Machine learning and tectonic setting determination: Bridging the gap between Earth scientists and data scientists

The comments of Roser and Korsch (1984) are related to two aspects: (1) their apparent inability to reproduce the results of the discriminant scores as given in table 9 of my paper (Bhatia 1983) and (2) the effect of grain size on the composition of clastic sedimentary rocks. The apparent discrepancy in the discriminant scores is due to their error in calculation. Roser and Korsch (1984) calculated the discriminant scores using the volatile-free averages of the published sandstone suites tabulated in tables 5-8 of my paper. However, the discriminant functions that I developed are based on the actual (non volatilefree) analyses of the sandstone suites of eastern Australia. Thus, the discriminant scores on the published averages given in table 9 of my paper were also calculated using the actual analyses and not the volatile-free analyses. This is mentioned in the text of my paper (Bhatia 1983 p. 620): "Discriminant scores for averages of the published analyses were calculated using the unstandardized function coefficients of table 3 and the actual abundance of element oxide in the average" [italics added]. The actual average chemical analyses and the calculation of the discriminant scores for three of the suites on which significant apparent discrepancies exist are presented in table 1 as examples. In the three cases presented (Aure Trough, Santa Ynez, and the Rhyolitic Sand suites), all the scores agree with those given in Bhatia (1983) and differ significantly from those calculated by Roser and Korsch (1984). The incomplete published analyses certainly posed some problem. Due to the im-

Many lung diseases like Chronic Obstructive Pulmonary Disease (COPD) and Asthma are chronic diseases and worldwide considered as third main cause of death. COPD remains a forefront issue in global health, presenting significant challenges due to its complex nature and the imperative for precise classification to effectively guide treatment protocols. Traditional diagnostic methods, while effective, often come with limitations such as invasiveness, cost, and the requirement for specialized expertise. Recent advancements in machine learning (ML), particularly supervised ML algorithms, have shown promise in enhancing COPD classification through the analysis of clinical data, imaging, and physiological data. This review paper aims to systematically examine the current state of research on the application of supervised ML algorithms for the classification of COPD. We evaluate the effectiveness, accuracy, and clinical applicability of these algorithms by analyzing studies published in the last decade. Our review covers a range of supervised ML techniques, including K-Nearest Neighbor (KNN), Logistic Regression (LR), Support Vector Machine (SVM), and Convolutional Neural Network (CNN), Extreme Gradient Boosting (EGB), emphasizing their effectiveness by employing evaluating metrics such as accuracy, specificity, AUC scores and sensitivity. The observations of this review indicate that supervised machine learning algorithms can significantly enhance the classification and prediction of COPD stages, offering prospects for customized treatment plans and enhanced patient prognosis.

The quality of source code is negatively impacted by code smells. Since the term "code smell" originated, numerous attempts have been made to comprehend it by identifying it using various techniques, such as metric-based, heuristic-based, optimization-based, machine learning (ML)-based, etc. Among these, supervised machine learning (SML) has shown effectiveness in detecting code smells. However, SML techniques have significant limitations, including the dependency on expensive and high-quality labeled data, the need for representative training datasets, and the risk of introducing biases in labeled examples that lead to skewed predictions. To overcome these challenges, this study introduces a method that leverages unsupervised machine learning (UnML) along with feature engineering. Unlike SML, UnML does not require labeled data and minimizes potential biases. The proposed method was evaluated using four datasets containing different types of code smells and was compared with a previous study that used SML techniques. The results indicate that the UnML-based method is effective, achieving outcomes closely aligned with those from the SML approach. This method is especially beneficial in situations where labeled data is scarce or unavailable and can be used to identify new code smells, generate labeled data for SML and detect multiple code smells simultaneously within a codebase.

Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, natural-looking motions, most data-driven approaches require considerable efforts of pre-processing, including motion segmentation and annotation. Existing (semi-) automatic solutions either require hand-crafted features for motion segmentation or do not produce the semantic annotations required for motion synthesis and building large-scale motion databases. In addition, human labeled annotation data suffers from inter- and intra-labeler inconsistencies by design. We propose a semi-automatic framework for semantic segmentation of motion capture data based on supervised machine learning techniques. It first transforms a motion capture sequence into a ``motion image'' and applies a convolutional neural network for image segmentation. Dilated temporal convolutions enable the extraction of temporal information from a large receptive field. Our model outperforms two state-of-the-art models for action segmentation, as well as a popular network for sequence modeling. Most of all, our method is very robust under noisy and inaccurate training labels and thus can handle human errors during the labeling process.

