Search

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]

[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]

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]

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]

This paper presents the findings about implementing a machine learning (ML) technique to optimize the performance of 5 G mm wave applications utilizing multiple-input multiple-output (MIMO) antennas operating at the 28 GHz frequency band. This article examines various methodologies, including simulation, measurement, and the utilization of an RLC-equivalent circuit model, to evaluate the appropriateness of an antenna for its intended applications. In addition to its compact dimensions, the proposed design exhibits a maximum gain of 10.34 dBi, superior isolation exceeding 26 dB, and a broad bandwidth of 16.56 % Centered at 28 GHz and spanning from 25.905 to 30.544 GHz. Another supervised regression machine learning technique is utilized to predict the antenna's gain accurately. Machine learning (ML) models can be assessed by several measures, such as the variance score, R square, mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), and Mean Absolute Percentage Error (MAPE). Among the six machine learning models considered, it is seen that the Gaussian Process Regression (GPR) model exhibits the lowest error and achieves the highest level of accuracy in forecasting gain. The antenna under consideration has promising qualities for its intended use in high-band 5 G applications. This is evidenced by the modelling findings obtained from Computer Simulation Technology (CST) and Advanced Design System (ADS)and the measured and projected results derived using machine learning methodologies. [ABSTRACT FROM AUTHOR]

This study addresses the challenges of hydrogen gas detection in pipelines, focusing on the highly flammable nature and low ignition energy of hydrogen. It highlights the limitations of traditional point-based detection methods and emphasizes the need for advanced safety technologies. An integrated approach combining onsite monitoring with Internet of Things (IoT) technology is proposed to enhance systematic safety management and quick leak detection in hydrogen infrastructures. The study reviews various hydrogen detection methods, emphasizing distributed temperature sensing (DTS) techniques to identify leaks through temperature variations. Over nine months of monitoring, the results indicate that DTS temperature variations are more influenced by sensor location than chamber configuration, suggesting that external DTS chamber installation is more effective for leak detection. Additionally, the study integrates Gaussian Process Regression with Machine Learning to predict temperature distribution in pipelines, providing valuable insights for future hydrogen leak detection research. • Developed new DTS technology with enhanced resolution for sensitive hydrogen leak detection. • Confirmed DTS system's reliability against IEC 61757-2-2 standards through rigorous testing. • Integrated IoT and 3D mapping in software for efficient hydrogen leak monitoring. • Found DTS temperature variations more influenced by installation location than chamber design. • Employed GPR and Machine Learning for predicting hydrogen pipeline temperature distribution. [ABSTRACT FROM AUTHOR]

The integration of chemistry poses a major bottleneck in numerical combustion modelling, as a significant amount of simulation time is consumed in the direct integration (DI) of differential equations into thermochemistry modelling. In this work, a probabilistic machine learning (ML) framework, using Gaussian processes (GPs), is developed as a chemical source term integrator to replace DI for the prediction of a H 2 /air auto-ignition case. In this context, two algorithms, namely Gaussian Process Regression (GPR) and Gaussian Process Autoregressive Regression (GPAR), are investigated. The training dataset is generated using zero-dimensional (0D) isobaric H 2 /air auto-ignition simulations in Cantera. To address the scalability issue of the GPs, the variational inducing points method is used. This method leverages a subset of the original data for training, allowing sparse approximations. The performances of the GPR and GPAR are compared to a standard artificial neural network (ANN) model. A priori comparison with direct integration shows that both GPR ( R t e s t 2 = 0. 997) and GPAR ( R t e s t 2 = 0. 998) outperform the ANNs ( R t e s t 2 = 0. 988) by capturing latent dynamics of the chemistry when working with small datasets. Additionally, GP models offer the capability to quantify the uncertainty of each prediction, providing deeper insights into the model's limitations. It is also shown that the inference with GP-based models is slower than ANNs with speed-up factors of 1.9-2.1 relative to the 0D reactor model, whereas the ANN speed-up factor goes up to 3.0. [Display omitted] • First use of a probabilistic ML framework for chemical source term prediction. • Gaussian Processes quantify uncertainty in predicted thermo-chemical states. • Probabilistic framework's strengths and limitations compared to neural networks. • Framework surpasses neural networks in data efficiency and accuracy. [ABSTRACT FROM AUTHOR]

This paper aims to apply data-driven maximum power point tracking (MPPT) techniques specifically tailored for fuel cell vehicle (FCV) supported hybrid DC microgrids to enhance the power harvesting capability of fuel cell (FC) stacks. Compared to existing MPPT techniques, the current study focuses on developing and evaluating data-driven approaches for maximum power extraction by dynamically determining the operating point of FC power sources through a Zeta converter. An in-depth analysis is conducted by considering parameters such as efficiency, tracking accuracy, response time, and robustness to variations in load demand and operating conditions. The performance results validate that the developed three-layer neural network (TNN)-based MPPT gives better performance findings than Gaussian process regression (GPR), support vector regression (SVR), decision tree regression (DTR), and bagging ensemble decision tree (BEDT). In the performance evaluation phase, a vehicular FC with a rating of 1.26 kW is designed and operated within the temperature range of 320 K to 343 K for hydrogen pressure values ranging from 1 bar to 1.8 bar. For these operational conditions, the prediction accuracy value of the proposed TNN method is 99.6% while the performance values GPR, SVR, DTR, and BEDT are 99%, 98.6%, 97.2%, and 96%. In addition, system efficiency is increased by 0.98%, 1.25%, 2.51%, and 3.02% compared to GPR, SVR, DTR, and BEDT, respectively. [Display omitted] • Developing data-driven algorithms-based MPPT techniques for vehicular FCs. • Providing advantages regarding high-speed tracking capability and tracking accuracy. • Providing stable DC bus voltage operation. • Improving system performance under dynamic load changes and operating conditions. [ABSTRACT FROM AUTHOR]

Accurate estimation of gas hydrate formation condition is crucial for many reasons. In one hand, the gas hydrate formation is a promising approach for gas separation, cold energy storage, seawater desalination, etc. On the other hand, in some industries, this phenomenon may cause some challenges, such as pipelines blockage. The current study was undertaken to develop trustworthy predictive tools for methane hydrate formation temperature (MHFT) in the presence of brines. To achieve this target, 1051 experimental data pertinent to the methane hydrate equilibrium in 26 single and multiple brines over an extensive range of operating conditions were amassed from published studies. Four simple factors, including pressure, brine concentration, salt molecular weight and salt melting temperature were defined as the input variables, and the black-box intelligent techniques, including gaussian process regression (GPR), multilayer perceptron (MLP) and radial basis function (RBF) were employed to link MHFT to the mentioned factors. A plethora of graphical and statistically-based assessments were performed to determine the accuracy level of the proposed models. While all intelligent models had excellent performances, the one established by the GPR method showed the best agreements with experimental data, and gave the AARE and R2 values of 0.14% and 99.17%, respectively, in the testing step. The foregoing model was capable of predicting MHFT over a broad range of conditions with relative deviations mostly below 0.10%. Additionally, it showed an excellent performance in describing the physical variations of MHFT versus operating factors. The authority of the analyzed databank and the presented model was asserted via the William's plot investigation. Moreover, a sensitivity analysis was undertaken in order to determine the most fundamental factors in controlling MHFT. Eventually, a simple mathematical correlation was also derived based on the white-box intelligent approach of gene expression programming (GEP), which allowed the accurate estimation of MHFT with an AARE of 0.56%. [Display omitted] • Smart predictive models were presented for methane hydrate formation condition. • 1051 methane hydrate equilibrium data in the presence of 26 brines were analyzed. • The GPR method presented the best predictions with the testing AARE of 0.14%. • The models favorably described the physical variations of MHFT. • A simple and accurate MHFT correlation was derived by the GEP approach. [ABSTRACT FROM AUTHOR]

