Learning Regression Research Articles

Python-based machine learning estimation ofthermo-hydraulic performance along varying nanoparticle shape, nanofluid and tube configuration

In this research article, a Python-based machine learning model prediction study was conducted based on the study results obtained from sudden expansion tubes containing different expansion angles, dimpled fin structures and nanofluids, whose thermo-hydraulic performance was previously examined. In the study, Artificial Neural Network and Ridge regression models were used to make predictions on the average Nusselt number (Nu), average Darcy friction factor (f) and performance evaluation criteria (PEC). Physical variations of the sudden expansion tube were taken into account and a detailed comparison of the results was made. A superior average Nu was acquired as 172.45 %, 22.05 %, 17.18 %, 13.65 %, and 7.76 % compared to Ag-MgO/H2O, Al2O3/H2O (blade), CoFe2O4/H2O, Al2O3/H2O (cylindrical), and Al2O3/H2O (platelet), respectively. The highest Performance Evaluation Criteria (PEC) for Re= 2000 based on Al2O3/H2O (platelet) shows an increase of 4.84 %, 12.08 %, 11.76 %, 66.05 %, and 148.94 % compared to Al2O3/H2O (cylindrical), Al2O3/H2O (blade), CoFe2O4/H2O, Fe3O4/H2O, and Ag-MgO/H2O, respectively. From the results obtained, it was determined that Python-based Machine Learning approach which facilitates custom optimizations showed a significant performance with small margins of error in predicting the heat transfer parameters. The lowest error rates of machine learning and polynomial ridge regression models ranged from 0.2 % to 5.4 % for the unseen test set and the application of Python-based algorithms provided considerable savings in calculation time compared to conventional methods. On the other hand, using machine learning models with feature engineering has been found to increase model performance by at least 30 %. In these years when studies on the predictions of thermo-hydraulic studies are very rare in the literature, this study is intended to facilitate scientists, engineers and academicians who will further study on this subject.

Pneumonia detection on chest X-rays from Xception-based transfer learning and logistic regression

Pneumonia is a dangerous disease that kills millions of children and elderly patients worldwide every year. The detection of pneumonia from a chest x-ray is perpetrated by expert radiologists. The chest x-ray is cheaper and is most often used to diagnose pneumonia. However, chest x-ray-based diagnosis requires expert radiologists which is time-consuming and laborious. Moreover, COVID-19 and pneumonia have similar symptoms which leads to false positives. Machine learning-based solutions have been proposed for the automatic prediction of pneumonia from chest X-rays, however, such approaches lack robustness and high accuracy due to data imbalance and generalization errors. This study focuses on elevating the performance of machine learning models by dealing with data imbalanced problems using data augmentation. Contrary to traditional machine learning models that required hand-crafted features, this study uses transfer learning for automatic feature extraction using Xception and VGG-16 to train classifiers like support vector machine, logistic regression, K nearest neighbor, stochastic gradient descent, extra tree classifier, and gradient boosting machine. Experiments involve the use of hand-crafted features, as well as, transfer learning-based feature extraction for pneumonia detection. Performance comparison using Xception and VGG-16 features suggest that transfer learning-based features tend to show better performance than hand-crafted features and an accuracy of 99.23% can be obtained for pneumonia using chest X-rays.

Machine learning integration with response surface methodology to enhance the removal efficacy of arsenate (V) through sulfur-functionalized mxene coated QPPO/PVA AEM

