Search

The chemical reactions between certain interstellar molecules are exothermic in nature and barrierless in the entrance channel, allowing these reactions to occur rapidly even at low astronomical temperatures, e.g., C and O2 interaction. Obtaining detailed rovibrational transition parameters for the reaction between C and O2, such as state-selected rate coefficients, is crucial for studying the associated atmospheric and astronomical environments. Hence, this work presents an approach that combines quasi-classical trajectory calculations with machine learning techniques based on Neural Network (NN) and Gaussian Process Regression (GPR) to determine state-selected rate coefficients. Employing this approach, we significantly reduced the computational requirements while simultaneously obtaining the accurate state-selected reaction cross sections and rate coefficients for the collision of C and O2. Both the NN-based and GPR-based models established in this work accurately predict the results calculated from explicit numerical calculations in the explored temperature range of 50–1500 K, achieving a coefficient of determination R2 > 0.96. Most importantly, the current work provides the most comprehensive dataset of rovibrational rate coefficients of v = 0–4, j = 0–70 → v′ = 0–15 for the astrophysical modeling of the C–O2 collision system. [ABSTRACT FROM AUTHOR]

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]

The ISO 17450-2:2012 defines the verification operation. The ISO 17450-1:2011 defines the extracted features and the extraction operations on the "non-ideal surface model or on the real surface of the workpiece". The ISO 12781-2:2011 and 12180-2:2011 provide dedicated extraction strategies for the flatness and cylindricity. But no real measurement process is explicit here. However, one of the key factors in an inspection plan is the choice of the measurement strategy. Some sampling strategies, such as Hammersley sequence, offer robust and efficient technics to ensure good distribution of measurement points. But measurements are always defined with a "blind sampling strategy". So, in this paper, the author proposed to use adaptative sampling strategies, based on the Active learning method based on Kriging for the Inspection of Large Surfaces (AK-ILS) and developed an original Active Learning method based on Multi-Layer-Perceptron (AL-MLP), to classify the conform / non-conform parts and to ensure the reconstruction of the surfaces, with smart Skin Models Shapes and a minimal sampling size. [ABSTRACT FROM AUTHOR]

Hydrogen is a promising alternative fuel due to its high energy density and carbon-free combustion. However, safe and widespread adoption requires effective hazard identification, assessment, and mitigation, including rapid hydrogen dispersion modeling for early risk mitigation. Data-driven modeling offers rapid predictive capabilities; however, such approaches are costly due to the need for vast amounts of high-quality or high-fidelity (HF) data. To this end, multi-fidelity (MF) modeling can fuse scarce HF data with abundant low-fidelity (LF) data for rapid HF predictions. In this work, we used helium as a surrogate light gas of hydrogen and developed a Bayesian regression-based MF model to predict the gas concentration in a semi-confined dispersion chamber at multiple locations for various operating conditions. The MF model predicts distributions of potential concentration values, allowing for uncertainty quantification and a statistical assessment of leakage risk. Both experimental and numerical approaches are used to generate datasets used in the current study. The experiment is designated as the HF model, serving as the ground truth with fewer data points. The numerical approach employing computational fluid dynamics (CFD) is designated as the LF model, with more data sets generated at a relatively lower cost. The MF model was trained on all LF data and a subset of the HF data. Good predictive performance is observed on the testing HF data, indicated by an R 2 value of 0.9, particularly for physical locations away from the leakage point. This study provides new pathways to rapidly assess hydrogen safety and mitigate early-stage risk with minimal HF data. [Display omitted] • A probabilistic model was developed to predict helium concentration in a semi-confined space by fusing datasets from low and high-fidelity helium dispersion models. • The model achieves an R 2 value of 0.9, with excellent predictive capabilities for locations far from the helium leakage source. • This study provides new pathways to rapidly assess hydrogen safety with sparse high-fidelity data. [ABSTRACT FROM AUTHOR]

To reduce the computational burden of aerodynamic design optimization, a multi-fidelity expected improvement (MFEI) method is developed, based on the error analysis of a multi-level hierarchical kriging (MHK) model for accelerating optimization convergence. By maximizing the MFEI function, a new sample of arbitrary fidelity level is determined to ameliorate the accuracy of the MHK model, and convergence to the high-fidelity optimum is ensured. The proposed optimization method based on MFEI and MHK is demonstrated by two analytical function cases and verified by two aerodynamic design optimizations: drag minimizations of an RAE2822 aerofoil and an ONERA M6 wing in transonic flows. It is shown that the MFEI method tends to infill more gainful samples of lower fidelities during optimization, so fewer highest-fidelity samples are required. This confirms that the proposed method can obtain optimal results within a limited computational budget and is more efficient than the existing single-fidelity or two-fidelity methods. [ABSTRACT FROM AUTHOR]