A multistage machining process is employed to machine the blades with low stiffness. Nonetheless, machining errors can be transferred and accumulate throughout the multistage machining process, complicating the precise prediction of the final accuracy of thin-walled blades. Consequently, this paper introduces a machining accuracy prediction model for thin-walled blades that takes into account initial error. The machining error prediction model of thin-walled blades is developed using Gaussian process regression optimized by the sparrow search algorithm (SSA-GPR) with the initial contour error, depth of cut, feed per tooth, and spindle speed as inputs, and the machining error as the output. And the results show that the prediction accuracy of the SSA-GPR is 6.73 % higher than that of the Gaussian process regression (GPR), 13.73 % higher than that of the back propagation neural network (BPNN), and 32.32 % higher than that of the support vector machine regression (SVR). The influence of the initial error and milling parameters on the machining error is analyzed through the length-scales of the Gaussian kernel function. The findings indicate that the depth of cut, feed per tooth and initial error significantly affect the machining error, whereas the spindle speed has a minor impact on the machining error. Furthermore, the 3D graph based on the SSA-GPR shows that the increase of the initial error will increase the machining error of thin-walled blades. This research provides a theoretical foundation for the process optimization of thin-walled blades. • A machining accuracy prediction method considering initial error is proposed. • Combine SSA with GPR to improve the prediction accuracy of GPR. • The correlation is conveniently examined via the hyperparameters of the GPR. • The initial error significantly affects the machining error of thin-walled blades. [ABSTRACT FROM AUTHOR]

[Display omitted] • Retrieval of key mangrove traits based on Sentinel-2 surface reflectance data. • Gaussian Processes Regression (GPR) was trained on PROSAIL simulations and active learning intelligent sampling techniques. • GPR model gives insight in the most relevant bands and delivers per-pixel uncertainty interval. • Optimal GPR models were implemented in Google Earth Engine for end-user mapping over space and time. • Time series gap-filling via Whittaker smoothing enabled temporal decomposition to monitor mangrove trait dynamics. As mangrove forests are facing escalating threats from anthropogenic and natural stressors, Earth observation capabilities are providing an unprecedented view of these vital ecosystems. This study aimed to leverage the extensive archive and continuous stream of Sentinel-2 (S2) data and its integration into cloud-computing platforms to map key mangrove traits, indicative of ecosystem health and resilience. Specifically, a hybrid retrieval model implemented in Google Earth Engine (GEE) was operationalized for quantitative estimation of multiple mangrove traits from S2. For this purpose, the leaf-to-canopy radiative transfer model (RTM) PROSAIL in synergy with non-parametric Gaussian Processes Regression (GPR) were selected for hybrid retrieval models of effective Leaf Area Index (LAI e), Leaf Chlorophyll Content (C a b ), Leaf Water Thickness (C w), and Leaf Dry Matter (C m). GPR models were trained and optimized with a PROSAIL-based simulated dataset in combination with active learning sampling techniques to reduce the training dataset towards the most informative samples. Validation against in situ measurements showed high accuracy models achieved for LAI e ( R 2 = 0.693, NRMSE = 12.03 %) and Cab ( R 2 = 0.689, NRMSE = 13.29 %), while moderate performances were obtained for Cm ( R 2 = 0.597, NRMSE = 16.37 %) and Cw ( R 2 = 0.442, NRMSE = 16.66 %). The GPR models were subsequently implemented into GEE for processing of a time series data stream ranging from 2019 to 2023, together with the cloud-gap filling by applying a Whittaker smoother. Seamless maps of four key mangrove traits were generated simultaneously with per-pixel uncertainty estimation. The entire GEE-based workflow enables time series decomposition to uncover trends and seasonal dynamics. Supported by field validation, this study demonstrates a scalable approach for spatiotemporal monitoring of key mangrove traits using hybrid retrieval models via GEE implementation. These advances may contribute to national-scale monitoring in Vietnam and beyond to support mangrove ecosystem protection efforts and management thereof. [ABSTRACT FROM AUTHOR]

The thermodynamic and transport properties of hydrogen isotopologues in the solid, liquid, and gas phases are crucial for hydrogen energy exploitation, such as the design of the fuel cycle of nuclear fusion reactors. However, experimental data for tritium-containing species are often not available. Alternatively, path integral (PI) simulation can evaluate hydrogen properties taking into account nuclear quantum effects; however, concerns about its reliability are present. This study proposes a method of Gaussian process regression (GPR) using both experimental and PI simulation data to obtain practically plausible estimates for all isotopologues. Using liquid viscosity and diffusivity as test cases, we demonstrate that the present method has high and robust predictive performance. The method has broad applicability and can also be used to design experiments and calculations to efficiently improve the regression model, and thus is expected to contribute to enhancing the availability and reliability of the hydrogen isotopologue property database. [Display omitted] • Experimental data on hydrogen properties are scarce for tritium-containing species. • Reliability of path-integral simulations is still limited. • Gaussian process regression can yield plausible predictions for all isotopologues. • The regression model can be efficiently improved using estimated model uncertainty. [ABSTRACT FROM AUTHOR]

[Display omitted] Skin tension plays a pivotal role in clinical settings, it affects scarring, wound healing and skin necrosis. Despite its importance, there is no widely accepted method for assessing in vivo skin tension or its natural pre-stretch. This study aims to utilise modern machine learning (ML) methods to develop a model that uses non-invasive measurements of surface wave speed to predict clinically useful skin properties such as stress and natural pre-stretch. A large dataset consisting of simulated wave propagation experiments was created using a simplified two-dimensional finite element (FE) model. Using this dataset, a sensitivity analysis was performed, highlighting the effect of the material parameters and material model on the Rayleigh and supersonic shear wave speeds. Then, a Gaussian process regression model was trained to solve the ill-posed inverse problem of predicting stress and pre-stretch of skin using measurements of surface wave speed. This model had good predictive performance (R 2 = 0.9570) and it was possible to interpolate simplified parametric equations to calculate the stress and pre-stretch. To demonstrate that wave speed measurements could be obtained cheaply and easily, a simple experiment was devised to obtain wave speed measurements from synthetic skin at different values of pre-stretch. These experimental wave speeds agree well with the FE simulations, and a model trained solely on the FE data provided accurate predictions of synthetic skin stiffness. Both the simulated and experimental results provide further evidence that elastic wave measurements coupled with ML models are a viable non-invasive method to determine in vivo skin tension. To prevent unfavourable patient outcomes from reconstructive surgery, it is necessary to determine relevant subject-specific skin properties. For example, during a skin graft, it is necessary to estimate the pre-stretch of the skin to account for shrinkage upon excision. Existing methods are invasive or rely on the experience of the clinician. Our work aims to present an innovative framework to non-invasively determine in vivo material properties using the speed of a surface wave travelling through the skin. Our findings have implications for the planning of surgical procedures and provides further motivation for the use of elastic wave measurements to determine in vivo material properties. [ABSTRACT FROM AUTHOR]

• In this study, we conducted a statistical analysis of foF2 and TEC data under both ionospheric quiet and disturbed conditions, employing the ionospheric slab thickness model. • The utilization of Kriging with external drift (KED) in generating maps has enhanced their realism. • The inclusion of foF2 data from the map's periphery has resulted in the overall stabilization of the map. • Based on our findings, we can conclude that the correlation distance between ionospheric characteristics should not exceed the range of 120–300 km. The importance of this study lies in its contribution to the field of ionospheric science, particularly in the monitoring and prediction of ionospheric parameters. This study focuses on comparing two techniques for spatio-temporal kriging of critical ionospheric parameters, namely the F2 layer critical frequency (foF2) and Total Electron Content (TEC), under both quiet and disturbed ionospheric conditions. The first technique, Ordinary Kriging (OK), relies solely on foF2 data, while the second technique, Kriging with External Drift (KED), incorporates the dynamic relationship between foF2 and TEC data to improve the interpolation process. This study demonstrates how KED, which utilizes dynamic secondary information, offers advantages over OK. By simultaneously monitoring the ionosphere from a single ionosonde station and collecting data from visible GPS satellites, KED enhances the accuracy of spatial structural analysis, enabling more precise estimations of ionospheric characteristics across interpolation grid nodes. The research highlights that the non-uniform distribution of ionosonde stations, especially in regions with limited foF2 data, can benefit from KED's incorporation of TEC data. Additionally, the study reveals the potential for improving TEC maps by assimilating foF2 data located at the periphery of the observation area. Furthermore, the paper discusses the determination of semivariogram structures for both foF2 and TEC data, emphasizing the spatial correlations between data points. These findings contribute to a better understanding of ionospheric behavior and the potential for enhanced ionospheric modeling. [ABSTRACT FROM AUTHOR]