Arsenic, a poisonous and carcinogenic heavy metal in drinking water, presents severe health risks to humans, including skin lesions, neurological damage, and circulatory disorders. Despite extensive research efforts have been carried out on removing arsenate (As(V)) using membrane technologies, however, there remains a critical need to further enhance membrane removal efficacy to achieve maximum reusability. Thus, to minimize this challenge, herein we explore the impact of S-functionalized Mxene coating over the surface of quaternary ammonium poly (2,6-dimethyl-1,4-phenylene oxide)/polyvinyl alcohol (QPPO/PVA) anion exchange AEM membrane against As(V) removal. To optimize and validate adsorption efficacy, response surface methodology (RSM) study was carried out using a central composite design (CCD) with R2 = 0.995. The significance of these variables was also confirmed by CCD matrix, yielding statistically significant results (p < 0.0001). Adsorption efficacy was further enhanced by employing different machine learning (ML) regression models to finely tune experimental parameters. Among ML models, Random Forest Regression (RFR) has shown highest predictive accuracy (R2 = 0.929, RMSE = 4.57 mg L-1) and identified As(V) concentration as the most influential factor affecting adsorption efficacy. ML-optimization has shown maximum adsorption efficacy at pH (3), contact time (5 min), and As(V) concentration (50 mg L−1). Freundlich isotherm model has shown adsorption capacity of 413 mg/g (R2 = 0.997), while pseudo-second-order kinetic model reflected R2 of 0.989. Thermodynamic assessments (ΔGᵒ, ΔH°, ΔS°) confirmed the process as spontaneous. To the best of our knowledge, this is the first study in which ML is employed to design highly efficient and reliable membranes, providing a novel approach to enhance membrane-based remediation strategies.

Digital twin for decision support system of industrial utility management

Manufacturing and industrial operations rely heavily on energy that is generated mostly from fossil fuels, such as coal, oil, and natural gas, which harm the environment and contribute to climate change. Thus, renewable energy is being integrated into industrial processes to lessen environmental effects and reduce fossil fuel usage. However, the renewable source performance process can be greatly affected by disturbances and constraints, such as ambient air temperature and relative humidity, minimum utility consumption, and the total energy required, making effective control difficult. This study proposes a digital twin built with machine learning regression techniques for load demand forecasting as a decision-support system for industrial utility management. From the results, the ensemble tree (ET) model produced the highest accuracy, based on validation and test dataset root mean squared error values of 23.164 and 27.558, respectively, and R2 values of 0.96 and 0.95, respectively. The digital twin and load demand forecasting approaches effectively created an efficient operating schedule for industrial utility management. The ET model had a total error of 23.86%, substantially lower than the average load demand's total error of 65.29%. Therefore, the ET model with weather conditions in four scenarios could be recommended to optimize energy utilization when creating the operating schedule.

Exploring the Nexus Between Fertility Rates and Geopolitical Risk with Intelligence Methods: A Multifaceted Analysis

Background/Objectives: This paper presents an analysis of birth rate statistics, specifically focusing on recorded births in Scotland. The main research objective focuses on investigating the influence of geopolitical concerns on birth rate forecasts. Specifically, we examine whether individuals may choose to postpone or abstain from having children during times of conflict or political turmoil due to concerns about personal safety, the welfare of their children, or uncertainty about the future caused by geopolitical risks. Additionally, this study examines how disruptions to healthcare services, such as limited access to prenatal care and maternal health facilities, can affect birth outcomes and lead to changes in birth rates. Methods: To approach the research objective both machine learning algorithms and classical statistical procedures. Also, as part of the current analysis, the Geopolitical Risk Index has been applied as an extra factor to predict the birth rate. Results: The results of our study demonstrate the effectiveness of machine learning in producing precise predictions in this field, while emphasizing the significant influence of geopolitical risk on comprehending the dynamics of birth rates in Scotland. Conclusions: This study examines the effectiveness of several machine learning regression models in accurately predicting the number of births in Scotland using data that is not included in the model training process. Findings show promising outcomes in predicting births, while geopolitical instability has been indicated as a substantial influence on birth rates and fertility rates.