Effective drilling planning relies on understanding the rock mechanical properties, typically estimated from petrophysical data. Real-time estimation of these properties, especially static Young's modulus ( E sta ), is crucial for geomechanical modeling, wellbore stability, and cost-effective decision-making. In this study, predictive models of E sta were developed using mudlogging data from two vertically drilled wells (A and B) in the same field. E sta was estimated from petrophysical data across the studied depth range in both wells using a field-specific equation. Outlier data were identified and removed by evaluating the cross plot of mechanical specific energy and drilling rate for Well A. The data from Well A were then randomly divided into training and testing sets. The algorithms, multi-layer perceptron neural networks, random forests, Gaussian process regression (GPR), and support vector regression, were adjusted and applied to the training data. The resulting models were evaluated on the test data. The GPR model demonstrated the lowest RMSE values in both the training (0.0075 GPa) and testing (0.4577 GPa) phases, indicating superior performance. To further assess the models, the overfitting index and scoring techniques were employed, revealing that the GPR model exhibited the lowest overfitting value and outperformed the other models. Consequently, the GPR model was selected as the best-performing model and was analyzed using Shapley additive explanation to evaluate the influence of each input feature on the output. This analysis indicated that depth had the greatest effect, while rotation speed had the least impact on the model's output. The application of the GPR model to predict E sta in Well B demonstrated its high generalization capability. Therefore, it can be confidently stated that with additional data, this model could be effectively applied to similar depth ranges in other wells within the field. The study introduces innovations by applying GPR to predict E sta from mudlogging data, addressing outlier impact on predictions, and developing a real-time E sta prediction model for drilling. [ABSTRACT FROM AUTHOR]

The elastic modulus of basalt is a significant engineering parameter required for many projects. Therefore, a total of 137 datasets of basalts from Digor-Kilittasi, Turkey, were used to predict the elastic modulus of intact rock (Ei) for this study. P wave velocity, S wave velocity, apparent porosity, and dry density parameters were employed as input parameters. In order to predict Ei, seven different models with two or three inputs were constructed, employing four different machine learning methods such as Support Vector Machine (SVM), Gaussian Process Regression (GPR), Ensembles of Tree (ET), and Regression Trees (RT). The performance of datasets, models, and methods was evaluated using the coefficient of determination (R2), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and Mean Absolute Error (MAE). This study presented and analyzed the performance of four machine learning methods. A ranking approach was employed to determine the best performing method and dataset. Based on these evaluations, all four machine learning techniques effectively estimate the value of Ei. While they can be used as an appropriate choice for estimating the elastic modulus of basaltic rocks, the ET approach appears to be the most successful method. However, the performance of the GPR is the worst according to model assessments. The average R² values for Model 1 through 7 of the ET method for the five test datasets are 0.97, 0.93, 0.89, 0.97, 0.91, 0.99, and 0.99, respectively. The the average R2 values for GPR from Models 1 to 7 for the five test datasets are 0.73, 0.55, 0.69, 0.48, 0.47, 0.73, 0.56, respectively. An additional indication that the ET performed better than all the other methods was the Taylor diagram, which made it simple to determine how well the model predictions matched the observations. Furthermore, these findings validate the performance of the machine learning techniques employed in this study as valuable instruments for future investigations into the modeling of complex engineering issues. The results of this study suggest that machine learning algorithms can help reduce the need for high-quality core samples and labor-intensive procedures in predicting the elastic modulus of basaltic rocks, resulting in time and cost savings. [ABSTRACT FROM AUTHOR]