Utilizing performance prediction models to predict students' graduation outcomes can offer crucial data support for academic early warning systems in higher education institutions, potentially becoming an essential tool for enhancing teaching quality. Therefore, in order to build a more accurate performance prediction model, a performance prediction method based on Gaussian process regression is proposed, and a series number of random experiments are carried out on the real performance data of seven majors such as broadcast and television directing major in a university to verify the effectiveness and feasibility of the method. The experimental results show that the proposed method has higher prediction accuracy and stability, and can provide effective reference for improving teaching quality. [ABSTRACT FROM AUTHOR]

The water hammer, resulting from sudden valve closures or similar operations, is a primary cause of leakage and damage in fluid-conveying pipe systems. This work aims to investigate the reliability sensitivity of fluid-conveying pipes under the water hammer. A reliability model for the fluid-conveying straight pipe, involving uncertainty and fluid-structure interaction, is developed based on the stress-strength interference theory. Then the method of characteristics is employed to analyze the nonlinear behaviors of the pipe. To avoid excessive model evaluations, the Kriging surrogate strategy is used to evaluate rapidly the statistics of nonlinear responses. Furthermore, the Kriging model coupled with the single-loop Monte Carlo simulation is presented for estimating reliability sensitivity indices. The accuracy of results is verified by the Monte Carlo simulation. The results reveal that the proposed method is feasible for the reliability sensitivity analysis of fluid-conveying pipe under the water hammer. Moreover, the wall thickness has the most obvious influence on stress failure, followed by the inner radius, while the pipe length, Young's modulus, density of the pipe material, and Poisson ratio show a low effect. This work can not only guide the safety design of pipe but also enrich the theory and application of statistical analysis and reliability sensitivity evaluation for liquid-conveying pipe systems. • A reliability model for water hammer-induced failure of fluid-conveying pipe is developed. • The reliability model is proposed, incorporating uncertainty and fluid-structure interaction. • The Kriging-based strategy is employed to estimate the response and reliability sensitivity of the pipe. • Different input variables have diverse effects on the nonlinear behavior and reliability of the pipe. [ABSTRACT FROM AUTHOR]

Phenolic compounds constitute an essential part of the plant's secondary metabolites and play a crucial role in ecosystem functioning, including nutrient cycling and plant defence against biotic and abiotic stressors. Quantifying the phenolic compounds across global biomes is important for monitoring the biological diversity and ecosystem processes. However, our understanding of foliar phenolic compounds remains limited, particularly regarding how they vary among temperate tree species and whether their variation and absorption features can be assessed using spectroscopy at the leaf level. In this study, we examined the relationships between the spectral properties of fresh leaves from temperate tree species and two ecologically important phenolic compounds (i.e., total phenol and tannin). We sampled the leaves of four dominant tree species (i.e., English oak, European beech, Norway spruce, and Scots pine) across two European temperate forest sites. Continuum removal was applied to the leaf spectra to enhance the assessment of the subtle absorption features that correlate with the phenolic content. Total phenol and tannin concentrations were estimated by comparing the performance of two empirical methods, namely partial least squares regression (PLSR) and Gaussian processes regression (GPR). Our results showed a large range of variation in total phenol and tannin between temperate tree species (p < 0.05). Spectral analysis revealed persistent and distinct phenolic absorption features near 1666 nm in the spectra of English oak, Norway spruce and European beech, whereas Scots pine exhibited a weaker absorption feature near 1653 nm. Regression results showed that both PLSR and GPR accurately estimated total phenol and tannin across temperate tree species, with informative bands for predicting these two traits well-corresponded between the two models utilised. Our results also suggested that total phenol was overall more accurately predicted than tannin regardless of employed methods. The most accurate estimations were achieved using PLSR with the continuum-removed SWIR spectra (total phenol: R 2=0.79, NRMSE=9.95%; tannin: R 2=0.59, NRMSE=14.53%). Testing the models established for individual species or forest types revealed variability in their prediction performances, with these specific models demonstrating lower accuracy (R 2=0.47–0.69 and 0.34–0.54 for total phenol and tannin, respectively) compared to the cross-species model. Our study extends the understanding of absorption features of phenolic compounds in common temperate tree species and demonstrates the potential for a generalised spectroscopy model to predict foliar phenolic compounds across temperate forests. These findings provide a foundation for mapping and monitoring phenolic compounds in temperate forests at the canopy level using airborne and spaceborne imaging spectroscopy. [ABSTRACT FROM AUTHOR]

The poor absolute positioning accuracy of industrial robots has limited their application in fields such as aerospace manufacturing. To address this issue, the spatial grid compensation method has been proposed as an effective solution. In this paper, we propose a sampling method based on three-dimensional discrete point space circular fitting for grid points to significantly reduce the sampling workload and improve compensation accuracy compared to traditional joint space grid compensation methods. Additionally, we use the Kriging interpolation algorithm instead of the inverse distance weighting (IDW) algorithm for spatial interpolation prediction of pose error. Based on this, the proposed sampling and interpolation prediction method in this paper was verified on a Comau NJ500–2.7 manipulator equipped with a fiber-laying end effector. The experimental results demonstrate that using our proposed sampling method yields pose data of grid points that have only a small deviation from directly sampled results and are only slightly higher than the robot's repeat positioning accuracy. Moreover, our proposed method can significantly reduce the sampling workload by 60% under the experimental conditions of this study (sampling 10 groups of data within 90 degrees range), with increasing sampling range leading to more obvious efficiency improvements. Finally, we show that compared to the IDW algorithm, the Kriging interpolation algorithm yields better results and improves the mean absolute positioning accuracy of robots after compensation by 30%. [ABSTRACT FROM AUTHOR]

Monoscopic deflectometry is a powerful and flexible measuring method for optical surfaces. Precise workpiece positioning is of significance because it directly determines the reliability of the measurement results. But unfortunately, the need for additional facilities severely limits the application of the monoscopic deflectometry. In this paper, a self-positioning method is proposed by combining the ray-tracing and Gaussian process regression. The phases retrieved from the captured images are parameterized using the Zernike polynomials. Then a training model is established for describing the relationship between the Zernike coefficients and the workpiece positions. Workpiece positioning is implemented by computing the associated joint Gaussian distribution. Experimental results show that the positioning accuracy of optical surfaces is comparable with that of a coordinate measuring machine, with a deviation less than 8 × 10−4° in tilt and 4 μm in translation. This greatly simplifies the sophisticated operation and improves the practicability and efficiency of deflectometric measurements. • Workpiece positioning for monoscopic deflectometry can be achieved without auxiliary instruments. • The retrieved phases are parameterized so that the position-independent error can be suppressed. • The required training samples can be conveniently obtained by numerical simulations. [ABSTRACT FROM AUTHOR]

A Kriging-based optimization method is proposed and applied to the design optimization of stacking sequence for quadrilateral laminated composite plates with curved edges. The vibration model for evaluating the fundamental frequency of plates is constructed using the first-order shear deformation theory (FSDT). Then a Kriging surrogate model is used to approximate the vibration model to improve design optimization efficiency. A starting strategy based on the fitting quality coefficient is proposed to determine when to use the expected improvement (EI) infill criterion during the sequential sampling process. Three widely used correlation functions are dynamically selected during the Kriging modeling process to improve the generalization ability of model. In addition, a hybrid whale optimization algorithm (HWOA) is employed to optimize the Kriging hyperparameters, maximize the mean squared error (MMSE), the Expected Improvement (EI) function, and the Kriging predictor. Finally, a comparison is made with the classical DACE toolbox, the optimization procedure using the MMSE criterion and the standard one-shot Kriging-based optimization procedure. Results have demonstrated the effectiveness of the proposed method and clearly indicate that the required number of samples for optimization can be effectively reduced when starting to use the EI infill criterion at the fitting quality coefficient larger than 0.85. [ABSTRACT FROM AUTHOR]