Evolving Transparent Credit Risk Models: A Symbolic Regression Approach Using Genetic Programming

Credit scoring is a cornerstone of financial risk management, enabling financial institutions to assess the likelihood of loan default. However, widely recognized contemporary credit risk metrics, like FICO (Fair Isaac Corporation) or Vantage scores, remain proprietary and inaccessible to the public. This study aims to devise an alternative credit scoring metric that mirrors the FICO score, using an extensive dataset from Lending Club. The challenge lies in the limited available insights into both the precise analytical formula and the comprehensive suite of credit-specific attributes integral to the FICO score’s calculation. Our proposed metric leverages basic information provided by potential borrowers, eliminating the need for extensive historical credit data. We aim to articulate this credit risk metric in a closed analytical form with variable complexity. To achieve this, we employ a symbolic regression method anchored in genetic programming (GP). Here, the Occam’s razor principle guides evolutionary bias toward simpler, more interpretable models. To ascertain our method’s efficacy, we juxtapose the approximation capabilities of GP-based symbolic regression with established machine learning regression models, such as Gaussian Support Vector Machines (GSVMs), Multilayer Perceptrons (MLPs), Regression Trees, and Radial Basis Function Networks (RBFNs). Our experiments indicate that GP-based symbolic regression offers accuracy comparable to these benchmark methodologies. Moreover, the resultant analytical model offers invaluable insights into credit risk evaluation mechanisms, enabling stakeholders to make informed credit risk assessments. This study contributes to the growing demand for transparent machine learning models by demonstrating the value of interpretable, data-driven credit scoring models.

Exploring blood-brain barrier passage using atomic weighted vector and machine learning.

This study investigates the potential of leveraging molecular properties, as determined by MD-LOVIs software and machine learning techniques, to predict the ability of compounds to cross the blood-brain barrier (BBB). Accurate prediction of BBB permeation is critical for the development of central nervous system (CNS) drugs. The study applies various machine learning models, including both classification and regression techniques, to predict BBB passage and molecular activity. Notably, classification models such as GBM-AWV (accuracy = 0.801), GLM-CN (accuracy = 0.808), SVMPoly-means (accuracy = 0.980), SVMPoly-AC (accuracy = 0.980), SVMPoly-MI_TI_SI (accuracy = 0.900), SVMPoly-GI (accuracy = 0.900), RF-means (accuracy = 0.870), and GLM-means (accuracy = 0.818) demonstrate high accuracy in predicting BBB passage. In contrast, regression models like ES-RLM-AG (R2 = 0.902), IB-IBK (R2 = 0.82), IB-Kstar (R2 = 0.834), IB-MLP (R2 = 0.843), and DRF-AWV (R2 = 0.810) exhibit strong performance in predicting molecular activity. The results show that classification models like GBM-AWV, GLM-CN, and SVMPoly variants, as well as regression models like ES-RLM-AG and IB-MLP, achieve high performance, demonstrating the effectiveness of machine learning in predicting BBB permeability. The computational methods employed in this study include the MD-LOVIs software for generating molecular descriptors and several machine learning algorithms, including gradient boosting machines (GBM), generalized linear models (GLM), support vector machines (SVM) with polynomial kernels, random forests (RF), ensemble regression models, and instance-based learning algorithms. These models were trained and validated using various datasets to predict BBB passage and molecular activity, with the performance metrics reported for each model. Standard computational techniques were employed throughout, ensuring the reliability of the predictions.

Predicting the Energy Spectra of Solar Energetic Particles with a Machine Learning Regression Algorithm

Solar energetic particles (SEPs) are a major source of space radiation, especially within the inner heliosphere. These particles, originating from solar flares and coronal mass ejections (CMEs), propagate primarily along interplanetary magnetic fields. The energy spectra of SEP events are crucial for assessing radiation effects and understanding the acceleration and propagation mechanisms in their source regions. In this study, we employed a decision tree regression algorithm with cost complexity pruning to predict SEP energy spectra, including peak flux and integral fluence spectra. This approach uses only solar flares, CMEs, and solar wind data as input parameters and demonstrates strong performance to accurately predict SEP spectra. This method holds significant real-time application value for monitoring and forecasting radiation risks in both deep space and near-Earth environments.

