Surrogate Approach Research Articles

DecTree: a physics-based geochemical surrogate for surface complexation of uranium on clay

Abstract. Geochemistry is usually the computational bottleneck in coupled reactive transport simulations, which hampers the complexity of the systems and of the processes they can investigate. In recent years, promising speedups have been obtained by substituting the numerical solution of geochemical models with approximated surrogates borrowed from artificial intelligence and machine learning (AI/ML). In the framework of the DONUT/EURAD project a set of benchmarks were defined to assess the performance and the accuracy of different surrogate approaches in settings relevant to the safety assessment of nuclear waste repositories, such as the surface complexation and exchange of U(VI) on clay. In this context, this work introduces am original surrogate modelling approach based on recursive partitioning of parameter space, which exploits prior domain knowledge for the training. The surrogate, which can be represented as a decision tree, hence the DecTree name, performs dimensionality reduction by identifying functional relationships between outputs and input variables using a straightforward non-monotonic extension of the Spearman's rank correlation coefficient. New predictions are then interpolated from the partitioned training data. Applied to a low-dimensional geochemical model, DecTree shows virtually no training time and excellent accuracy, ensuring a throughput of around 500 000 predictions per second on a single CPU core.

A reliability calculation method based on ISSA-BP neural network

PurposeTo address the shortcomings of the traditional back propagation (BP) neural network agent model, such as insufficient fitting accuracy and low computational efficiency, an improved method is proposed.Design/methodology/approachIn this study, an improved sparrow search algorithm (ISSA) is developed to optimize the reliability calculation of the BP neural network (ISSA-BP) using an enhanced BP neural network model. The traditional sparrow search algorithm is enhanced by incorporating a golden sine strategy to improve its position-updating mechanism, thereby overcoming its tendency to converge prematurely to local optima. Additionally, an opposition-based learning strategy is integrated to explore the reverse solution around the optimal solution of the sparrow search algorithm, mitigating the risk of local optima.FindingsThe results of the test function demonstrate that the proposed method significantly enhances fitting accuracy while maintaining computational efficiency. Finally, by applying this approach to the metro bogie frame as a case study, the structural reliability of the bogie frame is evaluated using the Monte Carlo method, providing valuable insights for subsequent analysis and structural optimization.Originality/valueThe use of the surrogate model approach for structural reliability analysis significantly improves solution efficiency. Furthermore, the integration of ISSA with the BP neural network enhances both fitting accuracy and computational efficiency, demonstrating the superiority and practicality of the proposed method.

Sensitivity analysis of a dual-continuum model system for integrated CO2 sequestration and geothermal extraction in a fractured reservoir

Depleted hydrocarbon reservoirs are considered as the most feasible option for CO2 geological sequestration and utilization. Most of the hydrocarbon reservoirs are naturally fractured. Simulation of fluid flow and heat transfer in these fractured formations remains a significant challenge in reservoir engineering. In this study, a dual-continuum model is developed to simulate integrated CO2 sequestration and CO2-circulated geothermal extraction in a fractured reservoir block in North Oman. The high-dimensional sensitivity of key parameters controlling CO2-brine flow and heat transfer in this matrix-fracture system is quantitatively evaluated by an efficient surrogate modeling approach. The surrogate models are constructed and validated based on a suite of physics-based model simulations. It is found that fracture permeability dominates the CO2 injectivity, storage, circulation and associated geothermal extraction. Response surface analysis shows that the flow area density between matrix-fracture and matrix block length controls the flux interaction between matrix and fracture formations. In contrast, the fracture aperture shows negligible influence in the dual-continuum modeling system. Particularly, sensitivity varying with locations on the response surface is analyzed for defined performance indicators.

Comprehensive targeted profiling of multiple steroid classes in rodent plasma using liquid chromatography-mass spectrometry

