Search

The Journal of Chemical Physics has released a special issue focused on software for atomistic machine learning. This issue aims to address the lack of journals dedicated to publishing scientific software papers. The collection of papers in this issue provides insight into the tools and goals of software implementations in the field of atomistic machine learning. The articles cover a range of topics, including machine-learning interatomic potentials, sampling, dataset repositories, workflows, and auxiliary tooling and analysis. The article concludes by emphasizing the importance of software implementations in the field and encourages further submissions on relevant topics. [Extracted from the article]

Data generation remains a bottleneck in training surrogate models to predict molecular properties. We demonstrate that multitask Gaussian process regression overcomes this limitation by leveraging both expensive and cheap data sources. In particular, we consider training sets constructed from coupled-cluster (CC) and density functional theory (DFT) data. We report that multitask surrogates can predict at CC-level accuracy with a reduction in data generation cost by over an order of magnitude. Of note, our approach allows the training set to include DFT data generated by a heterogeneous mix of exchange–correlation functionals without imposing any artificial hierarchy on functional accuracy. More generally, the multitask framework can accommodate a wider range of training set structures—including the full disparity between the different levels of fidelity—than existing kernel approaches based on Δ-learning although we show that the accuracy of the two approaches can be similar. Consequently, multitask regression can be a tool for reducing data generation costs even further by opportunistically exploiting existing data sources. [ABSTRACT FROM AUTHOR]

We investigate the endofullerene system 3He@C60 with a four-dimensional potential energy surface (PES) to include the three He translational degrees of freedom and C60 cage radius. We compare second order Møller–Plesset perturbation theory (MP2), spin component scaled-MP2, scaled opposite spin-MP2, random phase approximation (RPA)@Perdew, Burke, and Ernzerhof (PBE), and corrected Hartree–Fock-RPA to calibrate and gain confidence in the choice of electronic structure method. Due to the high cost of these calculations, the PES is interpolated using Gaussian Process Regression (GPR), owing to its effectiveness with sparse training data. The PES is split into a two-dimensional radial surface, to which corrections are applied to achieve an overall four-dimensional surface. The nuclear Hamiltonian is diagonalized to generate the in-cage translational/vibrational eigenstates. The degeneracy of the three-dimensional harmonic oscillator energies with principal quantum number n is lifted due to the anharmonicity in the radial potential. The (2l + 1)-fold degeneracy of the angular momentum states is also weakly lifted, due to the angular dependence in the potential. We calculate the fundamental frequency to range between 96 and 110 cm−1 depending on the electronic structure method used. Error bars of the eigenstate energies were calculated from the GPR and are on the order of ∼±1.5 cm−1. Wavefunctions are also compared by considering their overlap and Hellinger distance to the one-dimensional empirical potential. As with the energies, the two ab initio methods MP2 and RPA@PBE show the best agreement. While MP2 has better agreement than RPA@PBE, due to its higher computational efficiency and comparable performance, we recommend RPA as an alternative electronic structure method of choice to MP2 for these systems. [ABSTRACT FROM AUTHOR]

A merged potential energy surface (PES) is introduced for CO + CO collisions by combining a recent full-dimensional ab initio PES [Chen et al. J. Chem. Phys. 153, 054310 (2020)] and analytical long-range multipolar interactions. This merged PES offers a double advantage: it retains the precision of the ab initio PES in describing the van der Waals well and repulsive short range while providing an accurate physical description of long-range interaction; it significantly reduces the computational time required for trajectory integration since the long-range portion of the ab initio PES (involving numerous neural network fitting parameters) is now replaced by the analytical model potential. Based on the present merged PES, mixed Quantum-Classical (MQC) calculations, which capture quantum effects related to vibrational motion, align with a range of experimental data, including transport properties, vibrational energy transfer between CO and its isotoplogues, as well as rate coefficients for V–V and V–T/R processes. Notably, the original ab initio PES yields V–T/R rate coefficients at low temperatures that are significantly higher than the experimental data due to the artificial contribution of its unphysical long-range potential. In addition to conducting extensive MQC calculations to obtain raw data for V–V and V–T/R rate coefficients, we employ Gaussian process regression to predict processes lacking computed MQC data, thereby completing the considered V–V and V–T/R datasets. These extensive rate coefficient datasets, particularly for V–T/R processes, are unprecedented and reveal the significant role played by V–T/R processes at high temperatures, emphasizing the necessity of incorporating both V–V and V–T/R processes in the applications. [ABSTRACT FROM AUTHOR]

Kernel methods such as kernel ridge regression and Gaussian process regression with Matern-type kernels have been increasingly used, in particular, to fit potential energy surfaces (PES) and density functionals, and for materials informatics. When the dimensionality of the feature space is high, these methods are used with necessarily sparse data. In this regime, the optimal length parameter of a Matern-type kernel may become so large that the method effectively degenerates into a low-order polynomial regression and, therefore, loses any advantage over such regression. This is demonstrated theoretically as well as numerically in the examples of six- and fifteen-dimensional molecular PES using squared exponential and simple exponential kernels. The results shed additional light on the success of polynomial approximations such as PIP for medium-size molecules and on the importance of orders-of-coupling-based models for preserving the advantages of kernel methods with Matern-type kernels of on the use of physically motivated (reproducing) kernels. [ABSTRACT FROM AUTHOR]

Machine learning (ML) of kinetic energy functionals (KEFs), in particular kinetic energy density (KED) functionals, is a promising way to construct KEFs for orbital-free density functional theory (DFT). Neural networks and kernel methods including Gaussian process regression (GPR) have been used to learn Kohn–Sham (KS) KED from density-based descriptors derived from KS DFT calculations. The descriptors are typically expressed as functions of different powers and derivatives of the electron density. This can generate large and extremely unevenly distributed datasets, which complicates effective application of ML techniques. Very uneven data distributions require many training datapoints, can cause overfitting, and can ultimately lower the quality of an ML KED model. We show that one can produce more accurate ML models from fewer data by working with smoothed density-dependent variables and KED. Smoothing palliates the issue of very uneven data distributions and associated difficulties of sampling while retaining enough spatial structure necessary for working within the paradigm of KEDF. We use GPR as a function of smoothed terms of the fourth order gradient expansion and KS effective potential and obtain accurate and stable (with respect to different random choices of training points) kinetic energy models for Al, Mg, and Si simultaneously from as few as 2000 samples (about 0.3% of the total KS DFT data). In particular, accuracies on the order of 1% in a measure of the quality of energy–volume dependence B ′ = E V 0 − Δ V − 2 E V 0 + E ( V 0 + Δ V) Δ V / V 0 2 (where V0 is the equilibrium volume and ΔV is a deviation from it) are obtained simultaneously for all three materials. [ABSTRACT FROM AUTHOR]

We report on the detailed characterization of K2-370 b, a transiting sub-Neptune on a 2.14-d orbit around the chromospherically active G-type dwarf HD 284521 (⁠|$T_\mathrm{eff} = 5662\pm 44$|  K, |$\lt \log R^\prime _{\rm HK}\gt =-4.49$|⁠). The system parameters are derived based on a global fit to K2, TESS and CHEOPS photometry, and HARPS-N and HARPS radial velocities (RVs). A Gaussian process regression analysis is performed simultaneously to the orbital fit of the RVs of K2-370 to effectively model the strong stellar rotation signal with a period of |$13.5\pm 0.05$|  d and measure the planetary RV signal with semi-amplitude |$K_{\rm b}=5.6\pm 0.7$|  m s |$^{-1}$|⁠. We find that K2-370 b has a radius of |$2.67\pm 0.05$|   |${\rm R}_{\rm{\oplus }}$| and a mass of |$11.1\pm 1.4$|   |${\rm M}_{\rm{\oplus }}$|⁠. With an estimated equilibrium temperature |$T_\mathrm{eq}\sim 1480$| K, K2-370 b is the second-hottest sub-Neptune with a highly precise mass determination around primaries with |$T_\mathrm{eff}\gt 5500$|  K. The resulting density of |$3.2\pm 0.4$|  g cm |$^{-3}$| implies that K2-370 b either retains a significant (⁠|$\sim 2~{{\ \rm per\ cent}}$| by mass) H-rich atmosphere or its interior contains a high (⁠|$\sim 40~{{\ \rm per\ cent}}$|⁠) water–mass fraction. [ABSTRACT FROM AUTHOR]