Transferring spectroscopic stellar labels to 217 million Gaia DR3 XP stars with SHBoost

With Gaia Data Release 3 (DR3), new and improved astrometric, photometric, and spectroscopic measurements for 1.8 billion stars have become available. Alongside this wealth of new data, however, there are challenges in finding efficient and accurate computational methods for their analysis. In this paper, we explore the feasibility of using machine learning regression as a method of extracting basic stellar parameters and line-of-sight extinctions from spectro-photometric data. To this end, we built a stable gradient-boosted random-forest regressor (xgboost), trained on spectroscopic data, capable of producing output parameters with reliable uncertainties from Gaia DR3 data (most notably the low-resolution XP spectra), without ground-based spectroscopic observations. Using Shapley additive explanations, we interpret how the predictions for each star are influenced by each data feature. For the training and testing of the network, we used high-quality parameters obtained from the StarHorse code for a sample of around eight million stars observed by major spectroscopic stellar surveys, complemented by curated samples of hot stars, very metal-poor stars, white dwarfs, and hot sub-dwarfs. The training data cover the whole sky, all Galactic components, and almost the full magnitude range of the Gaia DR3 XP sample of more than 217 million objects that also have reported parallaxes. We have achieved median uncertainties of 0.20 mag in V-band extinction, 0.01 dex in logarithmic effective temperature, 0.20 dex in surface gravity, 0.18 dex in metallicity, and 12% in mass (over the full Gaia DR3 XP sample, with considerable variations in precision as a function of magnitude and stellar type). We succeeded in predicting competitive results based on Gaia DR3 XP spectra compared to classical isochrone or spectral-energy distribution fitting methods we employed in earlier works, especially for parameters AV and Teff, along with the metallicity values. Finally, we showcase some potential applications of this new catalogue, including extinction maps, metallicity trends in the Milky Way, and extended maps of young massive stars, metal-poor stars, and metal-rich stars.

Applying Machine Learning to Elucidate Ultrafast Demagnetization Dynamics in Ni and Ni80Fe20

Understanding the correlation between fast and ultrafast demagnetization (UFD) processes is crucial for elucidating the microscopic mechanisms underlying UFD, which is pivotal for various applications in spintronics. Initial theoretical models attempt to establish this correlation but face challenges due to the complex interplay of physical phenomena. To address this, a variety of machine learning (ML) methods are employed, including supervised learning regression algorithms and symbolic regression (SR), to analyze limited experimental data and derive meaningful mathematical expressions between demagnetization time (τM) and the Gilbert damping factor (α). The results reveal that polynomial regression and K‐nearest neighbors algorithms perform best in predicting τM. Additionally, variable‐selection sure‐independence‐screening‐and‐sparsifying‐operator (VS‐SISSO) as a SR method suggests a direct correlation between τM and α for Ni and Ni80Fe20, indicating spin‐flip scattering predominantly influences the UFD mechanism. The developed models demonstrate promising predictive capabilities, validated against independent experimental data. Comparative analysis between different materials underscores the significant impact of material properties on UFD behavior. This study underscores the potential of ML in unraveling complex physical phenomena and offers valuable insights for future research in ultrafast magnetism.

Machine learning-assisted DFT-prediction of pristine and endohedral doped (O and Se) Ge12C12 and Si12C12 nanostructures as anode materials for lithium-ion batteries

Nanostructured materials have gained significant attention as anode material in rechargeable lithium-ion batteries due to their large surface-to-volume ratio and efficient lithium-ion intercalation. Herein, we systematically investigated the electronic and electrochemical performance of pristine and endohedral doped (O and Se) Ge12C12 and Si12C12 nanocages as a prospective negative electrode for lithium-ion batteries using high-level density functional theory at the DFT/B3LYP-GD3(BJ)/6-311 + G(d, p)/GEN/LanL2DZ level of theory. Key findings from frontier molecular orbital (FMO) and density of states (DOS) revealed that endohedral doping of the studied nanocages with O and Se tremendously enhances their electrical conductivity. Furthermore, the pristine Si12C12 nanocage brilliantly exhibited the highest Vcell (1.49 V) and theoretical capacity (668.42 mAh g− 1) among the investigated nanocages and, hence, the most suitable negative electrode material for lithium-ion batteries. Moreover, we utilized four machine learning regression algorithms, namely, Linear, Lasso, Ridge, and ElasticNet regression, to predict the Vcell of the nanocages obtained from DFT simulation, achieving R2 scores close to 1 (R2 = 0.99) and lower RMSE values (RMSE < 0.05). Among the regression algorithms, Lasso regression demonstrated the best performance in predicting the Vcell of the nanocages, owing to its L1 regularization technique.