Droughts are among the most hazardous and costly natural disasters and are hard to quantify and characterize. Accurate drought forecasting reduces droughts' devastating economic effects on ecosystems and people. Eastern Anatolia is the largest and coldest geographical region of Türkiye. Previous studies lack drought forecasting in the Eastern Anatolia (Upper Mesopotamia) Region, where agriculture is limited due to being under snow most of the year. This study focuses on the Euphrates basin, specifically the Tercan and the Tunceli meteorological stations of the Karasu River sub-basin, a vital Eastern Anatolia Region water resource. In this context, time series of 1-, 3-, 6-, 9-, and 12-month Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) values were created. The Tuned Q-factor Wavelet Transform (TQWT) method and Univariate Feature Ranking Using F-Tests (FSRFtest) were used for pre-processing and feature selection. Several models were created, such as stand-alone, hybrid, and tribrid. Machine Learning (ML) methods such as Artificial Neural Networks (ANN), Gaussian Process Regression (GPR), and Support Vector Machine (SVM) were conducted for the time series analyses. The GPR approach was concluded to perform better than the ANN and SVM at the Tercan station. In other words, GPR performs better in 80% of cases than SVM and ANN models. At the Tunceli station for the SPI output, SVM, which had a superior performance in 60% of the cases, demonstrated a performance comparable to GPR. At the same time, ANN once again exhibited an inferior performance. Similarly, for the SPEI output at the Tunceli station, no clear superiority was observed between the GPR and ANN methods. Because both methods were successful in 40% of cases. This study contributes by introducing a third concept to the stand-alone and hybrid model comparison of drought forecasting, adding tribrid models. It has been detected that the Hybrid and Tribrid ML methods lead to a 91% and 64% decrease relative root mean square error percentage compared stand-alone ML methods for SPEI and SPI in two stations. While the hybrid model at Tercan station was more successful in 80% of the cases, the hybrid model at Tercan station was more successful in 90% of the cases. While hybrid models were observed to be superior, tribrid models not only demonstrated performance close to the hybrid models but also provided advantages such as reducing computational load and shortening calculation time. [ABSTRACT FROM AUTHOR]

Accurate digital elevation models (DEMs) derived from airborne light detection and ranging (LiDAR) data are crucial for terrain analysis applications. As established in the literature, higher point density improves terrain representation but requires greater data storage and processing capacities. Therefore, point cloud sampling is necessary to reduce densities while preserving DEM accuracy as much as possible. However, there has been a limited examination directly comparing the effects of various sampling algorithms on DEM accuracy. This study aimed to help fill this gap by evaluating and comparing the performance of three common point cloud sampling methods octree, spatial, and random sampling methods in high terrain. DEMs were then generated from the sampled point clouds using three different interpolation algorithms: inverse distance weighting (IDW), natural neighbor (NN), and ordinary kriging (OK). The results showed that octree sampling consistently produced the most accurate DEMs across all metrics and terrain slopes compared to other methods. Spatial sampling also produced more accurate DEMs than random sampling but was less accurate than octree sampling. The results can be attributed to differences in how the sampling methods represent terrain geometry and retain microtopographic detail. Octree sampling recursively subdivides the point cloud based on density distributions, closely conforming to complex microtopography. In contrast, random sampling disregards underlying densities, reducing accuracy in rough terrain. The findings guide optimal sampling and interpolation methods of airborne lidar point clouds for generating DEMs for similar complex mountainous terrains. [ABSTRACT FROM AUTHOR]

The 3D ionosphere structure is of interest in many fields such as radio frequency communication and global navigation satellite system (GNSS) applications. However, the limited temporal and spatial coverage of measurements poses a challenge for 3D electron density modeling. To overcome this challenge, we explore the use of kriging interpolation technique. The kriging interpolation is performed to obtain 3D representation of the ionosphere over electron density measurements retrieved by GNSS radio-occultation (RO) data. RO measurements are first reduced to "shape function," the ratio of electron density to vertical total electron content (VTEC), aiming to create a background model. Then, the empirical residual semivariogram is analyzed for variation characteristics of the shape functions under different solar geomagnetic conditions. Finally, 3D kriging is adopted for shape function interpolation. Compared to the modeling results without kriging, the maximum root mean square error (RMSE) reduction reaches 3.4 × 10 - 4 km - 1 , which amounts to 3.4 × 10 11 el/m 3 of electron density when VTEC is assumed as 100 TECU. This improvement accounts for 17.8% of root mean square (RMS) of shape function. [ABSTRACT FROM AUTHOR]

Purpose: A generalised approach to downscale areal observations of crop production data is illustrated using cotton yield and fibre quality (length and micronaire) data which is measured as a module (areal/block) average. Methods: Two features of the downscaling algorithm are; (i) to estimate spatial trends in yield and quality using regression with fine resolution predictors such as remote sensing imagery, and (ii) use area-to-point kriging (A2PK) to downscale either the observations in the absence of a useful spatial trend model or the residuals from the trend model (if useful) from areal averages. Results: Correlations with remote sensing covariates were stronger for cotton fibre yield than for cotton fibre micronaire, and much stronger compared to those for cotton fibre length. Spatial trends in cotton fibre yield and micronaire could be estimated with good model quality using regression with remote sensing covariates with or without A2PK in almost all fields. Conversely, model quality was poorer for cotton fibre length and there was only a small difference in model performance between the null and trend models. When the downscaling approach was tested using fine-resolution yield observations, model performance was poorer at a fine-resolution compared to the module-resolution, which was to be expected. Conclusion: This approach enables the creation of high-resolution raster maps of variables of interest with a much finer spatial resolution compared to the areal observations, and can be applied for any areal averaged crop production data in a range of broadacre and horticultural industries (e.g. sugarcane, apples, citrus). The finer spatial resolution may allow growers or agronomists to better understand the drivers of variability within fields, assess management implications, and create management plans at a higher resolution. [ABSTRACT FROM AUTHOR]