Single-crystal sapphire (α-Al2O3) has a wide range of applications in a variety of extreme environments due to its excellent mechanical and chemical properties as well as its stability under extreme service conditions. In addition, sapphire is a hard and brittle material, which makes it difficult to avoid the introduction of subsurface damage during processing, and the existence of a subsurface damage layer seriously affects the performance of the optical system. Therefore, this study focuses on the mechanism of subsurface damage in sapphire grinding, the suppression of damage depth, and the accurate and fast prediction of damage depth. A subsurface damage model for ultrasonic vibration–assisted grinding of sapphire was established by combining ultrasonic vibration single abrasive grain kinematics and dynamics analysis. The mechanism of ultrasonic vibration–assisted grinding was investigated by combining force and acoustic emission (AE) signals. And the effects of ultrasonic vibration–assisted grinding on the surface quality, subsurface damage form, and depth were analyzed. A comprehensive prediction model of SSD based on surface roughness (Sz) was established by combining indentation fracture mechanics and Gaussian process regression. Finally, by analyzing the influence law of each process parameter on the subsurface damage depth (SSD), the grinding process parameters were optimized, and the subsurface damage suppression strategy was proposed. This study provides theoretical guidance for the high-efficiency and low-damage grinding of sapphire. [ABSTRACT FROM AUTHOR]

Projections of commodity prices have long been a significant source of dependence for investors and the government. This study investigates the challenging topic of forecasting the daily regional steel price index in the northeast Chinese market from January 1, 2010, to April 15, 2021. The projection of this significant commodity price indication has not received enough attention in the literature. The forecasting model that is used is Gaussian process regressions, which are trained using a mix of cross-validation and Bayesian optimizations. The models that were built precisely predicted the price indices between January 8, 2019, and April 15, 2021, with an out-of-sample relative root mean square error of 0.5432%. Investors and government officials can use the established models to study pricing and make judgments. Forecasting results can help create comparable commodity price indices when reference data on the price trends suggested by these models are used. [ABSTRACT FROM AUTHOR]

Stillbirth is a devastating and often avoidable adverse pregnancy outcome. Monitoring stillbirth levels and trends—in a comprehensive manner that leaves no one uncounted—is imperative for continuing progress in pregnancy loss reduction. This analysis, completed as part of the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2021, methodically accounted for different stillbirth definitions with the aim of comprehensively estimating all stillbirths at 20 weeks or longer for 204 countries and territories from 1990 to 2021. We extracted data on stillbirths from 11 412 sources across 185 of 204 countries and territories, including 234 surveys, 231 published studies, 1633 vital statistics reports, and 10 585 unique location-year combinations from vital registration systems. Our final dataset comprised 11 different definitions, which were adjusted to match two gestational age thresholds: 20 weeks or longer (reference) and 28 weeks or longer (for comparisons). We modelled the ratio of stillbirth rate to neonatal mortality rate with spatiotemporal Gaussian process regression for each location and year, and then used final GBD 2021 assessments of fertility and all-cause neonatal mortality to calculate total stillbirths. Secondary analyses evaluated the number of stillbirths missed with the more restrictive gestational age definition, trends in stillbirths as a function of Socio-demographic Index, and progress in reducing stillbirths relative to neonatal deaths. In 2021, the global stillbirth rate was 23·0 (95% uncertainty interval [UI] 19·7–27·2) per 1000 births (stillbirths plus livebirths) at 20 weeks' gestation or longer, compared to 16·1 (13·9–19·0) per 1000 births at 28 weeks' gestation or longer. The global neonatal mortality rate in 2021 was 17·1 (14·8–19·9) per 1000 livebirths, corresponding to 2·19 million (1·90–2·55) neonatal deaths. The estimated number of stillbirths occurring at 20 weeks' gestation or longer decreased from 5·08 million (95% UI 4·07–6·35) in 1990 to 3·04 million (2·61–3·62) in 2021, corresponding to a 39·8% (31·8–48·0) reduction, which lagged behind a global improvement in neonatal deaths of 45·6% (36·3–53·1) for the same period (down from 4·03 million [3·86–4·22] neonatal deaths in 1990). Stillbirths in south Asia and sub-Saharan Africa comprised 77·4% (2·35 million of 3·04 million) of the global total, an increase from 60·3% (3·07 million of 5·08 million) in 1990. In 2021, 0·926 million (0·792–1·10) stillbirths, corresponding to 30·5% of the global total (3·04 million), occurred between 20 weeks' gestation and 28 weeks' gestation, with substantial variation at the country level. Despite the gradual global decline in stillbirths between 1990 and 2021, the overall number of stillbirths remains substantially high. Counting all stillbirths is paramount to progress, as nearly a third—close to 1 million in total—are left uncounted at the 28 weeks or longer threshold. Our findings draw attention to the differential progress in reducing stillbirths, with a high burden concentrated in countries with low development status. Scarce data availability and poor data quality constrain our capacity to precisely account for stillbirths in many locations. Addressing inequities in universal maternal health coverage, strengthening the quality of maternal health care, and improving the robustness of data systems are urgently needed to reduce the global burden of stillbirths. Bill & Melinda Gates Foundation. [ABSTRACT FROM AUTHOR]

[Display omitted] • Six machine learning models were used to predict MR and CT. • GPR model demonstrated the best predictive performance. • SHAP and PDP were introduced for model interpretation. • An easy-to-use GUI was developed for the prediction of MR and MC. Preparation of activated carbons is an important way to utilize municipal sludge (MS) resources, while drying is a pretreatment method for making activated carbons from MS. In this study, machine learning techniques were used to develop moisture ratio (MR) and composting temperature (CT) prediction models for the thermally assisted biodrying process of MS. First, six machine learning (ML) models were used to construct the MR and CT prediction models, respectively. Then the hyperparameters of the ML models were optimized using the Bayesian optimization algorithm, and the prediction performances of these models after optimization were compared. Finally, the effect of each input feature on the model was also evaluated using SHapley Additive exPlanations (SHAP) analysis and Partial Dependence Plots (PDPs) analysis. The results showed that Gaussian process regression (GPR) was the best model for predicting MR and CT, with R2 of 0.9967 and 0.9958, respectively, and root mean square errors (RMSE) of 0.0059 and 0.354 ℃. In addition, graphical user interface software was developed to facilitate the use of the GPR model for predicting MR and CT by researchers and engineers. This study contributes to the rapid prediction, improvement, and optimization of MR and CT during thermally assisted biodrying of MS, and also provides valuable guidance for the dynamic regulation of the drying process. [ABSTRACT FROM AUTHOR]

Performing reliability analysis for reinforced concrete structures is a tedious and challenging task because it requires conducting a four-nested loop calculation procedure involving millions of data samples to account for the complex behaviours of the structures and multiple random variables. Therefore, the study proposes a novel, practical, and accurate reliability framework that is applicable for multi-component RC frame structures exhibiting different behaviours ranging from linear elastic and non-linear elastic to non-linear plastic. For this purpose, this study first employs a tree-based boosting ensemble model combined with quantile regression, dubbed as QR-LightGBM to calculate the structures' limit state function and the associated uncertainty estimation at the same time. Next, an active learning process is implemented to improve the computed reliability results progressively. During each active learning step, relevant data samples with potentially high impacts on the model accuracy are determined based on their uncertainty, and then QR-LightGBM is retrained utilizing these samples. By doing so, the prediction performance of the surrogate model is enhanced with a minimized number of actual data samples, thus significantly reducing overall computational resources. The viability and effectiveness of the proposed framework are validated through three case studies involving a simple 1D reinforced concrete beam, a 2D three-story frame, and a 3D five-story building structure. Furthermore, its performance is quantitatively demonstrated via comparison studies with competing methods such as Monte Carlo simulation, Kriging-based models, and an original LightGBM without active learning. [ABSTRACT FROM AUTHOR]