This paper endeavors to utilize the numerical modeling method to evaluate the energy, economic, and environmental performances of a new hybrid PV-FC system for green hydrogen and electricity production. The proposed system consists of photovoltaic panels, fuel cells, an electrolyzer, a converter, and a hydrogen storage tank. A robust techno-enviro-economic (3E) analysis is conducted through comprehensive modeling for the system components using MATLAB/Simulink®. In this validated model, the essential parameters have been calculated: PV plant power, area and efficiency, electrolyzer efficiency, flow rate and power, stack power, area and efficiency, total LCOE of the integrated components, and CO 2 emission reduction. Moreover, the NSGA-II coupled with TOPSIS decision-making approach and Gaussian Process Regression machine learning method with selection kernel function are also utilized as a novel inclusion for the prediction and optimization of the 3E performances of this hybrid system. To obtain a multidimensional view of the optimization, six key decision variables of total stack power, fossil fuel-based generator energy, total CO 2 emissions coming from hydrogen production, total FC system voltage, module area, and number of PV modules have been adopted. The optimization problem encompasses maximizing the total fuel cell stack power and carbon emission reduction, while simultaneously minimizing the total stack area and levelized cost of energy. The simulation outcomes reveal that the stack can reach its maximum output power of 350 kW when operating temperatures are between 40 °C and 55 °C and there are more than 380 cells in the stack. Also, the LCOE was found to be less than $2/kWh for solar radiation above 250 W/m2 and PV outputs reaching 100 W. Further, Increasing FCs from 10 to 400 reduces CO 2 emissions by roughly 13% at 100 °C. Ultimately, the optimal configuration of the system yields stack power of 1589 kW, a total stack area of 269.9 m2, and total CO 2 emission reduction of 1268 ton CO2 , respectively. • Robust 3E analysis using MATLAB-based techno-environmental-economic study. • ML tool using GPR and GA optimization method used for performance optimization. • LCOE is less than $2/kWh for solar radiation above 250 W/m2 and 100 W PV output. • The PVFCEHST model exhibits a high degree of reliability and a robust integrated model. • FC power efficiency reaches 60% when operational temperature is between 40 and 55 °C. [ABSTRACT FROM AUTHOR]

This study presents an integrated framework of machine learning models (Artificial Neural Network, Ensembled Learning Tree, Support Vector Machine, and Gaussian Process Regression) and particle swarm optimization (PSO) to predict and optimize hydrogen production from SCWG using sewage sludge characteristics and process parameters. According to the results, ELT-PSO is preferred for forecasting hydrogen yield (Coefficient of determination (R2) = 0.997, Root Mean Square Error (RMSE) = 0.093), and it is highly suggested for handling complex variable-target correlation. However, Support Vector Machine (SVM) performed poorly, with R2 = 0.83 and RMSE = 2.28. According to SHAP feature importance Temperature, Carbon, Hydrogen, and Pressure are among the parameters that have strong impact. In addition, by adjusting the ML hyperparameters, optimization method (PSO) was used to maximize H2 yield. The optimized ELT-PSO model was utilized to establish a Graphical User Interface that made it simple to calculate H2 yield. [Display omitted] • ML with PSO used for prediction and analysis of H2 yield from SCWG. • PCC show temperature, oxygen, hydrogen, and volatile matter impact significantly. • ELT-PSO performed better than other machine learning optimization integrated model. • GUI is developed for H2 yield prediction for ease in the process. [ABSTRACT FROM AUTHOR]

The study aimed to present a fluidized bed reactor filled with 50% platinum catalytic beads and 50% quartz sand for syngas generation via the partial oxidation of dimethyl ether (DME). For obtaining useful information, experiments were carried out using Taguchi orthogonal array method, which cut test run by 75.3%, with the results being used for constructing the Kriging surrogate model. The model was then modified to reduce the mean square error. It is validated that the model can predict the results reasonably well. The outcome shows that the proposed reactor can self-sustain the syngas reforming reaction without incurring extra heat for reactants preheating. In the operation region, the results show that the start-up temperature is most negligible in hydrogen generation. The yield rate of hydrogen increases in sync with the increase of oxygen's molar ratio and DME, thanks to higher reaction temperature. The results also suggest that the higher the molar ratio of oxygen and DME, the more significant the reverse water shift reaction. Playing a key role in the fluidized bed in the proposed reactor for hydrogen generation, the normalized velocity must be at a proper level, in order to induce bubbling fluidization without causing a lower hydrogen yield, the latter due to the short residence time of reaction caused by excessive velocity. The sensitive analysis of independent variables also proved the inference from the measured results. By comparing with the literature, the performance of the proposed reactor in the present study shows a reasonably well performance. Given focused hydrogen generation, the study's findings can be used as a basis for evaluating DME as a hydrogen carrier and the proposed fluidized bed reaction. • A novel reactor filled with 50% quartz sand & 50% Pt catalytic beads is proposed. • The reactor does not need additional heat to sustain gas reforming reaction. • The surrogate model estimates the yield products of gas reforming fairly well. • The normalized velocity in the reactor dominates the syngas generation. • The demonstrated novel fluidized bed demonstrates a reasonably well performance. [ABSTRACT FROM AUTHOR]

In this paper, we develop surrogate models that can replace expensive predictive models and account for uncertainties in real-time treatment planning for irreversible electroporation of liver tumors. Standard non-intrusive surrogate modeling techniques that account for the model uncertainty and reduce the computational cost, such as polynomial chaos expansion and Gaussian process regression with conventional kernels, often do not capture the true physical behavior of the treatment outcome as required in the context of treatment planning. We improve the Gaussian process regression model by modifying the kernel function to a non-stationary Gibbs kernel with a support vector machine-based classifier in its length scale definition. This proposed model is compared with the standard surrogates in terms of their performance and accuracy. Our model is able to accurately replicate the behavior of the biophysics-based predictive model. There is a decrease of at least 81% in the overall root-mean-square error for treatment outcome when compared to the Gaussian process regression model with conventional kernels. Furthermore, we illustrate the application of the proposed surrogate model in treatment planning to address a voltage optimization problem for complete tumor ablation. Surrogate-assisted treatment planning exhibited good performance while maintaining similar levels of accuracy in comparison to treatment planning based on biophysical models. Finally, the effect of uncertainty in tissue electrical conductivities on the optimal voltage value is discussed. • Gaussian process regression-based surrogates can replace physics-based predictive models for irreversible electroporation. • Gibbs kernel with a support vector machine-based classifier is able to model relative tumor ablation for treatment planning. • Numerical illustrations indicate good accuracy with the use of the proposed kernel when compared to popular kernel choices. • Surrogate-assisted treatment planning was performed to solve a voltage optimization problem for complete tumor ablation. • The effect of uncertainty in electrical conductivities on the optimal voltage for irreversible electroporation is studied. [ABSTRACT FROM AUTHOR]

The electrochemical impedance spectrometry (EIS) measurement coupled with equivalent-circuit (EC) model is widely used to monitor the health status of proton exchange membrane fuel cell (PEMFC). However, limited studies are available to investigate the impact of measurement uncertainty on the evaluation of EC parameters. To fill this gap, this study aims at establishing a machine learning-based method to improve identification of EC parameters based on EIS measurement for PEMFC health monitoring. This computational method was employed to estimate the uncertainty of EC parameters with regard to oxygen stoichiometry that could be quantified by means of charge transfer resistance and limited current density. Gaussian process classification and combined sampling methods together with theoretical calculation were adopted to generate the synthetic data with an R2 of 0.991 to determine the measurement uncertainty of EC parameters. The effectiveness of this computational approach was validated against high-level noisy experimental data. The result shows that this approach can effectively reduce the variances of EC parameters from over 400% to less than 30% and satisfactorily quantify the measurement uncertainty within 35 s. The introduction of synthetic data allows Gaussian process regression to predict the most reliable EIS spectra in the absence of measured oxygen stoichiometry with the computational time optimized. This study expands our capacity in improving the PEMFC health management via machine learning-based computational methods. [Display omitted] • Studied EIS measurement uncertainty via machine learning (ML) methods. • Adopted surrogate equivalent circuit model to synthesize EIS data. • Quantified measurement uncertainty with regard to oxygen stoichiometry. • Discussed effect of synthetic data as training data on the ML performance. [ABSTRACT FROM AUTHOR]

