despite massive advances in digital image analysis, the interpretation of such data within the optical petrological context of the thin section has largely remained an analogue task in geochemistry. In this contribution, we registered optical and micro-chemical images from large thin section areas. Chemical datasets from scanning electron microscopy energy dispersive spectrometry (SEM-EDX) and Synchrotron X-ray fluorescence microscopy (S-XFM) were exported from proprietary software. We then evaluated two dimensionality reduction techniques against false-colour images and phase maps to test whether previously unnoticed features became discoverable. Principal component analysis (PCA) and deep sparse autoencoder (DSA) neural networks were used to summarise the multi-channel SEM-EDX and S-XFM into one single red-green-blue (RGB) representation each.Applied to an oceanic gabbro, a cratonic peridotite, and a pelagic limestone, the PCA-based dimensionality reduction was found to produce crisp RGB maps of phases with less noise than false-colour three-element RGB maps. They were registered with optical images to form a simple multi-channel input for pixel-based classification into classes (i.e., semantic segmentation). This was fast and worked well for typical igneous and metamorphic rocks (1–3 h routine). In the chemically quite homogenous limestone, the combined optical and S-XFM PCA input was successfully classified into many phases that were unclassifiable on the conventional SEM-EDX phase map. From the segmented optical and S-XFM PCA map, we exported pixel locations of classified accessory phases back into the original proprietary S-XFM software. This allowed quantification of trace elements whose X-ray peaks were invisible in the original S-XFM quantification.The DSA-based approach yielded phase maps with greater noise, but the technique was very strong at detecting subtle features. In the gabbro sample, the DSA image identified cryptic relict cores in clinopyroxene more clearly than in the previously used Cr concentration map. A DSA training set can be obtained on a small ROI to generate a consistent large area DSA image from which more fragmental cores were observed. For a ROI on the gabbro thin section, the DSA representation map and the blended optical image were segmented and inspected with a loupe tool. This allowed us to generate interactive histograms and bin-scatter concentration plots of selected phases and to search for co-variations of element concentrations. This approach can be expanded to include data from any in situ geochemical acquisition tools and may help discover previously unseen features in complex elemental imagery.

Land use and land cover mapping using Landsat-8 and Sentinel-2 data in Al Qunfudhah coast, western Saudi Arabia: A comparative study

Al Qunfudhah Governorate has assumed a tourist status in the strip of Saudi coastal cities on the Red Sea coast. Agriculture, food industries, and engineering industries are among the most important economic activities in the city. As a result, Land use and land cover (LULC) detection is essential for several reasons: urban planning, sustainability, resource management and environmental preservation. This research aims to identify the LULC of the Al Qunfudhah area in western Saudi Arabia by comparing Landsat-8 and Sentinel-2 data outputs and evaluating their accuracy results. Various methods are used to process satellite image data to enhance the contrast between surface features. Some of these techniques are true colour composite (TCC) images, enhanced true colour composite (ETCC) images, false colour composite (FCC) images, principal component analysis (PCA), band ratios and Maximum Likelihood Algorithm (MLA) Supervised Classification. By utilising band combination methods, PCA methods, and band ratio methods, we were able to map a variety of features, including vegetation cover, mangroves, Sabkha and non-Sabkha deposits, wadi basins, shallow and deep shelf areas, islands, sand and mud sediments, rocky reefs and urban areas. As part of the study, ArcGIS 10.8's supervised classification tool was employed to categorise the study region's features and calculate the percentage of each class. In both Landat-8 and Sentinel-2 classification images, the same classes were identified (i.e. sand and mud sediments, sabkhas, wadi basins, aeolian sand and loess sediments, islands, urban areas, vegetation, and mangroves). The accuracy of the classification results was determined using a reliable statistical approach. The accuracy assessments of Landsat-8 and Sentinel-2 revealed accuracy rates of 87% and 89.1% respectively, along with kappa coefficients of 84.9% and 87.3%. For the investigated area, the Landsat-8 and Sentinel-2 satellites were effective in producing LULC maps.