Given the high costs of soil sampling, low and extra-low sampling densities are still being used. Low-density soil sampling usually does not allow the computation of experimental variograms reliable enough to fit models and perform interpolation. In the absence of geostatistical tools, deterministic methods such as inverse distance weighting (IDW) are recommended but they are susceptible to the "bull's eye" effect, which creates non-smooth surfaces. This study aims to develop and assess interpolation methods or approaches to produce soil test maps that are robust and maximize the information value contained in sparse soil sampling data. Eleven interpolation procedures, including traditional methods, a newly proposed methodology, and a kriging-based approach, were evaluated using grid soil samples from four fields located in Central Alberta, Canada. In addition to the original 0.4 ha⋅sample−1 sampling scheme, two sampling design densities of 0.8 and 3.5 ha⋅sample−1 were considered. Among the many outcomes of this study, it was found that the field average never emerged as the basis for the best approach. Also, none of the evaluated interpolation procedures appeared to be the best across all fields, soil properties, and sampling densities. In terms of robustness, the proposed kriging-based approach, in which the nugget effect estimate is set to the value of the semi-variance at the smallest sampling distance, and the sill estimate to the sample variance, and the IDW with the power parameter value of 1.0 provided the best approaches as they rarely yielded errors worse than those obtained with the field average. [ABSTRACT FROM AUTHOR]

This study aimed to investigate and analyze the performance of twelve machine learning (ML) algorithms in estimating the construction time and cost of drill and blast tunnels. Thirteen tunnels located in different regions of Iran were selected, resulting in 900 data sets. Ten parameters were identified as influential factors affecting the construction time and cost of these tunnels. 80% of the data set was used for training, while the remaining 20% was reserved for testing. Additionally, 288 unseen data sets were utilized for evaluation purposes. All the algorithms demonstrated accurate performance on the test data sets, with R-squared values exceeding 0.93. However, only the Gaussian process regression algorithm achieved satisfactory results on the unseen data sets. Furthermore, a graphical user interface (GUI) was developed based on the trained ML models. This GUI allows real-time estimation of the time and cost of drill and blast tunnels and can be updated during construction. [ABSTRACT FROM AUTHOR]

Microscopic modeling of vehicle movements and interactions is pivotal in traffic flow theory. Physics-based car-following (CF) models using mathematical formulations can delineate driving behavior in various traffic conditions with decent interpretability. However, given predetermined mathematical forms, they might fail to characterize complex, highly nonlinear phenomena. Data-driven CF models naturally excel in this regard considering their flexible architectures, but their performance is subject to data quality, especially distribution bias. In this paper, we propose a novel physics-informed particle filter (PIPF) model that fuses and takes advantage of the two approaches. Utilizing the intelligent driver model as the physics-based model and the multioutput Gaussian process regression as the data-driven model, the PIPF model integrates and embeds both models into a particle filter framework, enhancing both model adaptability and accuracy. The performance of the proposed model is examined through both single vehicle and multivehicle numerical experiments using the NGSIM trajectory data set. Compared with physics-based and data-driven models alone, the PIPF model demonstrates a performance improvement in terms of the root mean square error of about 11.16% and 29.43% in scenarios characterized by sparse data and about 19.81% and 3.84% in scenarios with sufficient data. Compared to traditional particle filtering models, the number of particles to achieve optimal results is reduced by 20%, meaning less computational complexity. [ABSTRACT FROM AUTHOR]