Sustainable agricultural growth and management reduces over-utilization of farm resources and squeezes risk of negative impacts on environment. Monitoring continuous crop growth and health under various conditions at different spatio-temporal resolutions is a key to assess yield stability, crop diversity, adaptability, mitigation for stress and response. The quantification of crop biophysical and biochemical variables spatially from remotely sensed data with help of spectroscopic methods provide a reliable discerning information in the context of crop foliar condition like leaf greenness, senescence, canopy density, crop growth, stress and eco-physiological processes. Airborne Visible/Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) airborne hyperspectral data offers high spatial and spectral resolution giving a unique advantage and opportunity to test retrievals of crop biophysical (BP)-biochemical (BC) variables under varying conditions over different types of crops. A hybrid inversion of leaf-canopy Radiative Transfer model – PROSAIL-D complemented with use of data driven nonlinear non-parametric methods which offer simplicity, fastness, reliability and competency is a powerful method to retrieve crop biophysical and biochemical variables. The Hyperspectral band (feature) selection is a computationally cost efficient method to overcome data redundancy in high dimensional correlated input spectral bands. The determination of optimum subset or combination of hyperspectral bands specific to retrieval of vegetation properties (including canopy effects) determined using feature selection algorithm for regression-based retrievals are active research topic unlike classification problems in which it is more common. A band selection algorithm based on Gaussian Processes Regression was used to choose most sensitive bands from in-situ biophysical-biochemical measurements and crop spectral signatures collected for analysis in two different agricultural regions: Raichur (Karnataka) and Anand (Gujarat) districts of India representing diverse landscapes, heterogeneous crop canopies and agro climatic settings. The retrieval algorithm for AVIRIS-NG image employed a decision tree ensemble algorithm Canonical Correlation Forests using the optimum subset of bands for retrieval of targeted crop variable. Validation of retrieved crop variables were done using in-situ ground observations collected over heterogeneous diverse crop landscape. The results showed chlorophyll (RMSE = 6.61 µg cm−2), equivalent water thickness (RMSE = 0.002 cm), leaf area index (RMSE = 0.35 m2/m−2) and dry matter (RMSE = 0.003 g cm−2), carotenoid (RMSE = 14.3 µg cm−2), anthocyanin (RMSE = 12.92 µg cm−2) retrieved with better accuracies. The results obtained in context of feature (band) selection approach for Radiative Transfer model inversion show overlapping of sensitive spectral bands of chlorophyll-ab, carotenoid and anthocyanin especially between narrow spectral range 480 to 560 nm as predominant reason for decreased accuracies of anthocyanin and carotenoid compared to other variable. This poses a limitation as well as opportunity for further research in signal separation in context of feature selection approach especially in context of broader spectral bandwidths. It also sets ground for further development of feature selection algorithms that use hybrid regression methods customized for crop specific traits. [ABSTRACT FROM AUTHOR]

In wastewater treatment processes, lack of hardware sensors together with unacceptable dynamics, strong nonlinearity and large time delay often leads to a large number of key variables that are difficult to measure online accurately and timely, then frustrate safe operations of the processes. To accurately and timely capture the short-term behavior changes and trend development of critical variables, a novel neural network based soft-sensing model is proposed to take full use of multi-task learning, direct multi-step prediction strategy and evolutionary algorithm to formulate a novel multi-task multi-step evolution (MTMSE) neural network. Firstly, single-output MTMSE (SO-MTMSE) neural network is used to realize the dynamic monitoring of a single variable. Moreover, by considering the spatiotemporal interaction among the data, the model is extended to multi-output MTMSE (MO-MTMSE) neural network to simultaneously realize multi-step prediction of multiple variables, thus providing a desired reference for optimizing the wastewater treatment processes. Finally, the proposed model is applied to the benchmark simulation model 2 (BSM2) and a full-scale wastewater treatment plant in Shenzhen. And the results show that the proposed dynamic soft sensor model outperforms the standard methods, such as autoregressive moving average model (ARMA) and multiple output gaussian process regression (MGPR). [ABSTRACT FROM AUTHOR]

Biological age and brain age estimated using biological and neuroimaging measures have recently emerged as surrogate aging biomarkers shown to be predictive of diverse health outcomes. As aging underlies the development of many chronic conditions, surrogate aging biomarkers capture health at the whole person level, having the potential to improve our understanding of multimorbidity. Our study investigates whether elevated biological age and brain age are associated with an increased risk of multimorbidity using a large dataset from the Midlife in the United States Refresher study. Ensemble learning is utilized to combine multiple machine learning models to estimate biological age using a comprehensive set of biological markers. Brain age is obtained using Gaussian processes regression and neuroimaging data. Our study is the first to examine the relationship between accelerated brain age and multimorbidity. Furthermore, it is the first attempt to explore how biological age and brain age are related to multimorbidity in mental health. Our findings hold the potential to advance the understanding of disease accumulation and their relationship with aging. [ABSTRACT FROM AUTHOR]

[Display omitted] • We derived a mathematical relationship between the input and output data. • Design variables in this study are SVF, and temperature and objective function is TC of HNF. • 10 types of regressors are utilized for regression operations. • The values predicted by the MPR algorithm were compared with the experimental data. • There is less residual dispersion in the MPR algorithm and these residuals are close to zero. For conducting an analysis of the experimental data, it is imperative to establish a mathematical correlation between the input and output variables. This entails executing a curve fitting or regression procedure on the data, for which numerous methodologies exist. Within the scope of present investigation, the design variables encompass the solid volume fraction (φ) and temperature. Thermal conductivity (TC) of MWCNT-CuO-CeO 2 (20-40-40)/water hybrid nanofluid (HNF) is also the objective function. Ten different types of regressors are utilized for regression operations which are Multiple Linear Regression (MLR), Decision Tree (D-Tree), Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), Extreme Learning Machine (ELM), Radial Basis Function (RBF), Adaptive Neuro-Fuzzy Inference System (ANFIS), Gaussian Process Regression (GPR), Multivariate Polynomial Regression (MPR) and Group Method of Data Handling (GMDH). Once the governing equations linking the design variables and the objective functions have been established, these equations can be employed to forecast the simulation data. By substituting the above input values into the equations, we can calculate the corresponding output values for the TC of the HNF. The results obtained from the MPR algorithm are compared to the experimental data. For the GPR, MLR, D-Tree, ELM, MPR, MLP, RBF, SVM, ANFIS, and GMDH algorithms, the maximum margin of error is found to be 0.031, 0.02579, 0.028946, 0.033889, 0.01568, 0.02515, 0.03485, 0.03, 0.0385, and 0.0178, respectively. Moreover, the kernel density estimation diagram indicates the gap between experimental data and data predicted by regression algorithms. Finally, it is evident that the MPR algorithm demonstrates to have a reduced residual dispersion, with the residuals approaching zero. [ABSTRACT FROM AUTHOR]

The tool wear monitoring (TWM) system plays an increasingly important role to ensure high quality finishing and system safety in advanced CNC machining process. The pure data-based TWM approaches generally needs to develop complex machine learning models and require massive sensory data to learn the models to reach high monitoring accuracy, while the physics-based tool wear models are simple but hard to adapt to varied working conditions. In order to incorporate the benefits of both methods, a novel physics-informed Gaussian process model is developed to predict the tool wear. Different from the traditional approaches, three tool wear physical models are introduced to develop the physics-informed Gaussian process regression (PB-GPR) model. The wear model is applied to constrain the mean function of the Gaussian process, so that the PB-GPR is more in line with the actual tool wear. At the same time, the model can initiate small data training to meet limited tool wear labels in practice, and then update the model with new measurements. Multi-sensor signals are collected and multi-domain features are extracted for the model learning. The proposed approach is validated from high speed milling experiments. The results show a significant performance improvement including tool wear prediction accuracy and robustness in extrapolation compared to the conventional machine learning methods. • Propose a novel approach to explore the benefits both of physics and data methods. • Develop a physics-based Gaussian process regression model to predict the tool wear in a long term. • The model can be updated online and is effective for unexpected factors during machining process. • The model can provide high prediction accuracy and uncertainty estimation for tool wear monitoring. [ABSTRACT FROM AUTHOR]