Segregation of granular materials is a critical challenge in many industries, often aimed at being controlled or minimised. The discrete element method (DEM) offers valuable insights into this phenomenon. However, calibrating DEM models is a crucial, albeit time-consuming, step. Recently, using machine learning (ML)-based surrogate models (SMs) in the calibration process has emerged as a promising solution. Nevertheless, developing such SMs is challenging due to the high number of DEM simulations required for training. Additionally, choosing a suitable ML model is not trivial. This study aims to develop SMs that effectively link particle-particle and particle-wall DEM interaction parameters to segregation of a multi-component mixture. We evaluate several ML models, ranging from artificial neural networks to ensemble learning, that are trained on a very cost-effective dataset, employing Bayesian optimisation with cross-validation to tune their hyperparameters. Next, we introduce a novel transfer learning (TL)-based approach that leverages knowledge from a few scenarios to handle new "unseen" ones. This method enables the construction of adaptive SMs for unseen scenarios, such as a new initial configuration (IC) of granular mixtures, without the need for a full-sized dataset. Our findings indicate that Gaussian process regression (GPR) efficiently builds accurate SMs on a very small dataset. We also demonstrate that only a few samples are required to build an accurate SM for the unseen IC, which significantly reduces the data preparation burden. By incorporating one and five samples from unseen scenarios to update the TL-GPR-based surrogate model, the SM's performance (based on ) on unseen scenarios improves by 17 and 47%, respectively. The insights and methodology presented in this study will facilitate and accelerate the development of accurate SMs for DEM calibration, assisting in developing reliable DEM models in a shorter timeframe. [ABSTRACT FROM AUTHOR]

The study proposes an approach to elucidate spatiotemporal mesoscale variations of seawater Dimethylsulfide (DMS) concentrations, the largest natural source of atmospheric sulfur aerosol, based on the Gaussian Process Regression (GPR) machine learning model. Presently, the GPR was trained and evaluated by nested cross-validation across the warm-oligotrophic Mediterranean Sea, a climate hot spot region, leveraging the high-resolution satellite measurements and Mediterranean physical reanalysis together with in-situ DMS observations. The end product is daily gridded fields with a spatial resolution of 0.083° × 0.083° (~9 km) that spans 23 years (1998–2020). Extensive observations of atmospheric methanesulfonic acid (MSA), a typical biogenic secondary aerosol component from DMS oxidation, are consistent with the parameterized high-resolution estimates of sea-to-air DMS flux (FDMS). This represents substantial progress over existing coarse-resolution DMS global maps which do not accurately depict the seasonal patterns of MSA in the Mediterranean atmospheric boundary layer. [ABSTRACT FROM AUTHOR]

To improve the accuracy of photogrammetric joint roughness coefficient (JRC) estimation, this study proposes two optimization models based on ground sample distance (GSD), point density, and the root mean square error (RMSE) of checkpoints. First, an algorithm that automatically generates spatial positions for equipment based on the convergence strategy was developed, using principles of Structure from Motion and Multi-View Stereo (SfM-MVS) and the shooting parameter selection algorithm (SPSA). Second, a portable positioning plate containing ground control points and checkpoints was designed based on optical principles, and a moving camera capture strategy guided by SPSA was proposed. Combining SPSA, portable positioning plate, and moving camera capture strategy, a photogrammetric experiment for small-scale rock samples in the field was conducted, collecting 48 datasets with different shooting parameters. Subsequently, a dataset incorporating GSD, point density, RMSE, and three JRC estimation metrics was established, revealing their correlations and sensitivities. Using seven machine learning algorithms, optimization models for photogrammetric JRC accuracy were developed, with Linear Multidimensional Regression and Gaussian Process Regression models improving JRC accuracy by an average of 85.73%. Finally, the applicability and limitations of the newly proposed method were further discussed. [ABSTRACT FROM AUTHOR]

Bayesian Optimization (BO) is a popular approach to solve optimization problems using as few function evaluations as possible. In particular, Efficient Global Optimization (EGO) based on Kriging surrogate models has been successfully applied to many real-world applications in low dimensions (less than 30 design parameters). However, in high dimension, building an accurate Kriging model is difficult, especially when the number of samples is limited as is the case when dealing with numerical simulators. This is due to the inner optimization of the Kriging length-scale hyperparameters which can lead to inaccurate models and impacts the performances of the optimization. In this paper, we introduce a new method for high-dimensional BO which bypasses the length-scales optimization by combining sub-models with random length-scales, and whose expression, obtained in closed-form, avoids any inner optimization. We also describe how to sample suitable length-scales for the sub-models using an entropy-based criterion, in order to avoid degenerated sub-models having either too large or too small length-scales. Finally, the variance of the combination being not directly available, we present a method to compute the prediction variance for any weighting method. We apply our combined Kriging model to high-dimensional BO for analytical test functions and for the design of an electric machine. We show that our method builds more accurate surrogate models than ordinary Kriging when the number of samples is small. This results in faster convergence for BO using the combination. [ABSTRACT FROM AUTHOR]

Existing methods for small-area data involve a trade-off between maintaining area-level frequentist coverage rates and improving precision via the incorporation of indirect information. In this article, we develop an area-level prediction region procedure that mitigates this trade-off. The method takes a conformal prediction approach in which the conformity measure is the posterior predictive density of a working model that incorporates indirect information. The resulting prediction region has guaranteed within-area frequentist coverage regardless of the working model, and, if the working model assumptions are accurate, the region has smaller expected volume compared to other regions with the same coverage rate. For a normal working model, we prove such a prediction region is an interval and construct a straightforward algorithm to obtain its endpoints. We illustrate the performance of our method through simulation studies and an application to EPA radon survey data. [ABSTRACT FROM AUTHOR]

Autonomous navigation is critical to the development of next-generation shipping systems. The proposal of intelligent ships enables innovation in the shipping and shipbuilding industry and increases the safety and efficiency of ship operations. Autonomous control of surface ships to follow a prescribed trajectory is critical in a variety of maritime applications. This paper proposes a trajectory tracking control strategy for autonomous surface ships that combines nonparametric modelling using Gaussian Process Regression (GPR) with the Model Predictive Control (MPC) framework. A Bézier curve-based Virtual Ship(BVS) guidance strategy is proposed to convert dynamic trajectory points into reference heading angles and speeds, such that the trajectory tracking problem can be decomposed into heading control and speed control problems. Gaussian process regression is utilised to identify the correlation between propeller revolution speed and ship speed, as well as the correlation between rudder angle and heading angle based on experimental data. Two GPR models are therefore constructed as the prediction models for designing MPC controllers for heading control and speed control, respectively. Nonlinear optimisation algorithms are utilised to search for optimal control commands in each sampling interval to solve the optimisation problem in MPC with GPR models and input constraints. Simulations are carried out to evaluate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Power characteristics are important indicators of fuel cell performance. In the actual operation of fuel cells, changes in operating conditions lead to variations in their power characteristics. Therefore, it is imperative to explore the impact of operating conditions on power characteristics. This paper analyzes the factors influencing fuel cell power and uses sensitivity analysis to investigate how different factors affect fuel cell performance. The operating parameters are optimized using a Bayesian-optimized Gaussian process regression model. The research results indicate that temperature has the greatest impact on fuel cell power, followed by stoichiometry and backpressure. The Bayesian-optimized Gaussian process regression model performs the best, reducing its RSME from 0.1 to 0.0556. Residual analysis and regression characteristic analysis verify the optimized model's improved fitting and regression characteristics. Based on the Bayesian–Gaussian process regression model, the optimized operating parameters are obtained for maximum power: a temperature of 80 °C, stoichiometry of 4, and backpressure of 1.7 bar. This paper provides theoretical support for improving fuel cell performance. [ABSTRACT FROM AUTHOR]