Irrigation is important for the growth of world agriculture, as it enables greater security in agricultural production. The use of center-pivot for irrigation is very common in Brazil. However, there are some information gaps, mainly related to spatial variability in the water application in variable topography. Thus, the present study aimed to apply the geostatistical approach to characterize and evaluate the magnitude of the pressure head (PH) spatial variability in center-pivot lateral lines operating in plots with variable topography. For this analysis, six different points were installed along the lateral line and measured with PH transducers in 18 lateral line angular positions in the study area. Universal kriging (UK) was used to estimate PH across the whole field. The semivariogram was adjusted by the hole effect theoretical model, indicating a strong spatial dependence on PH. A decision support system tool was developed to assist in the analysis of the PH spatial distribution along the center-pivot lateral line using a geostatistical approach (kriging). The proposed tool can be useful for managers of irrigable areas and to identify zones with high energy use (wasted PH) along lateral lines of center-pivot systems. The estimation of PH distribution using geostatistical and UK techniques was satisfactory, allowing the creation of a thematic map. Precision irrigation and monitoring using a thematic map of PH distribution from kriging can help monitor the operating conditions of a center-pivot, as well as improve the decision-making regarding proper management of the whole irrigation system. Practical Applications: Center-pivot irrigation systems are very common in agricultural production areas around the world. Due to the large area irrigated by center-pivots, it is very important to study the reduction in water and energy use in these equipment. Thus, an important point to be studied is the PH distribution along the center-pivot lateral line in areas with undulating topography, where there is a significant PH variation. In this study, we present an analysis of the PH distribution along the lateral line using a geostatistical approach (kriging) to obtain PH values in the entire irrigated area. For this, PH data collected at six different points along the lateral line were used in a decision support system tool, developed to estimate PH in the entire irrigated area using the geostatistical approach. This estimate was satisfactory, allowing the creation of a thematic map. The proposed tool proved to be useful for easily identifying zones with high energy use (wasted PH). In this way, the use of precision irrigation and the analysis of the equipment through thematic mapping can help irrigators in monitoring the operating conditions of a center-pivot. [ABSTRACT FROM AUTHOR]

The dynamic cone penetrometer (DCP) provides local soil resistance information. The difference in the vertical and horizontal data resolution (centimetric vs. multi‐metric) makes it difficult to spatialize the DCP data directly. This study uses a high‐resolution Vs$V_s$ section, extracted by the seismic surface‐wave method, as the auxiliary and physical constraint for mapping the DCP index (DCPI). Geostatistical formalism (kriging and cokriging) is used. The associated measurement error of the seismic surface‐wave data is also included in the cokriging system, that is, the cokriging with variance of measurement error (CKVME). The proposed methods are validated for the first time on a test site designed and constructed for this study, with known geotechnical perspectives. Seismic and high‐intensity DCP campaigns were performed on the test site. The results show that with decimating the number of DCP soundings, the kriging approach is no longer capable of estimating the lateral variation in the test site, and the root‐mean‐square error (RMSE) value of the kriging section is increased by 87%$87\%$. With the help of Vs$V_s$ sections constraining the lateral variability model, the RMSE values of the cokriging and the CKVME sections are increased by 25%$25\%$ and 17%$17\%$. [ABSTRACT FROM AUTHOR]

Detailed wind pressure information plays a critical role in the accurate estimation of wind loads on high‐rise buildings, especially for complex‐shaped supertall buildings. However, owing to the limited internal space of a scaled building model and the capacity of data‐acquisition devices, it is often difficult to acquire the wind pressures at all positions of interest on the entire model in wind tunnel testing. To this end, a novel approach that combines the proper orthogonal decomposition (POD) and machine learning (ML) is presented in this paper for the prediction of wind pressure time series (WPTS) on supertall building models in wind tunnel testing. In this approach, the prediction of WPTS is converted into the estimation of several main eigenmodes and mean wind pressures by combining the POD with ML. This strategy can effectively reduce the computational effort compared to the direct prediction of WPTS. A combined ML model consisting of the Gaussian process regression (GPR), decision tree regression (DTR), and random forest (RF) (i.e., POD‐GPR‐DTR‐RF model) is utilized for the prediction of eigenmodes and mean wind pressures. Wind pressure records from a wind tunnel experiment of a 600‐m‐high building are employed to verify the accuracy and effectiveness of the presented approach. The results show that the combined ML model (i.e., POD‐GPR‐DTR‐RF model) developed based on the proposed approach performs satisfactorily in the prediction of WPTS and outperforms the conventional method that combines POD with backpropagation neural network model (i.e., POD‐BPNN model), demonstrating that the proposed approach is an effective tool for prediction of WPTS on supertall buildings. [ABSTRACT FROM AUTHOR]

The problem addressed in this work is the conditional simulation of a regionalized variable that is modeled as a realization of a non-monotonic transform of a Gaussian random field. As an alternative to Markov Chain Monte Carlo methods that often suffer from a slow convergence to the target distribution, we propose the use of sequential Monte Carlo approaches, with different variants of particle filtering. These variants are tested on synthetic and real datasets, to showcase their applicability and effectiveness under a proper setup of the importance sampling strategy, visiting sequence, number of particles, block size and kriging neighborhood used. The real case study, which deals with the simulation of gold grades in a porphyry copper-gold deposit, shows that the multi-Gaussian model based on a non-monotonic anamorphosis better assesses uncertainty than the traditional model based on a strictly monotonic anamorphosis, and that a moving neighborhood implementation of sequential Monte Carlo approaches can be successful, opening the door to applications to large-size problems in spatial uncertainty modeling. [ABSTRACT FROM AUTHOR]