A data-driven strategy for phase field nucleation modeling

We propose a data-driven strategy for parameter selection in phase field nucleation models using machine learning and apply it to oxide nucleation in Fe-Cr alloys. A grand potential-based phase field model, incorporating Langevin noise, is employed to simulate oxide nucleation and benchmarked against the Johnson-Mehl-Avrami-Kolmogorov model. Three independent parameters in the phase field simulations (Langevin noise strength, numerical grid discretization and critical nucleation radius) are identified as essential for accurately modeling the nucleation behavior. These parameters serve as input features for machine learning classification and regression models. The classification model categorizes nucleation behavior into three nucleation density regimes, preventing invalid nucleation attempts in simulations, while the regression model estimates the appropriate Langevin noise strength, significantly reducing the need for time-consuming trial-and-error simulations. This data-driven approach improves the efficiency of parameter selection in phase field models and provides a generalizable method for simulating nucleation-driven microstructural evolution processes in various materials.

Social Media Insight: Predicting Self-Harm Trends

Poisoning or injuring oneself can cause death or injury without intent. This is self-harm. Self-harm harms the perpetrators and the nation's economy. Studies have linked increased urbanization in emerging nations to rising self-harm and new technology. National self-harm patterns may be important for policymakers and public health experts to predict. This would allow them to immediately fix issues or avoid disasters. Studies have forecasted population-level self-harm patterns in many nations using simple statistics. In certain nations, prior data may be scarce or insufficient to make reliable projections. This makes it tougher to FAST assess and anticipate national self-harm. This essay proposes FAST, a technique that uses mental indicators from social media to forecast national self-harm trends. These markers can represent community mental health and help forecast self-harm patterns. Language-agnostic algorithms are taught to first identify mental indicators in gathered social media communications. These signals form multivariate time series. The time-delay embedding method then places these events in time. Last, many machine learning regressors are tried for future prediction. Tweets with 12 mental indicators may predict self-harm-related fatalities and injuries, according to a Thailand research. The suggested method predicted self-harm deaths and injuries. Better than ARIMA baseline by 43.56% and 36.48%. We think our research is the first to predict national self-harm trends using social media data. The findings improve self-harm prediction and establish the framework for new social network-based apps that forecast socioeconomic aspects. We used the top machine learning algorithms, Decision Tree and Voting Regressor. We found less MAE mistakes with these techniques.

QSAR Regression Models for Predicting HMG-CoA Reductase Inhibition

Background/Objectives: HMG-CoA reductase is an enzyme that regulates the initial stage of cholesterol synthesis, and its inhibitors are widely used in the treatment of cardiovascular diseases. Methods: We have created a set of quantitative structure-activity relationship (QSAR) models for human HMG-CoA reductase inhibitors using nested cross-validation as the primary validation method. To develop the QSAR models, we employed various machine learning regression algorithms, feature selection methods, and fingerprints or descriptor datasets. Results: We built and evaluated a total of 300 models, selecting 21 that demonstrated good performance (coefficient of determination, R2 ≥ 0.70 or concordance correlation coefficient, CCC ≥ 0.85). Six of these top-performing models met both performance criteria and were used to construct five ensemble models. We identified the descriptors most important in explaining HMG-CoA inhibition for each of the six best-performing models. We used the top models to search through over 220,000 chemical compounds from a large database (ZINC 15) for potential new inhibitors. Only a small fraction (237 out of approximately 220,000 compounds) had reliable predictions with mean pIC50 values ≥ 8 (IC50 values ≤ 10 nM). Our svm-based ensemble model predicted IC50 values &lt; 10 nM for roughly 0.08% of the screened compounds. We have also illustrated the potential applications of these QSAR models in understanding the cholesterol-lowering activities of herbal extracts, such as those reported for an extract prepared from the Iris × germanica rhizome. Conclusions: Our QSAR models can accurately predict human HMG-CoA reductase inhibitors, having the potential to accelerate the discovery of novel cholesterol-lowering agents and may also be applied to understand the mechanisms underlying the reported cholesterol-lowering activities of herbal extracts.