Air data inertial reference system (ADIRS) parameters are very important for the safe flight of an aircraft. The ADIRS consists of air data inertial reference units (ADIRUs) and the air data reference (ADR) part of the ADIRU, which provides the air data [altitude (ALT), angle of attack (AOA), airspeed, and temperature information] examined in this study. ADR is essential to continuously ensure accurate and precise information to the flight management guidance computers (FMGCs), electronic flight instruments system (EFIS), and other systems on the aircraft for reliable and safe flight operation. This study estimated the ADR parameters (altitude, angle of attack, airspeed, and temperature) to obtain a synthetic air data system for data continuity in the event of any sensor failure on the aircraft using correlated data. According to correlation analysis, the angle of attack, computed airspeed (CAS), and static air temperature (SAT) data have the highest correlation with the stabilizer position (STAB), whereas the altitude data have the highest correlation with the low-pressure engine spool rotational speed (N1). The AOA, CAS, SAT, and ALT parameters were estimated by decision tree, support vector machine, and Gaussian process regression models using real flight data collected from a local airline. The Gaussian process regression model was better at generalizing the data set for data estimation than were the other machine learning methods used in this study. MATLAB version R2023a software was used in all operations. [ABSTRACT FROM AUTHOR]

The conventional manual design process and data acquisition for aerodynamic parameters can be time-consuming. Consequently, this study proposes a solution to address this issue. The main contributions of this study are as follows. (1) A surrogate model based on ensemble learning (Ensemble) is proposed, which utilizes a two-layer learner combining the Cokriging model (Cokriging) with the neural network model based on transfer learning (TL). A numerical example is conducted to evaluate its performance, comparing it with single-surrogate methods. (2) A criterion—the mp-cvvor hybrid sampling strategy—is proposed for application to any surrogate model. The efficiency of the mp-cvvor method compared to that of other sampling strategies is validated by a synthetic benchmark. (3) The aerodynamic optimization framework is applied to the RAE2822 airfoil. Our method reduces average computation fluid dynamics (CFD) calls by more than 48.2% than do the nondominated sorting genetic algorithm-II (NSGA-II) and particle swarm optimization (PSO), and the lift-drag ratio increases by 3.087% compared to the increase from the single-surrogate-based Cokriging approach. [ABSTRACT FROM AUTHOR]

Lightweight cellular structures are investigated intensively in additive manufacturing and require optimization strategies to distribute both patterns, cross-sections sizes and type, and even materials. There exist several parametric optimization techniques that permit not only obtaining lightweight structures but also ensuring maintaining the rigidity. Among these techniques, design of experiments is time-consuming, and the values of the optimal parameters are estimated based on their possible range rather than being determined precisely. An original scientific strategy is to use the Kriging swarm optimization technique to achieve the global optimum using a minimal amount of computer simulations. Therefore, the objective of this paper is to determine the optimal cross-sections of structures using bio-inspired "L-systems". These L-systems-based structures were created and distributed along the directions of the principal stress lines (PSLs), then mimicking material growth and distribution inside biological structures. Two PSLs directions were separately investigated for each load case; the first direction is used as a guide for the growth of L-systems and the second one serves for branch extensions and limitations. To do so, a metamodel is used upon particle swarm optimization technique (PSO) and several case studies are conducted to improve the stiffness-to-weight ratio while respecting the additive manufacturability. [ABSTRACT FROM AUTHOR]

This study addresses the estimation of material properties at a mesoscopic level using the PuMA software from an uncertainty quantification perspective. Stochastic simulation with PuMA is primarily related to the random distribution of fibers, which is an intrinsic source of uncertainty. Additionally, the selection of certain physical parameters, such as the fiber's thermal conductivity, introduces further uncertainties. The first contribution of this study is to propose a low-cost surrogate-based methodology with an unequal allocation scheme, applied for the first time to the stochastic mesoscale characterization of ablative materials. The second contribution is a study on uncertainty propagation and sensitivity analysis of material properties, providing a systematic assessment of the choice of voxel resolution for both the fibers and the domain. Specifically, the convergence of quantities of interest can be monitored, thus identifying the minimal reference elementary volume. • Building surrogate to compute statistics of material properties of a stochastic solver. • First-ever assessment of material properties at mesoscopic level using PuMA under Uncertainty Quantification. • Assessment of the choice of the voxel resolution surveying convergence, identifying minimal reference elementary volume. • Thermal conductivity variance explained by uncertainty on porosity for in-plane conductivity. [ABSTRACT FROM AUTHOR]

Safety life analysis can provide guidance for safety service and maintenance plan of structure. To efficiently analyze the structural safety life under required failure possibility in the presence of fuzzy uncertainty, this paper proposes a sequential Kriging (SK)-based fuzzy simulation (FS) combined with dichotomy (SK-FS-D) method. Firstly, based on monotonic relationship of time-dependent failure possibility (TDFP) and service time, the SK-FS-D uses dichotomy method to search the safety life. Secondly, the SK-FS-D proposes a strategy of sequentially updating Kriging surrogate model in the candidate sample pool (CSP) of fuzzy simulation (FS) to estimate the TDFP corresponding to each possible life searched by dichotomy, and the next dichotomy interval is determined by TDFP estimated by the convergent Kriging model. This strategy can improve the efficiency of SK-FS-D by avoiding training Kriging model at the life not visited by dichotomy and extend the engineering applicability of SK-FS-D by inheriting the advantages of FS method. Moreover, the CSP reduction strategy is further adopted to improve the computational efficiency of TDFP according to some correct information provided by the convergent Kriging model and the property of fuzzy design point. Finally, one numerical example and three engineering examples are introduced to verify the superior performance of the proposed SK-FS-D over the existing methods. [ABSTRACT FROM AUTHOR]

To improve the efficiency of the double-loop fuzzy simulation (DLFS) for estimating the time-dependent failure possibility (TDFP), a single-loop fuzzy simulation (SLFS) is proposed in this paper. In the SLFS, an equivalent transformation formula of TDFP is put forward for the first time, then the estimation of TDFP is transformed into a single-loop fuzzy simulation procedure where the fuzzy inputs and time parameter are sampled in the same level. As only single-loop sampling is needed in the SLFS, the computational complexity and cost of the proposed method are both reduced compared to the DLFS. Subsequently, a single-loop Kriging model based SLFS (ASLK-SLFS) is developed to enhance the performance of the SLFS. Based on the candidate sampling pool of SLFS to sample the fuzzy inputs and the time parameter in the same level, a single Kriging can be more efficiently constructed and updated. To further improve the efficiency of ASLK-SLFS, an improved version is then developed by using a candidate sampling pool reduction strategy. Finally, three examples are employed to illustrate the advantages of the proposed methods. Through the proposed ASLK-SLFS, the safety degree of the time-dependent structure with fuzzy uncertainty can be efficiently evaluated. [ABSTRACT FROM AUTHOR]

In this work, probabilistic damage quantification under varying loading conditions in a non-stationary, guided-wave environment is being tackled via the synergistic integration between Time-varying Autoregressive (TAR) models and Gaussian Process regression models (GPRMs). Applying these TAR-GPRMs onto an aluminum coupon with simulated damage under different loading conditions fitted with piezoelectric sensors/actuators, the TAR models show the capability of capturing the non-stationarity in the ultrasonic guided-wave signals generated by the actuators under varying plate-loading conditions. They also provide insights to the maintainer by showing when in time the guided-wave time series deviate the most. In order to take advantage of that, a time instant selection algorithm was developed to allow flexibility in choosing the time instant(s) at which probabilistic damage quantification should be done. Finally, this quantification task is tackled by GPRMs, in which multiple GPRMs are trained using the TAR model parameters under varying conditions, and then used to predict damage size and/or loading state. While this framework is much more powerful in terms of tapping into the dynamics of how guided-waves change with varying conditions compared to simpler forms of GPRMs (such as damage index-trained GPRMs), training of TAR-GPRMs is far more complex. The advantages and challenges associated with the proposed TAR-GPRM approach is presented herein along with potential open areas for research in this regard. [ABSTRACT FROM AUTHOR]