This paper presents advancements in machine learning and cloud deployment that enable rapid and accurate automated lithology interpretation. A supervised machine learning technique is described that enables rapid, consistent, and accurate lithology prediction alongside quantitative uncertainty from large wireline or logging-while-drilling (LWD) datasets. To leverage supervised machine learning, a team of geoscientists and petrophysicists made detailed lithology interpretations of wells to generate a comprehensive training dataset. Lithology interpretations were based on applying determinist cross-plotting by utilizing and combining various raw logs. This training dataset was used to develop a model and test a machine learning pipeline. The pipeline was applied to a dataset previously unseen by the algorithm, to predict lithology. A quality checking process was performed by a petrophysicist to validate new predictions delivered by the pipeline against human interpretations. Confidence in the interpretations was assessed in two ways. The prior probability was calculated, a measure of confidence in the input data being recognized by the model. Posterior probability was calculated, which quantifies the likelihood that a specified depth interval comprises a given lithology. The supervised machine learning algorithm ensured that the wells were interpreted consistently by removing interpreter biases and inconsistencies. The scalability of cloud computing enabled a large log dataset to be interpreted rapidly; >100 wells were interpreted consistently in five minutes, yielding >70% lithological match to the human petrophysical interpretation. Supervised machine learning methods have strong potential for classifying lithology from log data because: 1) they can automatically define complex, non-parametric, multi-variate relationships across several input logs; and 2) they allow classifications to be quantified confidently. Furthermore, this approach captured the knowledge and nuances of an interpreter's decisions by training the algorithm using human-interpreted labels. In the hydrocarbon industry, the quantity of generated data is predicted to increase by >300% between 2018 and 2023 (IDC, Worldwide Global DataSphere Forecast, 2019–2023). Additionally, the industry holds vast legacy data. This supervised machine learning approach can unlock the potential of some of these datasets by providing consistent lithology interpretations rapidly, allowing resources to be used more effectively.

Geographical discrimination and adulteration analysis for edible oils using two-dimensional correlation spectroscopy and convolutional neural networks (CNNs).

Botanists study in general the characteristics of leaves to give to each plant a scientific name; such as shape, margin...etc. This paper proposes a comparison of supervised plant identification using different approaches. The identification is done according to three different features extracted from images of leaves: a fine-scale margin feature histogram, a Centroid Contour Distance Curve shape signature and an interior texture feature histogram. First represent each leaf by one feature at a time in, then represent leaves by two features, and each leaf was represented by the three features. After that, the authors classified the obtained vectors using different supervised machine learning techniques; the used techniques are Decision tree, Naïve Bayes, K-nearest neighbour, and neural network. Finally, they evaluated the classification using cross validation. The main goal of this work is studying the influence of representation of leaves' images on the identification of plants, and also studying the use of supervised machine learning algorithm for plant leaves classification.

Due to the highly variable clinical phenotype, Klinefelter Syndrome is underdiagnosed. Assessment of supervised machine learning based prediction models for identification of Klinefelter Syndrome among azoospermic patients, and comparison to expert clinical evaluation. Retrospective patient data (karyotype, age, height, weight, testis volume, follicle-stimulating hormone, luteinizing hormone, testosterone, estradiol, prolactin, semen pH and semen volume) collected between January 2005 and June 2019 were retrieved from a patient data bank of a University Centre. Models were trained, validated and benchmarked based on different supervised machine learning algorithms. Models were then tested on an independent, prospectively acquired set of patient data (between July 2019 and July 2020). Benchmarking against physicians was performed in addition. Based on average performance, support vector machines and CatBoost were particularly well-suited models, with 100% sensitivity and >93% specificity on the test dataset. Compared to a group of 18 expert clinicians, the machine learning models had significantly better median sensitivity (100% vs. 87.5%, p=0.0455) and fared comparably with regards to specificity (90% vs. 89.9%, p=0.4795), thereby possibly improving diagnosis rate. A Klinefelter Syndrome Score Calculator based on the prediction models is available on http://klinefelter-score-calculator.uni-muenster.de. Differentiating Klinefelter Syndrome patients from azoospermic patients with normal karyotype (46,XY) is a problem that can be solved with supervised machine learning techniques, improving patient care. Machine learning could improve the diagnostic rate of Klinefelter Syndrome among azoospermic patients, even more for less-experienced physicians.