Robust approximation of the conditional mean for applications of Machine Learning

Machine Learning approaches are increasingly used in a range of applications. They are shown to produce low conventional errors but in many real applications fail to model the underlying input–output relationships. This is because the error measures used only predict the conditional mean under some restrictive assumptions, often not met by the data we extract from applications. However, new approaches to Machine Learning, for example using Evolutionary Computation, allow a range of alternative error measures to be used. This paper explores the use of the Fit to Median Error measure in machine learning regression automation, using evolutionary computation in order to improve the approximation of the ground truth. When used alongside conventional error measures it improves the robustness of the learnt input–output relationships to the conditional median. It is compared to traditional regularisers to illustrate that the use of the Fit to Median Error produces regression neural networks which model more consistent input–output relationships. The problem considered is ship power prediction using a fuel-saving air lubrication system, which is highly stochastic in nature. The networks optimised for their Fit to Median Error are shown to approximate the ground truth more consistently, without sacrificing conventional Minkowski-r error values.

Fuzzy-based ensemble methodology for accurate long-term prediction and interpretation of extreme significant wave height events

Providing an accurate prediction of Significant Wave Height (SWH), and specially of extreme SWH events, is crucial for coastal engineering activities and holds major implications in several sectors as offshore renewable energy. With the aim of overcoming the challenge of skewness and imbalance associated with the prediction of these extreme SWH events, a fuzzy-based cascade ensemble of regression models is proposed. This methodology allows to remarkably improve the predictive performance on the extreme SWH values, by using different models specialised in different ranges on the target domain. The method’s explainability is enhanced by analysing the contribution of each model, aiding in identifying those predictor variables more characteristic for the detection of extreme SWH events. The methodology has been validated tackling a long-term SWH prediction problem, considering two case studies over the southwest coast of the United States of America. Both reanalysis data, providing information on various meteorological factors, and SWH measurements, obtained from the nearby stations and the station under examination, have been considered. The goodness of the proposed approach has been validated by comparing its performance against several machine learning and deep learning regression techniques, leading to the conclusion that fuzzy ensemble models perform much better in the prediction of extreme events, at the cost of a slight deterioration in the rest of the samples. The study contributes to advancing the SWH prediction field, specially, to understanding the behaviour behind extreme SWH events, critical for various sectors reliant on oceanic conditions.

Estimation of the soluble solid content of citrus based on the fractional-order derivative and optimal band combination algorithm.

The soluble solid content (SSC) is a primary characteristic index for evaluating the internal quality of citrus fruits. The development of rapid and nondestructive SSC detection techniques can help address the current issues of postharvest quality grading in China's citrus industry. In this study, a total of 261 experimental samples, including 70 Murcott, 91 Clementine, and 100 Navel orange, were divided into prediction and validation sets in a 7:3 ratio. After obtaining the reflection spectra and SSCs, SNV-FOD (Standard Normal Variate-Fractional-Order Derivative) was used to process the spectra, and the optimal band combination algorithm was introduced to select SSC-sensitive bands. Then, the obtained optimal dual-band combination was input into eight regression models for comparison, and the best performing models stacked ensemble models was selected. Finally, the H-ELR (HyperOpt-optimized ensemble learning regression) model, optimized using a Bayesian function, was applied for the effective estimation of SSC for three common citrus varieties in Guangxi, Murcott, Clementine, and Navel oranges. The results show that (1) the SNV-FOD preprocessing method proposed in this study improved the correlation coefficient with the SSC from 0.546 to 0.836 compared to that of the original spectrum, (2) the optimal dual-band combination (969 and 1069nm) constructed by integrating the differential index and 1.2-order derivative yielded the most accurate results (RPD=2.13), and (3) the H-ELR model, based on HyperOpt optimization, achieved good estimated performance (RPD=2.46). PRACTICAL APPLICATION: This research contributes to the development of practical SSC prediction instruments with excellent universality and ease of application.