In the realm of sustainable energy, photovoltaic (PV) technology stands as a pivotal solution for clean energy generation. Continual advancements in PV technology have ushered in more efficient and cost-effective components, yet the precise localization and tracking of the maximum power point (MPP) remain critical for enhancing PV system performance. Over the years, various Maximum Power Point Tracking (MPPT) algorithms like Perturb and Observe (P&O) and Incremental Conductance (INC) have been established to address this challenge. In this proposed study, a novel approach using Gaussian Process Regression (GPR) for MPPT in PV systems is introduced. The GPR model is designed to predict the MPP accurately, thereby enhancing system efficiency and contributing to the advancement of sustainable energy generation. Implemented within the MATLAB/Simulink environment, the model utilizes a dataset comprising 1000 observations of solar irradiance, temperature, and corresponding voltages, where 120 datapoints among these were taken as sample for training and evaluation. The results demonstrate promising outcomes with a Mean Squared Error (MSE) of 1.2783 x 10-5 and a Root Mean Squared Error (RMSE) of 0.0031, indicating high accuracy in predicting the MPP. This study underscores the effectiveness of GPR in optimizing PV system performance, supporting its adoption for sustainable energy applications and paving the way for further advancements in renewable energy technologies. [ABSTRACT FROM AUTHOR]

Erosion causes significant damage to life and nature every year; therefore, controlling erosion is of great importance. Therefore, maintaining the balance between soil, plants, and water plays a vital role in controlling erosion. Aim of this study was to estimate some erodability parameters (structural stability index—SSI, aggregate stability—AS, and erosion ratio—ER) with indices and reflectance obtained via TripleSat satellite imagery using machine learning algorithms (support vector regression—SVR, artificial neural network—ANN, and K-nearest neighbors—KNN) in Samsun Province, Vezirköprü, Türkiye. Various interpolation methods (inverse distance weighting—IDW, radial basis function—RBF, and kriging) were also used to create spatial distribution maps of the study area for observed and predicted values. Estimates were made using NDVI, SAVI, and ASVI indices obtained from satellite images and NIR reflectance. Accordingly, the ANN algorithm yielded the lowest MAE (2.86%), MAPE (9.46%), and highest R2 (0.82) for SSI estimation. For AS and ER estimation, SVR had the highest predictive accuracy. Given the RMSE values in spatial distribution maps for observed and estimated values (SSI 7.861–7.248%, AS 14.485–14.536%, and ER 4.919–3.742%), the highest predictive accuracy was obtained with kriging. Thus, it was concluded that erosion parameters can be successfully estimated with reflectance and index values obtained from satellite images using SVR and ANN algorithms, and low-error distribution maps can be created using the kriging method. [ABSTRACT FROM AUTHOR]

Accurately predicting the remaining useful life (RUL) of lithium‐ion batteries is a challenging task, with significant implications for managing battery usage risks and ensuring equipment stability. However, the phenomenon of capacity regeneration and the lack of confidence interval expression result in imprecise predictions. To tackle these challenges, this article proposes a novel method for predicting RUL by optimizing health features (HFs) and integrating multiple models. First, multiple HFs are collected from the charging curves, and the fusion HF is optimized by kernel principal component analysis. To eliminate local fluctuations caused by capacity regeneration effects, the complete ensemble empirical mode decomposition with adaptive noise is employed to decompose the fusion HF. Second, to address the issue of lacking confidence interval expression, a hybrid model is proposed by integrating bidirectional long short‐term memory neural network with Gaussian process regression for effectively capturing the lithium‐ion battery capacity‐declining trend and accurately predicting the RUL. Finally, the proposed model's effectiveness is validated by comparing it with several other models using National Aeronautics and Space Administration and Center for Advanced Life Cycle Engineering datasets. The results indicate that this model achieves a root mean square error of 0.0023 and a mean absolute error of 0.0058, demonstrating significant improvements in predictive accuracy for RUL with high reliability. [ABSTRACT FROM AUTHOR]

Kriging-based finite element method (K-FEM) is an enhancement of the FEM using Kriging interpolation in place of the conventional polynomial interpolation. This paper presents the development of the K-FEM for analysis of curved beams based on a deep arc theory, which accounts for membrane and shear deformation. The discrete strain gap technique is employed to circumvent shear locking and membrane locking. The numerical tests show that the Kriging-based elements are free from any locking, are able to provide highly accurate solutions with a regular course mesh discretization, and have excellent convergence characteristics, especially for circular beams. [ABSTRACT FROM AUTHOR]

The porous underground structures have recently attracted researchers' attention for hydrogen gas storage due to their high storage capacity. One of the challenges in storing hydrogen gas in aqueous solutions is estimating its solubility in water. In this study, after collecting experimental data from previous research and eliminating four outliers, nine machine learning methods were developed to estimate the solubility of hydrogen in water. To optimize the parameters used in model construction, a Bayesian optimization algorithm was employed. By examining error functions and plots, the LSBoost method with R² = 0.9997 and RMSE = 4.18E-03 was identified as the most accurate method. Additionally, artificial neural network, CatBoost, Extra trees, Gaussian process regression, bagged trees, regression trees, support vector machines, and linear regression methods had R² values of 0.9925, 0.9907, 0.9906, 0.9867, 0.9866, 0.9808, 0.9464, and 0.7682 and RMSE values of 2.13E-02, 2.43E-02, 2.44E-02, 2.83E-02, 2.85E-02, 3.40E-02, 5.68E-02, and 1.18E-01, respectively. Subsequently, residual error plots were generated, indicating the accurate performance of the LSBoost model across all ranges. The maximum residual error was − 0.0252, and only 4 data points were estimated with an error greater than ± 0.01. A kernel density estimation (KDE) plot for residual errors showed no specific bias in the models except for the linear regression model. To investigate the impact of temperature, pressure, and salinity parameters on the model outputs, the Pearson correlation coefficients for the LSBoost model were calculated, showing that pressure, temperature, and salinity had values of 0.8188, 0.1008, and − 0.5506, respectively, indicating that pressure had the strongest direct relationship, while salinity had an inverse relationship with hydrogen solubility. Considering the results of this research, the LSBoost method, alongside approaches like state equations, can be applied in real-world scenarios for underground hydrogen storage. The findings of this study can help in a better understanding of hydrogen solubility in aqueous solutions, aiding in the optimization of underground hydrogen storage systems. [ABSTRACT FROM AUTHOR]

This paper proposes an optimized operational strategy for user-side proton exchange membrane (PEM) electrolyzer hydrogen production systems, considering the degradation of hydrogen production efficiency over time. The work is divided into three parts. First, a combined hydrogen production efficiency model based on operational data is established, using polynomial surface fitting (PSF) and gaussian process regression (GPR) to model the electrolyzer's efficiency from two perspectives: operational time and input power. Second, an optimization model for the operational strategy of the user-side electrolytic hydrogen production system is constructed, aiming to enhance overall system efficiency by adjusting the electrolyzer's input power. Finally, the hydrogen efficiency model from the first part is applied to the optimization strategy in the second part for empirical analysis. The results show that the optimized strategy, which accounts for the degradation of hydrogen production efficiency, significantly improves system performance, validating the method's effectiveness and practicality. This study provides theoretical support and practical guidance for the efficient operation of user-side electrolyzers, contributing to the promotion and application of green hydrogen technologies. • The simplified model estimates electrolyzer efficiency for any given range. • Comparison of power-efficiency and time-power-efficiency models. • Ignoring performance degradation leads to a 15.9% overestimation of production. • The optimization strategy boosts profitability by 16.4%. [ABSTRACT FROM AUTHOR]