The escalating threat of natural disasters to public safety worldwide underlines the crucial role of effective environmental risk management tools, such as insurance. This is particularly evident in the case of earthquakes that occurred in Oklahoma between 2011 and 2020, which were linked to wastewater injection, underscoring the need for earthquake insurance. In this regard, from a survey of 812 respondents in Oklahoma, USA, we used supervised machine learning techniques (i.e., logit, ridge, least absolute shrinkage and selection operator (LASSO), decision tree, and random forest classifiers) to identify the factors that influence earthquake insurance uptake and to predict individuals who would acquire earthquake insurance. Our findings reveal that influential factors that affect earthquake insurance uptake include demographic factors such as older age, male gender, race, and ethnicity. These were found to significantly influence the decision to purchase earthquake insurance. Additionally, individuals residing in rental properties were less likely to purchase earthquake insurance, while longer residency in Oklahoma had a positive influence. Past experience of earthquakes was also found to positively influence the decision to purchase earthquake insurance. Both decision trees and random forests demonstrated good predictive capabilities for identifying earthquake insurance uptake. Notably, random forests exhibited higher precision and robustness, emerging as an encouraging choice for earthquake insurance modeling and other classification problems. Empirically, we highlight the importance of insurance as an environmental risk management tool and emphasize the need for awareness and education on earthquake insurance as well as the use of supervised machine learning algorithms for classification problems.

The Meso-Neoproterozoic shales of the Bastar craton, Central Indian Shield have been analyzed geochemically to study their geochemical characteristics and to evaluate paleoweathering, provenance, tectonic setting and paleoredox conditions. The shale samples have been classified into the calcareous and the non-calcareous shales on the basis of presence of calcite and CaO concentrations. In comparison to the calcareous shales, the non-calcareous shales have higher concentrations of most major elements and trace elements including rare earth elements (REEs). The Upper Continental Crust (UCC) normalized elemental ratios of the calcareous and the non-calcareous shales suggest evolved sources similar to the UCC (Upper Continental Crust). The Th/Co versus La/Sc and La-Th-Sc diagrams, chondrite normalized REE patterns and negative Eu/Eu* values of the calcareous and non-calcareous shale samples further reveal that the sediments have been derived from a felsic source and the source rocks have been identified to be the granites and the gneisses of the Bastar craton. The SiO2 versus K2O/Na2O and the SiO2/Al2O3 versus K2O/Na2O tectonic setting discrimination diagrams indicate sediments were deposited in a passive margin tectonic setting. The CIA (Chemical Index of Alteration), PIA (Plagioclase Index of Alteration), Th/U and K/Rb ratios and the K2O-Fe2O3-Al2O3 relations of both the calcareous and the non-calcareous shales indicate that source area was affected by moderate to intense weathering history. The geochemical parameters like Ce/Ce* and Mn* suggest that the calcareous shales were deposited in suboxic environment compared to the non-calcareous shales.

In recent years, deep learning (DL) has revolutionized medical imaging, offering notable promise in orthopedic diagnostics. This systematic review explores how DL, particularly Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), are applied to detect and analyze orthopedic anomalies such as fractures, spinal deformities, and foot deformities. We reviewed 63 peer-reviewed studies published between 2017 and 2025, analyzing their methodologies, datasets, performance metrics, and clinical relevance. The findings reveal significant advancements in fracture classification and vertebral labeling, though challenges persist for subtle anomalies and less-represented deformities. Despite encouraging results, limitations include small sample sizes, lack of external validation especially for rare pathologies. We conclude by identifying research gaps and proposing future directions for developing robust, clinically integrated DL tools to enhance diagnostic accuracy, data diversity, and anomaly detection in complex orthopedic scenarios.

This article present results from automatic detection of dust impact signals observed by the Solar Orbiter – Radio and Plasma Waves instrument. A sharp and characteristic electric field signal is observed by the Radio and Plasma Waves instrument when a dust particle impact the spacecraft at high velocity. In this way, ∼5–20 dust impacts are daily detected as the Solar Orbiter travels through the interstellar medium. The dust distribution in the inner solar system is largely uncharted and statistical studies of the detected dust impacts will enhance our understanding of the role of dust in the solar system. It is however challenging to automatically detect and separate dust signals from the plural of other signal shapes for two main reasons. Firstly, since the spacecraft charging causes variable shapes of the impact signals and secondly because electromagnetic waves (such as solitary waves) may induce resembling electric field signals. In this article, we propose a novel machine learning-based framework for detection of dust impacts. We consider two different supervised machine learning approaches: the support vector machine classifier and the convolutional neural network classifier. Furthermore, we compare the performance of the machine learning classifiers to the currently used on-board classification algorithm and analyze one and a half year of Radio and Plasma Waves instrument data. Overall, we conclude that classification of dust impact signals is a suitable task for supervised machine learning techniques. In particular, the convolutional neural network achieves a 96 % ± 1 % overall classification accuracy and 94 % ± 2 % dust detection precision, a significant improvement to the currently used on-board classifier with 85 % overall classification accuracy and 75 % dust detection precision. In addition, both the support vector machine and the convolutional neural network detects more dust particles (on average) than the on-board classification algorithm, with 14 % ± 1 % and 16 % ± 7 % detection enhancement respectively. The proposed convolutional neural network classifier (or similar tools) should therefore be considered for post-processing of the electric field signals observed by the Solar Orbiter.