Mineral resources are estimated to establish potential orebody with acceptable quality (grade) and quantity (tonnage) to validate investment. Estimating mineral resources is associated with uncertainty from sampling, geological heterogeneity, shortage of knowledge and application of mathematical models at sampled and unsampled locations. The uncertainty causes overestimation or underestimation of mineral deposit quality and/or quantity, affecting the anticipated value of a mining project. Therefore, uncertainty is assessed to avoid any likely risks, establish areas more prone to uncertainty and allocate resources to scale down potential consequences. Kriging, probabilistic, geostatistical simulation and machine learning methods are used to estimate mineral resources and assess uncertainty, and their applicability depends on deposit characteristics, amount of data available and expertise of technical personnel. These methods are scattered in the literature making them challenging to access when needed for uncertainty quantification. Therefore, this review aims to compile information about uncertainties in mineral resource estimation scatted in the literature and develop a knowledge base of methodologies for uncertainty quantification. In addition, mineral resource estimation comprises different interdependent steps, in and through which uncertainty accumulates and propagates toward the final estimate. Hence, this review demonstrates stepwise uncertainty propagation and assessment through various phases of the estimation process. This can broaden knowledge about mineral resource estimation and uncertainty assessment in each step and increase the accuracy of mineral resource estimates and mining project viability. [ABSTRACT FROM AUTHOR]

Injection molding is a pivotal industrial process renowned for its high production speed, efficiency, and automation. Controlling the motion speed of injection molding machines is a crucial factor that influences production processes, directly affecting product quality and efficiency. This paper aims to tackle the challenge of achieving optimal tracking control of injection speed in a standard class of injection molding machines (IMMs) characterized by nonlinear dynamics. To achieve this goal, we propose a learning-based model predictive control (LMPC) scheme that incorporates Gaussian process regression (GPR) to predict and model uncertainty in the injection molding process (IMP). Specifically, the scheme formulates a nonlinear tracking control problem for injection speed, utilizing a GPR-based learning residual model to capture uncertainty and provide accurate predictions. It learns the dynamics model and historical data of the IMM, automatically adjusting the injection speed according to target requirements for optimal production control. Additionally, the optimization problem is efficiently solved using a control-constrained differential dynamic programming approach. Finally, we conduct comprehensive numerical experiments to demonstrate the effectiveness and efficiency of the proposed LMPC scheme for controlling injection speed in IMP. [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]

Radio environment maps (REMs) have demonstrated their significance in spectrum sensing, control, and sharing, particularly in relation to unmanned systems, the Internet of Things (IoT), and 5G communication. However, they encounter challenges related to meeting the increasing accuracy requirements. This paper introduces the BHM-RK algorithm, a novel approach for constructing REMs in scenarios with multiple transmitters. The algorithm utilizes spatial clustering for transmitter partitioning, Bayesian posterior inference within partitions, and residual Kriging interpolation to address challenges posed by diverse transmitter influences. Experimental validation demonstrates the superior performance of the BHM-RK algorithm in terms of construction accuracy compared to existing methods, highlighting its effectiveness in enhancing precision in REM construction for scenarios with multiple transmitters. [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]

Existing dam displacement statistical methods simulate the thermal effects using simple harmonic functions ignoring the effects of ice periods, extreme heat, and seasonal weather. Moreover, existing data‐driven methods usually utilize a separate modeling strategy, inevitably ignoring the spatiotemporal correlation of multiple displacement points in dams, resulting in poor predictive performance. To overcome these shortcomings, this study proposes a novel machine learning (ML)—aided multiple‐point dam displacement predictive model considering the temperature hysteresis effect. Firstly, an improved hydraulic‐Air_temperture_Time (HTairT) statistical monitoring model is developed using the measured air temperature lagging monitoring data. On this basis, the multitask Gaussian process regression (multipoint GPR) algorithm with an improved kernel function to construct a multipoint deformation prediction model for ultrahigh arch dams. Then, the improved meta‐heuristic physics‐driven Frost algorithm is utilized to determine the optimal parameters of the multipoint GPR model. A high arch dam with a height of 305 m is used as the case study, and five displacement monitoring points are used for validation. Five advanced ML‐based algorithms are used to comparatively evaluate and verify the performance of the proposed method in terms of forecast accuracy and interpretability. The HTairT statistical model can better simulate the hysteresis effect of temperature on dam deformation. Moreover, the Frost‐optimized dam multipoint displacement prediction model with the RQ kernel functions outperforms the other comparison methods in terms of R2, mean absolute error (MAE), and root mean squared error (RMSE) evaluation indicators. This indicates the proposed method can mine the spatiotemporal correlation among multiple monitoring points of ultrahigh arch dams, further improving the overall deformation prediction and uncertainty estimation. [ABSTRACT FROM AUTHOR]