Leaf chlorophyll content (LCC) is crucial for monitoring the physiological processes of crops. Many studies have utilized spectral features to develop regression models for accurate LCC estimation, enabling the quantitative assessment and evaluation of crop growth status. The selection of optimal spectral features and regression algorithms significantly affects the precision of LCC estimation. In this study, we compared and analyzed the optimal spectral features for LCC estimation, as well as the consistency of machine learning methods across different crop types, phenology periods, and sensors. First, we extracted various spectral features, including the original spectral features (OS), first-order derivative spectral features (FDS), original continuum-removed spectra (CR) along with their four related derivative spectral features, principal component variables derived from different spectral features, and highly correlated spectral features with LCC. These extracted spectral features were then employed to construct the LCC models using six common regression algorithms on different datasets. Finally, we analyzed the optimal combination of spectral features and regression algorithms for accurate LCC estimation considering various dimensions, such as crop type, phenological period, and sensor used in observation conditions. The results demonstrate that the combinations of the principal component variables of continuum-removed derivative reflectance with the top 10 correlations with LCC (PCA_CRDR_R) combined with Gaussian process regression (GPR) can be considered as the optimal choice for estimating LCC under diverse observation conditions at a canopy scale, and its R2 can reach 0.62 for sugar beet LCC estimation; thus providing valuable theoretical guidance for selecting appropriate spectral features for LCC estimation. [ABSTRACT FROM AUTHOR]

Accurate estimation of chlorophyll is essential for monitoring maize health and growth, for which hyperspectral imaging provides rich data. In this context, this paper presents an innovative method to estimate maize chlorophyll by combining hyperspectral indices and advanced machine learning models. The methodology of this study focuses on the development of machine learning models using proprietary hyperspectral indices to estimate corn chlorophyll content. Six advanced machine learning models were used, including robust linear stepwise regression, support vector machines (SVM), fine Gaussian SVM, Matern 5/2 Gaussian stepwise regression, and three-layer neural network. The MRMR algorithm was integrated into the process to improve feature selection by identifying the most informative spectral bands, thereby reducing data redundancy and improving model performance. The results showed significant differences in the performance of the six machine learning models applied to chlorophyll estimation. Among the models, the Matern 5/2 Gaussian process regression model showed the highest prediction accuracy. The model achieved R2 = 0.71 for the training set, RMSE = 338.46 µg/g and MAE = 264.30 µg/g. In the case of the validation set, the Matern 5/2 Gaussian process regression model further improved its performance, reaching R2 =0.79, RMSE=296.37 µg/g, MAE=237.12 µg/g. These metrics show that Matern’s 5/2 Gaussian process regression model combined with the MRMR algorithm to select optimal traits is highly effective in predicting corn chlorophyll content. This research has important implications for precision agriculture, particularly for real-time monitoring and management of crop health. Accurate estimation of chlorophyll allows farmers to take timely and targeted action. [ABSTRACT FROM AUTHOR]

To enhance the material utilization rate in hot forging of straight teeth face gears, an optimization model of the process parameters was built. The "protrusion" volume generated during hot forging was used as the optimization objective, while the maximum stress was used as the constraint. And key parameters crucial to the hot forging process, including deformation temperature, friction factor, mold preheating temperature, and forging strike speed, were selected as design variables. To evaluate the "protrusion" volume and maximum stress under different process parameters, the inherited Latinized centroidal Voronoi tessellation (ILCVT) method was used to generate training samples containing initial design points. Subsequently, the hot forging process of spur gears was simulated by using deform-3D software. The Kriging model was introduced to model the implicit relationship between design variables and performance responses. The simulated annealing algorithm was introduced. Moreover, the disturbance model, annealing temperature attenuation method, and temperature variation strategy were improved to enhance the algorithm search efficiency. The optimized forging process parameters were workpiece deformation temperature of 1 049 °C, friction factor of 0.32, mold preheating temperature of 206 °C, and forging strike speed of 249 mm/s. The effectiveness of the optimization results were verified through a combination of simulation and experimental methods. The results show that the optimized process parameters effectively reduces the "protrusion" volume. [ABSTRACT FROM AUTHOR]

The failure modes of complex systems are often highly dependent. Aiming at the reliability analysis of engineering systems with multiple failure modes, an efficient surrogate model for system reliability with multiple failure modes is proposed, namely, the Copula Adaptive Kriging surrogate model (CAKSM). First, the initial Kriging model is established based on the initial samples. In order to select more effective added samples to update the Kriging model, a new learning function, namely, Copula Unites with Expected Improvement Function (CUEIF), is established. The function can make a reasonable sample selection by considering the failure correlation. Then, based on the optimal Copula function, the reliability data of each failure mode are coupled and analyzed. In order to adapt to various computing scales, regularization is introduced to improve the prediction speed of the surrogate model, and the probability density function of each performance function is obtained by introducing nonparametric kernel density estimation. Finally, the effectiveness of the CAKSM method and the learning function CUEIF is verified through four examples. [ABSTRACT FROM AUTHOR]

During the takeoff phase, aircraft engines reach maximum speed and temperature to achieve the required thrust. Due to these harsh operating conditions, the performance of aircraft engines may decrease. This decrease in performance increases both fuel consumption and environmental damage. Reducing or eliminating the damages caused by aircraft is among the objectives of ICAO. In order to achieve this goal, aircraft engines are compulsorily tested, evaluated by experts and certified. The data obtained during the test process is recorded and stored in the engine emission databank (EEDB). During the takeoff phase, there is no system that can evaluate aircraft engines without dismantling and without expert knowledge. In this study, EEDB 2019 and 2021 takeoff phase data sets were used. Fuel flow T/O parameter is an important parameter used both in the calculation of aircraft emissions and in the evaluation of engine performance. Gaussian process regression (GPR), support vector machine (SVM) and multilayer perceptron (MLP) models were used to estimate the fuel flow T/O parameter. The results obtained were compared according to error performance criteria and the best model was selected. In MATLAB® environment, confidence intervals were plotted with the estimated fuel flow T/O value at 99% confidence level. This study demonstrates that the performance evaluation of aircraft engines during the takeoff phase can be performed without the need for expert knowledge. [ABSTRACT FROM AUTHOR]

With the proposal of intelligent mines, the demand for drilling is increasing daily. Therefore, it is particularly crucial to gather more geological data by interpolation of limited drilling data for subsequent three-dimensional geological modeling. In this paper, a hybrid sparrow optimization Kriging model (HSSA), in which chaos theory and Levy flight are integrated into the initial population update algorithm of the sparrow algorithm and the location update algorithm of the entrants, is proposed. Next, the golden sine optimization algorithm is introduced into the reconnaissance and early warning mechanism of the sparrow algorithm to further improve the accuracy and local escape ability. By the correlation optimization of the original sparrow algorithm, the speed and accuracy of swarm intelligence optimization are further improved. In addition, the model solves the parameters of the variation function of the ordinary Kriging interpolation and reduces the generation error of the formation data interpolation. The results of relevant experiments show that the hybrid sparrow optimization Kriging model improves the accuracy and convergence speed compared with other swarm intelligence algorithms and that the accuracy of this model is improved by 8.4% compared with the original Kriging interpolation algorithm. Based on the hybrid sparrow optimization Kriging model, we propose a three-dimensional stratigraphic model for the Yangchangwan Coal Mine, which provides further support for mining operations and three-dimensional stratigraphic research in this area. The accuracy and applicability of the hybrid sparrow optimization Kriging model are further explained using a case study with the stratigraphic model data in the Yangchangwan Coal Mine. HSSA with significant potential for applications in industries such as coal mining and geological exploration. In these fields, the efficient acquisition, processing, and modeling of stratigraphic data are critical for enhancing geological interpretation and optimizing operational workflows. [ABSTRACT FROM AUTHOR]