Numerous studies on sampling methods have been conducted to balance the inspection efficiency and accuracy of coordinate measuring machines (CMMs). However, almost all existing methods only take into account the information from the processed surface during the reconstruction process. To address this limitation, an adaptive sampling method based on co-kriging method is proposed, according to the characteristics of the interpolation reconstruction method, we treat certain feature points on the surface as anchor points and determine the distribution of other measurement points through iteration. In the reconstruction process, we employ the co-kriging interpolation method and combine extra information of the model surface to enhance the reconstruction accuracy. Through simulations and actual measurements of processed surfaces, we compare the proposed method with other algorithms. The results indicate that our method is particularly suited for complex surfaces with a limited number of measurement points, and can substantially reduce the reconstruction error when the number of measurement points is the same. • A method using CAD model information has been proposed, which improves reconstruction accuracy without additional time cost. • An adaptive sampling method based on co-kriging interpolation has been proposed. • This method has a high degree of scalability, compensating of CAD information is effective for any adaptive method. • The proposed method can significantly improve inspection accuracy, especially when there are limited measurement points. [ABSTRACT FROM AUTHOR]

Uncertainty quantification (UQ) tasks, such as sensitivity analysis and parameter estimation, entail a huge computational complexity when dealing with input-output maps involving the solution of nonlinear differential problems, because of the need to query expensive numerical solvers repeatedly. Projection-based reduced order models (ROMs), such as the Galerkin-reduced basis (RB) method, have been extensively developed in the last decades to overcome the computational complexity of high fidelity full order models (FOMs), providing remarkable speed-ups when addressing UQ tasks related with parameterized differential problems. Nonetheless, constructing a projection-based ROM that can be efficiently queried usually requires extensive modifications to the original code, a task which is non-trivial for nonlinear problems, or even not possible at all when proprietary software is used. Non-intrusive ROMs – which rely on the FOM as a black box – have been recently developed to overcome this issue. In this work, we consider ROMs exploiting proper orthogonal decomposition to construct a reduced basis from a set of FOM snapshots, and Gaussian process regression (GPR) to approximate the RB projection coefficients. Two different approaches, namely a global GPR and a tensor-decomposition-based GPR, are explored on a set of 3D time-dependent solid mechanics examples. Finally, the non-intrusive ROM is exploited to perform global sensitivity analysis (relying on both screening and variance-based methods) and parameter estimation (through Markov chain Monte Carlo methods), showing remarkable computational speed-ups and very good accuracy compared to high-fidelity FOMs. [ABSTRACT FROM AUTHOR]

Hyperspectral remote sensing has emerged as an efficient tool to quantify the spatial and temporal variations in crop foliar nutrients, thus reducing the burden on in-situ tissue sampling and traditional chemical assays. However, the physical mechanism of hyperspectral remote sensing of foliar nutrients is under-explored, especially for those lacking absorption features. Using four-year data collected from a cranberry farm, we demonstrate the capacity of leaf and imaging spectroscopy to quantify a comprehensive set of crop foliar nutrients, including seven macronutrients (N, P, K, Mg, Ca, S, Na) and five micronutrients (Fe, Mn, B, Cu, Zn). Specifically, we: 1) compared the performance of four data-driven approaches to estimate foliar nutrients at both leaf and canopy scales, including partial least square regression (PLSR), support vector regression (SVR), Gaussian process regression (GPR) and random forest regression (RFR); and 2) explored the physical basis of hyperspectral remote sensing of foliar nutrients. Our results showed that: 1) at leaf scales linear approaches PLSR and SVR performed best for nine nutrients (P, Mg, Ca, S, Na, Fe, B, Cu and Zn), whereas nonlinear approaches GPR and RFR performed best only for three nutrients (N, K and Mn); 2) at canopy scales no data-driven approach significantly outperformed others; 3) the best modelling accuracy varied with foliar nutrients (leaf scales: R2 from 0.30 to 0.93 and RRMSE from 9 to 51%; canopy scales: R2 from 0.15 to 0.81 and RRMSE from 7 to 37%). The physical basis of hyperspectral remote sensing of foliar nutrients was mainly attributed to their strong correlations with leaf compounds that have apparent absorption features. More specifically, at leaf scales the correlation between foliar nutrients and LMA (leaf mass per area) was leveraged by models to predict foliar nutrients from leaf spectra; at canopy scales the correlation of foliar nutrients with leaf chlorophyll and canopy LAI (Leaf area index) was leveraged by models to predict foliar nutrients from canopy spectra. This study revealed the importance of trait correlations in predicting foliar nutrients, and improved our understanding of the physical mechanisms in hyperspectral remotes sensing of foliar nutrients. [ABSTRACT FROM AUTHOR]

• A DC-Gaussian process regression model is used to the prediction of Dst index. • DC-GPR model has the best stability among the three models among DC-GPR, DC-SVM, and DC-NN models • DC-GPR model exhibits the better forecasting performance than DC-SVM and DC-NN models in Dst forecasting. In this paper we apply a class of Bayesian machine learning model, Gaussian Process Regression, to the prediction of Dst index by using 80 intense geomagnetic storms data (Dst ⩽ - 100 nT) from 1995 to 2014. The purpose of this paper is to compare the performance of Gaussian process regression model with Support Vector Machine model combined together with Distance Correlation (DC-SVM) and Neural Network model combined together with Distance Correlation (DC-NN) (Lu et al., 2016). For comparison, we estimate the correlation coefficients (CC), the RMS errors, the absolute value of difference in minimum Dst (Δ Dst min ) and the absolute value of difference in minimum time (Δ t Dst ) between observed Dst and predicted one.In order to compare the prediction effects and the generalizability of the three models to magnetic storm events, we combined 70 intense magnetic storm events and 10 super large magnetic storm events into one group. It is shown that DC-GPR model exhibits the better forecasting performance than by DC-SVM model and DC-NN model in magnetic storm. The CC, the RMS errors, the Δ Dst min , and the Δ t Dst of GPR are 0.65, 35.45 nT , 16.12 nT and 1.16 h , respectively. [ABSTRACT FROM AUTHOR]

The integration of machine learning technology into ionospheric prediction has emerged as a burgeoning field of research. However, several challenges still exist, such as the disregard of delays in real-world data acquisition, variations in accuracy due to different input data and methods. In this study, we present an ionospheric Gaussian process regression (GPR) model with multiple input parameters to forecast global ionospheric total electron content (TEC). We assess two solutions based on GPR model that leverage different ionospheric data, namely the vertical TEC (VTEC) and spherical harmonic coefficients (SHC) prediction solutions. Our findings demonstrate that both GPR models exhibit strong accuracy and stability. Specifically, for 1-day-ahead-predicted global ionospheric maps (GIMs) in 2015 year and 2019 year, the root mean square error (RMSE) of the SHC prediction solution is 4.343 TECU and 1.702 TECU, respectively, while the VTEC prediction solution has RMSE values of 4.321 TECU and 1.673 TECU. Moreover, in high and low solar activity, over 29% and 68% of the absolute residuals are within 1.0 TECU, respectively. Furthermore, we compare the GPR model with conventional methods (such as Adaptive Autoregressive Model (AAR)) and observe that the RMSE of the GPR model is lower than that of the AAR model for GIMs predicted under different solar and geomagnetic activities, with a difference ranging from 0.2 to 0.4 TECU. In addition, the GPR model can provide prediction intervals for the predicted values. These intervals are typically represented using the mean and standard deviation, where the mean represents the predicted value and the standard deviation represents the uncertainty associated with the prediction. Prediction intervals can assist users in understanding the uncertainty of the model's predictions. [ABSTRACT FROM AUTHOR]

• Precise predictive models for CO 2 frosting temperature were developed. • Machine learning algorithms of GPR and MLP were utilized for modeling. • The novel models showed excellent results for different natural gas mixtures. • The models provided excellent physical trends under different operating conditions. • The most effective operating factors on frosting temperature were identified. In this study, universal and precise predictive models for CO 2 frosting temperature in different natural gas mixtures were developed employing the machine learning algorithms of multilayer perceptron (MLP) and gaussian process regression (GPR). The models were verified by an extensive databank including 430 experimental samples collected from 7 published sources, enveloping a broad range of conditions in methane/CO 2 binary mixtures as well as the ternary mixtures of methane/CO 2 /ethane and methane/CO 2 /nitrogen. Both GPR and MLP models exhibited excellent predictions with total average absolute relative errors (AAREs) of 0.16% and 0.42%, and R2 values of 99.80% and 99.38%, respectively. The novel models use only 4 simple adjusted parameters, and they were found to be applicable for both binary and ternary mixtures with high precisions. In addition, the effects of each operating parameter on frosting temperature were studied, and the new models showed excellent physical trends. Subsequently, in order to provide more insight about the most effective factors on frosting temperature, a sensitivity analysis based on the present databank was performed. [ABSTRACT FROM AUTHOR]