The significance of rigorous optimization techniques in antenna engineering has grown significantly in recent years. For many design tasks, parameter tuning must be conducted globally, presenting a challenge due to associated computational costs. The popular bio-inspired routines often necessitate thousands of merit function calls to converge, generating prohibitive expenses whenever the design process relies on electromagnetic (EM) simulation models. Surrogate-assisted methods offer acceleration, yet constructing reliable metamodels is hindered in higher-dimensional spaces and systems with highly nonlinear characteristics. This work suggests an innovative technique for global antenna optimization embedded within a machine-learning framework. It involves iteratively refined kriging surrogates and particle swarm optimization for generating infill points. The search process operates within a reduced-dimensionality region established through fast global sensitivity analysis. Domain confinement enables the creation of accurate behavioral models using limited training data, resulting in low CPU costs for optimization. Additional savings are realized by employing variable-resolution EM simulations, where low-fidelity models are utilized during the global search stage (including sensitivity analysis), and high-fidelity ones are reserved for final (gradient-based) tuning of antenna parameters. Comprehensive verification demonstrates the consistent performance of the proposed procedure, its superiority over benchmark techniques, and the relevance of the mechanisms embedded into the algorithm for enhancing search process reliability, design quality, and computational efficiency. [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]

Reservoir-level forecasting, while being crucial for optimal operation, is challenged by complex physical processes and changing climate conditions. Machine learning approaches offer deterministic predictions but often neglect system physics and uncertainty. This article presents a probabilistic data-driven approach combining long short-term memory (LSTM) and Gaussian process regression (GPR) to provide both point forecasts and uncertainty estimates. The hybrid model leverages LSTM’s fitting capabilities with GPR’s robust Bayesian frameworks for uncertainty estimation in non-linear problems, offering accurate predictions without extensive high-fidelity modelling, and avoiding frequent training and parameter optimization. Evaluation with real reservoir data from India shows the model’s superiority over the vanilla LSTM for both univariate and multivariate scenarios. The proposed model achieved a Nash-Sutcliffe efficiency of 0.97 to 0.98, a mean biased error of −0.5634 to −1.0314 for 10-day forecasts, and a continuous ranked probability score of 5.80 and 1.87 for the Bhakra and Pong reservoirs, respectively. [ABSTRACT FROM AUTHOR]

The optimal power flow (OPF) problem, characterized by its inherent complexity and strict constraints, has traditionally been approached using analytical techniques. OPF enhances power system sustainability by minimizing operational costs, reducing emissions, and facilitating the integration of renewable energy sources through optimized resource allocation and environmentally aligned constraints. However, the evolving nature of power grids, including the integration of distributed generation (DG), increasing uncertainties, changes in topology, and load variability, demands more frequent OPF solutions from grid operators. While conventional methods remain effective, their efficiency and accuracy degrade as computational demands increase. To address these limitations, there is growing interest in the use of data-driven surrogate models. This paper presents a critical review of such models, discussing their limitations and the solutions proposed in the literature. It introduces both Analytical Surrogate Models (ASMs) and learned surrogate models (LSMs) for OPF, providing a thorough analysis of how they can be applied to solve both DC and AC OPF problems. The review also evaluates the development of LSMs for OPF, from initial implementations addressing specific aspects of the problem to more advanced approaches capable of handling topology changes and contingencies. End-to-end and hybrid LSMs are compared based on their computational efficiency, generalization capabilities, and accuracy, and detailed insights are provided. This study includes an empirical comparison of two ASMs and LSMs applied to the IEEE standard six-bus system, demonstrating the key distinctions between these models for small-scale grids and discussing the scalability of LSMs for more complex systems. This comprehensive review aims to serve as a critical resource for OPF researchers and academics, facilitating progress in energy efficiency and providing guidance on the future direction of OPF solution methodologies. [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]