A machine learning (ML) guided approach is presented for the accelerated optimization of chemical vapor deposition (CVD) synthesis of 2D materials toward the highest quality, starting from low‐quality or unsuccessful synthesis conditions. Using 26 sets of these synthesis conditions as the initial training dataset, our method systematically guides experimental synthesis towards optoelectronic‐grade monolayer MoS2 flakes. A‐exciton linewidth (σA) as narrow as 38 meV could be achieved in 2D MoS2 flakes after only an additional 35 trials (reflecting 15% of the full factorial design dataset for training purposes). In practical terms, this reflects a decrease of the possible experimental time to optimize the parameters from up to one year to about two months. This remarkable efficiency was achieved by formulating a constrained sequencing optimization problem solved via a combination of constraint learning and Bayesian Optimization with the narrowness of σA as the single target metric. By employing graph‐based semi‐supervised learning with data acquired through a multi‐criteria sampling method, the constraint model effectively delineates and refines the feasible design space for monolayer flake production. Additionally, the Gaussian Process regression effectively captures the relationships between synthesis parameters and outcomes, offering high predictive capability along with a measure of prediction uncertainty. This method is scalable to a higher number of synthesis parameters and target metrics and is transferrable to other materials and types of reactors. This study envisions that this method will be fundamental for CVD and similar techniques in the future. [ABSTRACT FROM AUTHOR]

With the fast expansion of intermittent renewable energy sources in the upcoming smart grids, simple and accurate day-ahead systems for residual load forecasts are urgently needed. Machine learning strategies can facilitate towards drastic cost minimizations in terms of operating-reserves avoidance to compensate the mismatches between the actual and forecasted values. In this study, a multi-input/multi-output model is developed based on artificial neural networks to map the relationship between different predictor inputs, including time indices, weather variables, human activity parameters, and energy price indicators, and target outputs such as wind and photovoltaic generation. While the information flows in only one direction (from the predictor nodes through the hidden layers to the target node), benchmark training algorithms are employed and assessed under different case studies. The model is evaluated under both parametric and non-parametric formulations, namely neural networks and Gaussian process regression. Essential improvements are achieved by enhancing the number of embedded predictors, while superior performance is observed by using Bayesian regularization mechanisms. In terms of mean-error indices and determination coefficient, this opens the pathway towards minimization via Bayesian inference-based approaches in the presence of increased and highly stochastic renewable inputs. [ABSTRACT FROM AUTHOR]

Urban trees play an important role in mitigating effects of climate change and provide essential ecosystem services. However, the urban environment can stress trees, requiring the use of effective monitoring methods to assess their health and functionality. The objective of this study, which focused on four deciduous tree species in Rennes, France, was to evaluate the ability of hybrid inversion models to estimate leaf chlorophyll content (LCC), leaf area index (LAI), and canopy chlorophyll content (CCC) of urban trees using eight Sentinel-2 (S2) images acquired in 2021. Simulations were performed using the 3D radiative transfer model DART, and the hybrid inversion models were developed using machine-learning regression algorithms (random forest (RF) and gaussian process regression). Model performance was assessed using in situ measurements, and relations between satellite data and in situ measurements were investigated using spatial allocation (SA) methods at the pixel and tree scales. The influence of including environment features (EFs) as model inputs was also assessed. The results indicated that random forest models that included EFs and used the pixel-scale SA method were the most accurate with R2 values of 0.33, 0.29, and 0.46 for LCC, LAI, and CCC, respectively, with notable variability among species. [ABSTRACT FROM AUTHOR]

In this work, four mainstream machine learning (ML) techniques are used to evaluate the bulk porosity and static elastic modulus of weathered Yungang Grottoes sandstone. Datasets are gathered from the experiments, which includes 432 groups effective experimental data including 8 inputs features. bulk porosity and static elastic modulus were considered as outputs to determine the weathering degrees of Yungang Grottoes sandstone. The 4 performance criteria were used to evaluate the ML models. Results demonstrate that the Artificial Neural Network (ANN) is the best-fitted models for estimating the bulk porosity and static elastic modulus compared to Multiple Linear Regression (MLR), Support Vector Regression (SVR), Gaussian Process Regression (GPR). The accuracy of the trained model for static elastic modulus is slightly higher than that of bulk porosity. The GPR and ANN model can accurately predict the bulk porosity and static elastic modulus in training stages. The ANN with multi-hidden layers developed is competent with high degree of precision and generalization ability for bulk porosity and static elastic modulus compared to other selected regression-based ML models (MLR, SVR, and GPR). The coefficient of determinations of ANN in the range of (0.9537–0.9641) during the testing stages is more stable and higher than that of (0.8883–0.9453) other built ML models. The prediction efficiency of pretrained ANN model was well adjusted for the actual and forecast datasets at the training and testing stages, and the error range was no more than 0.7% and 0.15 GPa at both stages of prediction for bulk porosity and static elastic modulus respectively. And the ANN based static elastic modulus prediction model's error proportions significantly decreased and were confined to a modest range between + 10% and − 10%. The proposed surrogate models are valid for the bulk porosity ranging from 7 to 14% and the static elastic modulus ranging from 0.7 to 1.4 Gpa, which can be utilized for the accurate and fast prediction of the weathering degrees of Yungang Grottoes sandstone. [ABSTRACT FROM AUTHOR]

ABSTRACT This paper presents a novel approach to pollution assessment by investigating support vector machines (SVM) with an uncertainty option to overcome the limitations of traditional kriging. While kriging is a major tool for geostatistical modelling, allowing to estimate the distribution of contaminants in a region from a small set of samples, it does not allow to extract also the uncertainty map. An uncertainty map is of great interest, as it allows to identify regions of high uncertainty where one should sample in order to reduce high level of uncertainties. In this paper, we propose two variants of the SVM with an uncertainty option, each using a different hinge loss to improve the accuracy and efficiency. These losses allow to estimate different levels of contaminations, as well as uncertainty, such as the three levels: positive, uncertain and negative, namely for pollution estimation: high‐pollution, uncertain and low‐pollution. In addition to the exploration of SVM variants, we propose an innovative active sample selection strategy based on the uncertainty criterion. This strategy is designed to systematically reduce uncertainties in pollution assessment, thus providing adaptability to dynamic environmental changes. An incremental SVM with an uncertainty option is introduced to further optimise the sample selection process. Furthermore, the decision‐making process is refined through the introduction of a novel three‐hinge loss. The corresponding optimization problem and its resolution allow for a more nuanced contamination assessment with multiple levels of estimation, providing a valuable tool for characterising contamination levels with increased granularity. Extensive experiments on synthetic and real data validate the proposed methodology. Synthetic data simulations assess the quality of the approach, while real data from a two‐dimensional porosity measurement demonstrate practical applicability. This research contributes to the advancement of pollution assessment methodologies, providing an adaptable solution for environmental monitoring. [ABSTRACT FROM AUTHOR]

The nearshore wind stress, u∗2 ${u}_{\ast }^{2}$, is examined using machine‐learning models for air‐ocean data collected via new flux buoys deployed across four experiments. Consistent with prior nearshore studies, existing open‐ocean models predict nearshore u∗2 ${u}_{\ast }^{2}$ with a large error of 0.0152 m2/s2. Gaussian Process Regression (GPR) for nearshore u∗BM2 ${u}_{\ast \text{BM}}^{2}$ is developed, reducing errors to 0.0108 m2/s2. Nearshore air‐sea parameterizations are examined with wind speed (61%) and the wind‐wave frequency of encounters (16%) being the most important. A simpler nearshore, GPR‐derived, wind‐dependent‐only model (u∗NSU2 ${u}_{\ast \text{NSU}}^{2}$) is developed, with errors of 0.0135 m2/s2. GPRs, evaluated using identical variables, were applied to nearshore observations, and these observations modeled with open‐ocean formulations for an initial comparison of parameterizations between these two regimes. The parameterizations are similar, though with subtle nonlinear differences. The new nearshore data set and machine‐learning models enhance the accuracy of predictions and understanding of differences from the open‐ocean. Plain Language Summary: Understanding and accurately parameterizing wind stress on the ocean surface is crucial for modeling oceanic and atmospheric phenomena. Despite its significance, nearshore wind stress and its influencing factors remain inadequately understood due to limited in situ observations and the complexity of the problem. To address this gap, ten shallow‐water air‐sea buoys were developed and deployed alongside directional wave buoys in four field experiments, yielding a substantial data set of nearshore wind stress and associated variables. Discrepancies between nearshore and open‐ocean models were observed, with open‐ocean models exhibiting large errors. Machine‐learning models enhance the accuracy of predictions and understanding of the input variables. A new data‐informed machine‐learning model for nearshore wind stress significantly reduced the error by 30%. Each variable parameterization is described, and a simple model for wind stress based solely on wind speed is provided. Furthermore, an examination of wind stress parameterizations revealed similarities and differences between nearshore and open‐ocean, primarily attributed to wind speeds. These findings significantly enhance the accuracy of weather and ocean forecasts, particularly for nearshore regions. Key Points: Ten air‐sea buoys for winds and fluxes, deployed with wave buoys in four experiments, improve nearshore wind stress observation gapsSupervised machine learning enhances nearshore wind stress predictions, yielding parameterized variable responses without preconceptionsNearshore wind stress parameterizations relative to the open‐ocean have similar variable responses though with small nonlinear differences [ABSTRACT FROM AUTHOR]