• An improved multi-fidelity unsteady aerodynamic model based on Hierarchical Kriging is proposed. • Uncertainty estimation is allowed by the Hierarchical Kriging. • The proposed model improves accuracy while allowing error estimation. • An active learning strategy is developed that balances accuracy and cost. By fusing aerodynamic data from multiple sources, multi-fidelity methods can well balance model accuracy and computational cost. To extend multi-fidelity models for predicting unsteady aerodynamics with uncertainty estimation, an improved modelling framework based on the Hierarchical Kriging (HK) is proposed for nonlinear aerodynamic reduced-order modelling. This aerodynamic modelling framework is achieved by a two-stage modelling strategy. In the first stage, using the current and time-delayed low-fidelity aerodynamic load and pitching motion as input, a linear regression model is built to achieve preliminary aerodynamic prediction. In the second stage, the current and time-delayed preliminary prediction, as well as pitching motion history are used as the input of the Hierarchical Kriging model to predict the high-fidelity aerodynamic loads. The generalization capability of this improved modelling framework is firstly verified by several analytical examples. Furthermore, with three sets of training samples taken from harmonic pitching motions of an airfoil in transonic flow, the proposed model achieves accurate prediction on unsteady aerodynamics of other harmonic and random motions, and provides reliable uncertainty estimation of the predicted unsteady aerodynamics. In addition, the computational cost and prediction errors of multi-fidelity and the single-fidelity aerodynamic model are compared. Even with the same computational cost, the proposed multi-fidelity model still shows improved accuracy. Finally, using the uncertainty estimation of the proposed model, an active learning task is performed, which actively selects and incrementally adds the required training samples. With active learning, a good balance between model accuracy and cost of data acquisition is maintained, while avoiding over-fitting problems of the proposed model. [ABSTRACT FROM AUTHOR]

In recent years, improvements in wireless communication have led to the development of microstrip or patch antennas. The article discusses using simulation, measurement, an RLC equivalent circuit model, and machine learning to assess antenna performance. The antenna's dimensions are 1.01 λ 0 × 0.612 λ 0 with respect to the lowest operating frequency, the maximum achieved gain is 6.76 dB, the maximum directivity is 8.21 dBi, and the maximum efficiency is 83.05%. The prototype's measured return loss is compared to CST and ADS simulations. The prediction of gain and directivity of the antenna is determined using a different supervised regression machine learning (ML) method. The performance of ML models is measured by the variance score, R square, mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), and mean squared logarithmic error (MSLE), etc. With errors of less than unity and an accuracy of roughly 98%, Ridge regression gain prediction outperforms the other seven ML models. Gaussian process regression is the best method for predicting directivity. Finally, modeling results from CST and ADS, as well as measured and anticipated results from machine learning, reveal that the suggested antenna is a good candidate for LTE. [ABSTRACT FROM AUTHOR]

• Developed 2D deformation model using multiband SAR with rates and errors. • Deformation model connect to terrestrial reference frame. • new method to estimate interpolation errors using Natural Neighbour interpolation. • error estimation method replicates the error behaviour from Ordinary Kriging. • Natural Neighbour interpolation is at least 100 times faster than Ordinary Kriging. A long term objective for Australia is to develop a continent-wide 2D deformation model based on satellite interferometric synthetic aperture radar (InSAR). Nation-wide InSAR processing has been demonstrated in European countries and Japan. However, there are some key differences to the Australian situation for a 2D model (i.e., vertical and east–west surface movement rates) where SAR data from ascending and descending satellite orbits are needed. The primary difference is that while ESA's Sentinel-1 ascending and descending satellite observations underpin 2D models in other parts of the world, the Australian continent is only covered by descending Sentinel-1 SAR data in most areas. Combined with Australia's large size of 7.63 million km2, this means a different approach is needed to realise 2D deformation models. In this article, we propose the novel approach of (1) combining supplementary multiband SAR (ascending X-band and L-band) with the descending C-band Sentinel-1 data, and (2) using natural neighbour (NN) interpolation as a computationally efficient interpolation method for combining the multiband InSAR data on common grids prior to 2D model computation. This is an alternative to the computationally intensive Ordinary Kriging (OK) approach. A disadvantage of NN compared to OK is that it does not compute an error estimate, which we address by deriving an error estimate for the NN interpolation so that errors are provided for each 2D rate to aid with their correct interpretation. To demonstrate our new approach, we compute experimental 2D deformation models that propagate the full error budget from InSAR, a GNSS connection to ITRF2014 and NN interpolation into an error grid in the Latrobe Valley in southeast Australia. The significance of our approach is that it provides a suitable combination of methods that may be used to develop 2D continental deformation models for Australia's unique circumstances. Our results demonstrate the accuracy of NN and OK interpolation are at the same level (within error), and the error estimates from both interpolation techniques are also comparable: X band (TerraSAR-X) ∼ 1 mm/yr; C band (Sentinel-1) ∼ 2.5 mm/yr, and L band (ALOS PALSAR1) 4 mm/yr. For the first time, we reveal 2D deformation in the Latrobe Valley region showing horizontal east–west deformation in the area surrounding an above-ground mine and reaching 20 mm/yr, with vertical subsidence rates reaching −40 mm/yr. [ABSTRACT FROM AUTHOR]

Most of the existing research on thermal error regression modeling of CNC machine tools establishes deterministic models, presents point predictions for thermal errors and focuses on the scenario where there is no hysteresis effect between input and output. There is little research on quantifying the uncertainties of spindle axial thermal error when there exist significant hysteresis effects between the temperature points and spindle axial thermal error. In this regard, this paper presents a novel uncertainty modeling method for spindle axial thermal error. Firstly, to screen out key temperature points, the whole temperature points are sorted according to the minimal redundancy maximal relevance (mRMR) criterion, and the candidate input feature sets are generated. Then, the gated recurrent unit (GRU) model is introduced to handle the hysteresis effects. Finally, the deterministic GRU model is transformed into the prediction interval-based GRU (PI-GRU) model, which can produce prediction intervals (PIs) of the spindle axial thermal error. The correctness and effectiveness of this method are verified by the spindle axial thermal error experiments. In contrast with the Gaussian process regression (GPR) method, the proposed method deals with the hysteresis effects more appropriately and performs better in uncertainty prediction accuracy. • Propose a novel uncertainty modeling method for spindle axial thermal error. • Apply the minimal redundancy maximal relevance criterion to screen out the key temperature points. • Transform the gated recurrent unit (GRU) model into the prediction interval-based GRU (PI-GRU) model. • The hysteresis effects are properly considered by the PI-GRU model. [ABSTRACT FROM AUTHOR]

In the present study, a black box model for phase change heat exchangers is developed based on Kriging interpolation. The input and output of the heat exchanger black box model were established based on the mass-flow-guided method. Methods for the input domain determination of are established respectively for the application of system simulation and separate heat exchanger simulation. A training data set sampling method is established based on the Latin hypercube sampling method to achieve significant reduction in sample points while maintaining the integrity of the sample data characteristics. The heat exchanger calculation trend was determined by establishing a regression model; the accurate prediction of heat exchanger performance was achieved by making local corrections to the prediction results through a stochastic distribution process model. Validation results show that, for the condenser model, the average pressure drop prediction error is 0.25%, and the average heat transfer prediction error is 1.18%; for the evaporator model, the average pressure drop prediction error is 0.71%, and the average heat transfer prediction error is 0.80%. The model can achieve high prediction accuracy with a small amount of training data and has a good fitting performance in the range of general applications. [ABSTRACT FROM AUTHOR]