Quantum algorithms are emerging tools in the design of functional materials due to their powerful solution space search capability. How to balance the high price of quantum computing resources and the growing computing needs has become an urgent problem to be solved. We propose a novel optimization strategy based on an active learning scheme that combines the Quantum-inspired Genetic Algorithm (QGA) with machine learning surrogate model regression. Using Random Forests as the surrogate model circumvents the time-consuming physical modeling or experiments, thereby improving the optimization efficiency. QGA, a genetic algorithm embedded with quantum mechanics, combines the advantages of quantum computing and genetic algorithms, enabling faster and more robust convergence to the optimum. Using the design of planar multilayer photonic structures for transparent radiative cooling as a testbed, we show superiority of our algorithm over the classical genetic algorithm (CGA). Additionally, we show the precision advantage of the Random Forest (RF) model as a flexible surrogate model, which relaxes the constraints on the type of surrogate model that can be used in other quantum computing optimization algorithms (e.g., quantum annealing needs Ising model as a surrogate). [ABSTRACT FROM AUTHOR]

Territorial accessibility conditions are a relevant concept for the continuous development of cities; hence, it is necessary to accurately determine their characteristics and how population or physical factors influence them when interacting with transportation. In the present study, a mathematical model is developed using transport supply models to evaluate the average global accessibility of bicycle infrastructure, considering factors such as the longitudinal slope of the road and the socioeconomic stratum. The methodology focuses on six main stages: starting with the collection of population census data and GPX traces of trips made in the mode; second, analyzing the relationship between slope and speed using linear regressions for different categories of roads with data from the previous stage; third, conditioning geographic information layers with and without slope; fourth, evaluating geographic accessibility using Dijkstra's shortest path algorithm; fifth, calculating the average global accessibility and generating isochronous curve maps using the ordinary Kriging geostatistical algorithm; sixth, estimating the relationship between travel times considering the slope of the road and a base scenario without slope. The results indicate that steeper slopes significantly reduce the average speed of cyclists, which in turn increases travel times and negatively affects accessibility conditions. Additionally, it shows how topographical features, and the city sector influence the mobility of the cycling community. These findings reveal the importance of considering road slope in urban planning to generate strategies that develop efficient road infrastructure and promote the use of bicycles as a means of transport, fostering sustainable mobility. [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]

Assessing and mapping the geographical variation of soil properties is essential for precision agriculture to maintain the sustainability of the soil and plants. This study was conducted in El-Ismaillia Governorate in Egypt (arid zones), to establish site-specific management zones utilizing certain soil parameters in the study area. The goal of the study is to map out the variability of some soil properties. One hundred georeferenced soil profiles were gathered from the study area using a standard grid pattern of 400 × 400 m. Soil parameters such as pH, soil salinity (EC), soil organic carbon (SOC), calcium carbonate (CaCO3), gravel, and soil-available micronutrients (Cu, Zn, Mn, and Fe) were determined. After the data were normalized, the soil characteristics were described and their geographical variability distribution was shown using classical and geostatistical statistics. The geographic variation of soil properties was analyzed using semivariogram models, and the associated maps were generated using the ordinary co-Kriging technique. The findings showed notable differences in soil properties across the study area. Statistical analysis of soil chemical properties showed that soil EC and pH have the highest and lowest coefficient of variation (CV), with a CV of 110.05 and 4.80%, respectively. At the same time Cu and Fe had the highest and lowest CV among the soil micronutrients, with a CV of 171.43 and 71.43%, respectively. Regarding the physical properties, clay and sand were the highest and lowest CV, with a CV of 177.01 and 9.97%, respectively. Moreover, the finest models for the examined soil attributes were determined to be exponential, spherical, K-Bessel, and Gaussian semivariogram models. The selected semivariogram models are the most suitable for mapping and estimating the spatial distribution surfaces of the investigated soil parameters, as indicated by the cross-validation findings. The results demonstrated that while Fe, Cu, Zn, gravel, silt, and sand suggested a weak spatial dependence, the soil variables under investigation had a moderate spatial dependence. The findings showed that there are three site- specific management zones in the investigated area. SSMZs were classified into three zones, namely high management zone (I) with an area 123.32 ha (7.09%), moderate management zone (II) with an area 1365.61ha (78.49%), and low management zone (III) with an area 250.8162 ha (14.42%). The majority of the researched area is included in the second site zone, which represents regions with low productivity. Decision-makers can identify locations with the finest, moderate, and poorest soil quality by using the spatial distribution maps that are produced, which can also help in understanding how each feature influences plant development. The results showed that geostatistical analysis is a reliable method for evaluating and forecasting the spatial correlations between soil properties. [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]