Remaining useful life (RUL) is a key indicator for assessing the health status of lithium (Li)-ion batteries, and realizing accurate and reliable RUL prediction is crucial for the proper operation of battery systems. As high-capacity Li batteries have more complex chemical properties, most of the current RUL prediction methods rely mainly on a priori knowledge to make judgments. As a result, prediction accuracy is not high. In this study, we developed a health indicator-capacity (HI-C) dual Gaussian process regression (GPR) model based on incremental capacity analysis (ICA) and optimized its kernel function to achieve accurate RUL prediction for 280 Ah high-capacity Li batteries. Validation against the United States National Aeronautics and Space Administration's four battery test datasets showed that the use of the HI-C dual GPR model resulted in a mean absolute percentage error and root mean square error of less than 0.02 and 0.04, respectively, for the four battery-rated capacity predictions. Additionally, this model achieved an absolute error of less than five battery failure turns. Compared with a single model, the HI-C dual GPR model not only had high accuracy but also solved the problem that the HI was not measurable in the actual battery operation, which made it more suitable for RUL prediction of Li batteries. [ABSTRACT FROM AUTHOR]

River sediment load estimation poses a critical challenge for water engineers due to its complex and nonlinear hydrological processes. This study assessed the amount of suspended sediment at the Bagh-e-Kalayeh hydrometric station on the Alamut River in the Qazvin province of Iran using two hydrological and meteorological variables, including discharge and rainfall, by considering three scenarios (discharge, discharge + monthly rainfall, and discharge + monthly rainfall + daily rainfall). For modeling, kernel-based data-driven methods, including Gaussian process regression (GPR) and support vector regression (SVR), and tree models, including the M5 tree, random forest (RF), random tree (RT), extra trees, reduced error pruning tree (REPT), and multi-search methods, were used. The results showed that the best performance was achieved by the SVR, with r = 0.948, Wilmot index = 0.965, and RMSE = 0.011 in the first scenario (only discharge). Discharge had the most significant impact on sediment estimation compared to rainfall. It was determined that the suspended sediment load in the Alamut River can be successfully estimated by the SVR method, where only the discharge was used as the input parameter. Additionally, the results indicated that given its characteristics and inherent features, the multi-search method can be used as a complementary approach in sediment modeling, especially in situations where the data volume is not extensive. [ABSTRACT FROM AUTHOR]

Objective: Despite long simulation times, recently developed finite element analysis (FEA) models of knee joints have demonstrated their suitability for predicting individual risk of onset and progression of knee osteoarthritis. Therefore, the objective of this study was to assess the feasibility of machine learning (ML) to replicate outcomes obtained from FEA when simulating mechanical responses and predicting cartilage degeneration within the knee joint. Design: Two ML models based on the Gaussian Process Regression (GPR) algorithms were developed. The first model (GPR1) utilized age, weight, and anatomical joint dimensions as predictor variables to predict tissue mechanical responses and cartilage degeneration based on FEA data. The second model (GPR2) utilized age, weight, height, and gender to predict anatomical joint dimensions, which were then used as inputs in the GPR1 model. Finally, the GPR1 and combined GPR1+GPR2 models were used to investigate the importance of clinical imaging when making personalized predictions for knees from healthy subjects with no history of knee injuries. Results: In the GPR1 model, R2 of 0.9 was exceeded for most of the predicted mechanical parameters. The GPR2 model was able to predict knee shape with R2 of 0.67–0.9. Both GPR1 and combined GPR1+GPR2 models offered equally good performances (AUC = 0.73–0.74) in classifying patients at high risk for the onset and development of knee osteoarthritis. Conclusions: In the future, real-time and easy-to-use GPR models may provide a rapid technology to evaluate mechanical responses within the knee for researchers or clinicians who have no former knowledge of FEA. [ABSTRACT FROM AUTHOR]

Continental shelf sediments contain some of the largest stocks of organic carbon (OC) on Earth and play a vital role in influencing the global carbon cycle. Quantifying how much OC is stored in shelf sediments and determining its residence time is key to assessing how the ocean carbon cycle will be altered by climate change and possibly human activities. Spatial variations in terrestrial carbon stocks are well studied and mapped at high resolutions, but our knowledge of the distribution of marine OC in different seafloor settings is still very limited, particularly in dynamic and spatially variable shelf environments. This lack of knowledge reduces our ability to understand and predict how much and for how long the ocean sequesters CO2. In this study, we use high-resolution multibeam echosounder (MBES) data from the Eastern Shore Islands offshore Nova Scotia (Canada), combined with OC measurements from discrete samples, to assess the distribution of OC content in seafloor sediments. We derive four different spatial estimates of organic carbon stock: (i) OC density estimates scaled to the entire study region assuming a homogenous seafloor, (ii) interpolation of OC density estimates using empirical Bayesian kriging, (iii) OC density estimates scaled to areas of soft substrate estimated using a high-resolution classified substrate map, and (iv) empirical Bayesian regression kriging of OC density within areas of estimated soft sediment only. These four distinct spatial models yielded dramatically different estimates of standing stock of OC in our study area of 223 km2: 80 901, 58 406, 16 437 and 6475 t of OC, respectively. Our study demonstrates that high-resolution mapping is critically important for improved estimates of OC stocks on continental shelves and for the identification of carbon hotspots that need to be considered in seabed management and climate mitigation strategies. [ABSTRACT FROM AUTHOR]

Key message: Accurate volume estimation in Eucalyptus plantation stands was achieved by a linear model using SPOT and Landsat multispectral imagery, specifically texture indices and pixel-scale NDVI time integrals, which reflect the local plantation growth history. Spatial modelling techniques such as Kriging with External Drift and Generalized Additive Model slightly improved predictions by accounting for spatial correlation of volume between sample points. Context: Forest inventories are widely used to estimate stand production. To capture the inherent spatial variability within stands, spatial modelling techniques such as Kriging with External Drift (KED) and the generalized additive model (GAM) have emerged. These models incorporate information on spatial correlation and auxiliary variables that can be obtained from satellite imagery. Aims: Our study explored the use of reflectance data from SPOT and Landsat multispectral imagery. We focused on texture indices and temporal integration of vegetation indices as auxiliary variables in KED and GAM to predict stem volume of fast-growing Eucalyptus sp. plantations in Brazil. Methods: The components extracted from the high-resolution SPOT-6 image included spectral band values, band ratio metrics, key vegetation indices (NDVI, SAVI, and ARVI), texture measurements, and indices derived from texture analysis. Additionally, we included the accumulated NDVI time series acquired from Landsat 5, 7, and 8 satellites between the planting date and the forest inventory measurement date. Results: The best linear model of stem volume using remotely sensed predictors gave an R-squared value of 0.95 and a Root Mean Square Error (RMSE) of 12.44 m3/ha. The R-squared increased to 0.96 and the RMSE decreased to 10.6 m3/ha when the same predictors were included as auxiliary variables in the KED and GAM spatial models. Conclusion: The linear model using remotely sensed predictors contributed most to volume prediction, but the addition of spatial coordinates in the KED and GAM spatial models improved local volume predictions. [ABSTRACT FROM AUTHOR]