• A Kriging-assisted global reliability-based design optimization (KG-RBDO) algorithm is proposed. • KG-RBDO consists of a global optimization module and a local optimization module. • A new infill criterion considering both the optimality and the reliability requirement of the solutions is proposed. • KG-RBDO is more approximate to the global reliability-based design optimization problems. Surrogate models have been extensively used in reliability-based design optimization (RBDO); however, few studies have focused on the global optimality of RBDO. This paper proposes a global RBDO framework that employs Kriging surrogate models to approximate both the objective function and performance functions. The proposed algorithm comprises two major modules: the global optimization module and the local optimization module. The former module aims to identify the interested region containing potential optima, while the latter module refines the local optima. To address the time-consuming acquisition of samples, two different infill strategies are implemented in these two modules. Furthermore, in addition to evaluating the optimal solution in the local optimization module for infill, a reliability-constrained expected improvement infill criterion is developed for the global optimization module. This criterion inherits the property of the expected improvement from the Kriging model, which balances the exploration and the exploitation of the objective space, while taking reliability into account by introducing the shifting vector into the calculation of the probability of feasibility. Numerical experiments indicate that the performance of the proposed infill criterion is significantly superior to others in searching for optima. Several examples verify the global optimization capability of the proposed algorithm and illustrate that it is more suitable for RBDO problems with multiple local optima. [ABSTRACT FROM AUTHOR]

In the recent years, radiative cooling has emerged as a promising technology for space cooling applications. Nevertheless, radiative cooling phenomenon is dependent on weather conditions and it presents some performance limitations, meaning that the cooling capacity is limited in some climates. The radiative cooling potential is the maximum theoretical limit that can be achieved. In this study we analyse the evolution of the radiative cooling potential in Europe under the context of climate change. Radiative cooling potential maps for the period 2020–2050 are provided. The results reveal that radiative cooling potential remains constant for this period, evidencing a resilience of this technology during the following decades. We also provide a seasonal study of the potential by regions. Summer, when cooling needs are higher, is the season with the least nocturnal energy potential and the second with the highest nocturnal power potential. Shifting to all-day radiative cooling, the energy potential increases by 1.64 in winter; 2.97 in spring; 4.03 in summer and 2.2 in autumn. [ABSTRACT FROM AUTHOR]

Many farms document daily milk yields of individual cows because these are a good indicator of cow well-being. It is established that extreme meteorological conditions influence the milk yields by causing heat and cold stress, whereas less is known about the effects of moderate changes in meteorological conditions. Thus, the aim of the present study was to evaluate whether individual daily milk yield predictions can be improved by considering such changes. We evaluated 8 years of milking and meteorological data from Eastern Switzerland with a total of 33,938 daily milkings from 145 Brown Swiss and 64 Swiss Fleckvieh cows. The cows were aged between 1.9 and 13.5 years at parturition. The data set was split into 7 periods according to the days in milk (DIM) and subsequently filtered into subsets by breed and parity. We applied Gaussian process regression to predict individual daily milk yield. We compared different models including DIM, lagged milk yield, and meteorological variables as features and found that models including the lagged milk yield performed best. Within the period of 5 to 90 DIM, we were able to predict individual next-day milk yield from the cow's last milkings with a root mean squared error (RMSE) of 2.1 kg. In contrast, without information on the previous milk yield, accuracy of milk yield prediction was lower, with an RMSE close to 8 kg. The models holding information about previous milk yields showed a substantial increase in performance. Within a more homogeneous data subset filtered by breed or parity or both, predictions were even better, with a relative RMSE of 4.3% for first-parity Fleckvieh cows. However, we found that including meteorological features, such as temperature, rainfall, wind speed, temperature humidity index, cooling degree, and barometric pressure, did not improve the predictions in any of the evaluated periods. This finding indicates that considering meteorological features in daily milk yield prediction models is not useful in moderate climates; considering lagged milk yield is sufficient. We hypothesize that this meteorological information, among other influences, is indirectly contained in the lagged milk yield. [ABSTRACT FROM AUTHOR]

• A multi-step PI prediction method based on feature analysis was proposed. • Three new indicators were constructed to extract the features of fluctuations. • Optimal membership search was used to curb the decaying accuracy of prediction. • Prediction method based on fluctuation types improved the prediction performance. Power prediction can effectively mitigate the uncertainty in photovoltaic power generation, enabling better operation and scheduling of power grids. Therefore, in this study, a multi-step interval prediction method for ultra-short-term photovoltaic power from time-series-segment (TSS) feature analysis is proposed. First, three TSS indicators are defined to determine the fluctuation characteristics of historical data and combined with fuzzy C-means clustering to address the time mismatch problem. Subsequently, a deterministic multi-step prediction method is proposed based on the optimal membership search using deep recurrent neural networks, improving the prediction stability. Finally, based on the difference in the TSS types, an improved interval prediction method is proposed in combination with Gaussian process regression, narrowing the average interval width. Experiments are conducted to compare the performances of the conventional and proposed methods using measured data from Australia. Compared with the baseline scheme, the proposed scheme enhances the accuracy of multi-step prediction by 19.7%, and the average error of each step does not exceed 5%.The average interval width is reduced by 45.6% while ensuring more than 95% interval coverage in the probability interval prediction. The experimental findings demonstrate that the TSS feature analysis can effectively reveal the potential patterns of PV power output under various weather conditions. This enables the algorithm to learn clearer sample features and thus enhances the performance of multi-step probability interval prediction. [ABSTRACT FROM AUTHOR]

Zero carbon fuels can be used to reduce CO 2 emissions from internal combustion engines. Hydrogen is an important zero-carbon fuel that can be used as the primary fuel for spark ignition (SI) engines or in dual-fuel operation in compression ignition (CI) engines. The combustion properties of hydrogen often result in high combustion temperature which produces harmful nitrogen oxides (NO x) emissions. To reduce NO x and soot emissions from hydrogen fueled engines, an engine can be optimized using a hardware-in-the-loop (HIL) setup to reduce calibration efforts for the engine. In addition, optimal model based combustion control (MCC) can reduce engine-out emissions. Both of HIL and MCC techniques require fast and accurate NO x and soot emission models. The accuracy of a fast physics-based engine model with pre-mixed combustion is dependent on predicting the laminar flame speed (LFS). In this study, LFS is predicted using an artificial neural network (ANN) machine learning (ML) method. Then the LFS model and engine combustion model are validated for both an SI hydrogen engine and for a CI hydrogen-diesel engine. Next, black-box and gray-box soot and NO x emission models are developed for the hydrogen-diesel engine using ANN, support vector machine (SVM) and Gaussian process regression (GPR) methods with different feature-sets and compared with the a common one-dimensional physics-based NO x model. The developed gray-box emission models can predict NO x and soot emissions with an R test 2 value of higher than 0.99 which makes them suitable for engine HIL setups where accuracy is very important. On the other hand, the black-box emission models can predict NO x and soot emissions with R test 2 value higher than 0.95 with a run time thousands of times faster than the gray-box models. This makes the black-box models suitable for model-based real time hydrogen combustion control where limited computational power is available. • Model to predict combustion and performance of single and dual fuel hydrogen engines. • Gray box model to Predict NOx and soot emission of hydrogen engine with R2 test > 0.99. • Physical hydrogen engine models using embedded machine learning laminar flame speed. • Systematic machine learning method and input feature set study for emission models. • Experimental data for spark and compression ignition hydrogen fueled engines. [ABSTRACT FROM AUTHOR]

Geostatistics is the knowledge of manifestations that vary in space and time. The analysis of spatial data is currently of great interest in statistical modeling. Various parametric and non-parametric kriging techniques are widely used for modeling and prediction of spatially reference data. In this article, we have applied and compared the parametric and non-parametric kriging techniques to model groundwater quality parameters. The data used in this study consists of 366 water samples collected from major cities of Pakistan by the Pakistan Council of Research in Water Resources (PCRWR) survey. The water quality parameters are grouped by spatial variation using cluster analysis and principal component analysis. In order to generate prediction maps and evaluate the probability of groundwater quality parameters, parametric and non-parametric kriging techniques are used. Non-parametric kriging techniques showed better performance than parametric kriging techniques when the normality assumption of kriging is violated. [ABSTRACT FROM AUTHOR]