The geochemistry and detrital zircon geochronology of the Quemoco sandstones from the Woruo Mountain area, North Qiangtang Basin, are analysed to discriminate their provenance and tectonic setting. The sandstones were classified as litharenite according to their geochemical data. The index of chemical variability and SiO2/Al2O3 ratio values suggest that the compositional maturity and recycling are weak to moderate. The weathering indices, such as chemical index of alteration, plagioclase index of alteration, and chemical index of weathering, and A–CN–K (Al2O3–(CaO* + Na2O)–K2O) ternary plot reflect that the source areas have undergone a weak degree of weathering. The TiO2 versus Zr, La/Th versus Hf, and Co/Th versus La/Sc bivariate diagrams and multimajor elements discrimination diagram of Quemoco sandstones indicate that the provenances were primarily derived from felsic igneous rocks and may also have less intermediate igneous source rocks. The paleocurrent data and low composition and textural maturity of the Quemoco sandstones suggested that the provenances are mainly from the southwest of the study area and with proximal source features. The U–Pb ages studied here could be divided into 8 groups: 206–219 Ma, 268–283 Ma, 446–630 Ma, 700–970 Ma, 1006–1346 Ma, 1457–1843 Ma, 2087–2214 Ma, and 2331–2587 Ma. The provenances are mainly from the Central Uplift Belt and surrounding of the study area according to the detrital zircon ages and rare earth element parameters, which are composed of Late Triassic tuff, Permian basalt, Early Ordovician granite, Cambrian granite gneiss, and Precambrian crystalline basement. Two multidimensional tectonic discrimination diagrams based on major elements show a complicated tectonic setting composed of a collision, rift, and minor arc setting for the Quemoco sandstones, which is consistent with the nature of a rifted margin during the late Late Triassic.

A robust calibration and supervised machine learning reliability framework has been developed to aid the circuit designer in the design and implementation of reliable digitally-reconfigurable self-healing RFICs. For calibration algorithm performance and reliability validation, we advocate the use of surrogate modeling, a supervised machine learning technique, which offers a significant reduction in the required computational complexity relative to relying solely on the execution of expensive circuit simulations. An RF phase rotator test case is used to show the robustness and utility of the developed self-healing reliability framework.

The aim of this study was to assess measurements of the maxillary canines using Cone Beam Computed Tomography (CBCT) and develop a machine learning model for sex estimation. CBCT scans from 610 patients were screened. The maxillary canines were examined to measure total tooth length, average enamel thickness, and mesiodistal width. Various supervised machine learning algorithms were employed to construct predictive models, including Decision Tree, Gradient Boosting Classifier, K-Nearest Neighbors (KNN), Logistic Regression, Multi-Layer Perceptron (MLP), Random Forest Classifier, Support Vector Machine (SVM), XGBoost, LightGBM, and CatBoost. Validation of each model was performed using a 10-fold cross-validation approach. Metrics such as area under the curve (AUC), accuracy, recall, precision, and F1 Score were computed, with ROC curves generated for visualization. The total length of the tooth proved to be the variable with the highest predictive power. The algorithms that demonstrated superior performance in terms of AUC were LightGBM and Logistic Regression, achieving AUC values of 0.77 [CI95% = 0.65-0.89] and 0.75 [CI95% = 0.62-0.86] for the test data, and 0.74 [CI95% = 0.70-0.80] and 0.75 [CI95% = 0.70-0.79] in cross-validation, respectively. Both models also showed high precision values. The use of maxillary canine measurements, combined with supervised machine learning techniques, has proven to be viable for sex estimation. The machine learning approach combined with is a low-cost option as it relies solely on a single anatomical structure.