Integrated Machine Learning and Region Growing Algorithms for Enhanced Concrete Crack Detection: A Novel Approach

In the field of construction engineering, the cracking of concrete structures is a common engineering problem, which has a great impact on the overall stability and service life of the engineered structure. During structural repair, crack detection is the most critical step. Automatic detection significantly reduces the engineering cost and human factor error compared with manual detection. However, due to the changeable environment of the project site and different image specifications, using a single algorithm makes it difficult to balance high efficiency and high accuracy. In this study, we designed a combined recognition method including the region growth algorithm and machine learning regression that can achieve a tradeoff between accuracy and efficiency. Firstly, the regression method learns the image features of the dataset and the specific region growth threshold, and the regression function is trained by using the open-source dataset to determine the region growth threshold using the characteristics of the images included in the tests. The region growth algorithm is used to expand the threshold from the seed points of the image to obtain the crack recognition results. The results show that this method improves the accuracy of SSIM by 7% compared with the traditional region growth algorithm, and does not significantly increase the computational cost, with an increase of 0.78 s per photo process. Compared with the deep learning method, the recognition accuracy of SSIM is decreased by 5.96%, but it takes less resources and has high efficiency.

Predictive Modeling of the Hydrate Formation Temperature in Highly Pressurized Natural Gas Pipelines

In this study, we aim to develop advanced machine learning regression models for the prediction of hydrate temperature based on the chemical composition of sweet gas mixtures. Data were collected in accordance with the BOTAS Gas Network Code specifications, approved by the Turkish Energy Market Regulatory Authority (EMRA), and generated using DNV GasVLe v3.10 software, which predicts the phase behavior and properties of hydrocarbon-based mixtures under various pressure and temperature conditions. We employed linear regression, decision tree regression, random forest regression, generalized additive models, and artificial neural networks to create prediction models for hydrate formation temperature (HFT). The performance of these models was evaluated using the hold-out cross-validation technique to ensure unbiased results. This study demonstrates the efficacy of ensemble learning methods, particularly random forest with an R2 and Adj. R2 of 0.998, for predicting hydrate formation conditions, thereby enhancing the safety and efficiency of gas transport and processing. This research illustrates the potential of machine learning techniques in advancing the predictive accuracy for hydrate formations in natural gas pipelines and suggests avenues for future optimizations through hybrid modeling approaches.

Predicting the Energetic Proton Flux with a Machine Learning Regression Algorithm

The need for real-time monitoring and alerting systems for space weather hazards has grown significantly in the last two decades. One of the most important challenges for space mission operations and planning is the prediction of solar proton events (SPEs). In this context, artificial intelligence and machine learning techniques have opened a new frontier, providing a new paradigm for statistical forecasting algorithms. The great majority of these models aim to predict the occurrence of an SPE, i.e., they are based on the classification approach. This work is oriented toward the successful implementation of onboard prediction systems, which is essential for the future of space exploration. We present a simple and efficient machine learning regression algorithm that is able to forecast the energetic proton flux up to 1 hr ahead by exploiting features derived from the electron flux only. This approach could be helpful in improving monitoring systems of the radiation risk in both deep space and near-Earth environments. The model is very relevant for mission operations and planning, especially when flare characteristics and source location are not available in real time, as at Mars distance.