BackgroundReliable quantification of multiple steroid classes in biological fluids within a single method remains an analytical challenge despite many previously published methods. Crosstalk of positional isomers, overlap of stereoisomer fragmentation patterns, differing proton affinities, in-source fragmentation, varying stability of protonated ions in the gas phase across steroid classes, and non-existence of steroid-free matrix are the main challenges limiting the number of simultaneously profiled steroids. ResultsIn this study, we focused on the development of a derivatization-free, achiral, high-throughput, and cost-effective UHPLC-MS/MS approach that allows simultaneous profiling of a spectrum of 38 steroids covering progestogens, androgens, corticosteroids, and estrogens, while properly addressing the hurdles of steroid analysis. Within a 20-min method, 16 stereoisomers and 15 positional isomers were fully resolved within a single run while separated from 7 additional non-interfering steroids and matrix interferences in rodent plasma. Protein precipitation (PP) and supported liquid extraction (SLE) methods using only 40 μL of sample were developed to achieve the lowest possible limits of quantification. Nevertheless, 5α-dihydroprogesterone and 3α,5α-THDOC could be only qualitatively assessed when using PP. In contrast, DHEA-S could not be quantified or identified when using SLE. A novel surrogate matrix-background subtraction approach, using rat plasma after the animal's adrenalectomy, has been implemented into the optimized PP-UHPLC-MS/MS workflow, successfully validated according to the unified ICH/EMA M10 guidelines, and compared to the traditional quantification strategies. Moreover, the validity of the newly adopted approach has been verified by the targeted profiling of multiple biologically active endogenous steroids in more than 500 samples of mouse plasma in total. SignificanceUnderestimation of hurdles associated with steroid analysis often compromises the accurate steroid quantification. Our comprehensive, fully validated UHPLC-MS/MS method targeting a wide spectrum of endogenous steroids, mitigating steroid crosstalk and using a minimal sample volume together with a novel surrogate matrix-background subtraction approach significantly advances steroid analysis for research and clinical applications covering multiple biological scopes.

Optimization of pressure management strategies for geological CO2 storage using surrogate model-based reinforcement learning

Injecting greenhouse gas (e.g. CO2) into deep underground reservoirs for permanent storage can inadvertently lead to fault reactivation, caprock fracturing and greenhouse gas leakage when the injection-induced stress exceeds the critical threshold. It is essential to monitor the evolution of pressure and the movement of the CO2 plume closely during the injection to allow for timely remediation actions or rapid adjustments to the storage design. Extraction of pre-existing fluids at various stages of the injection process, referred as pressure management, can mitigate associated risks and lessen environmental impact. However, identifying optimal pressure management strategies typically requires thousands of simulations, making the process computationally prohibitive. This paper introduces a novel surrogate model-based reinforcement learning method for devising optimal pressure management strategies for geological CO2 sequestration efficiently. Our approach comprises of two steps. The first step involves developing a surrogate model using the embed to control method, which employs an encoder-transition-decoder structure to learn dynamics in a latent or reduced space. The second step, leveraging this proxy model, utilizes reinforcement learning to find an optimal strategy that maximizes economic benefits while satisfying various control constraints. The reinforcement learning agent receives the latent state representation and immediate reward tailored for CO2 sequestration and choose real-time controls which are subject to predefined engineering constraints in order to maximize the long-term cumulative rewards. To demonstrate its effectiveness, this framework is applied to a compositional simulation model where CO2 is injected into saline aquifer. The results reveal that our surrogate model-based reinforcement learning approach significantly optimizes CO2 sequestration strategies, leading to notable economic gains compared to baseline scenarios.

Determination of adalimumab by HPLC with fluorescence detection using the König reaction

Monoclonal antibody drugs (mAb) are widely used to treat various diseases. Keeping quality of mAbs is crucial to maximize efficacy and minimize adverse effects. To this end, mAb content in the drug product must be precisely quantified. As methods for the determination of mAbs, absorbance measurement at 280 nm, the ligand binding assay based on ELISA, or the LC-MS/MS method based on the surrogate peptide approach is usually used. However, these methods have drawbacks in terms of selectivity, reliability, and cost, respectively. The present method is based on the surrogate peptide approach where a peptide specific to the mAb is determined by a post-column derivatization LC system with fluorescence detection and the König reaction, which is usually used for the detection of cyanide and its derivatives. The detection mechanism was the production of cyanide from the surrogate peptide by chloramine T and the generated cyanide was detected by the König reaction. In this study, adalimumab was used as a model target protein. The calculated LOD and LOQ of the present method were 0.31 μg/mL and 0.94 μg/mL, respectively. The intra-day accuracies and precisions were 127.1 % and 2.94 % for 5 μg of adalimumab and 101.6 % and 10.2 % for 50 μg of adalimumab, respectively. The inter-day accuracies and precisions were 121.8 % and 5.71 % for 5 μg of adalimumab and 101.8 % and 6.98 % for 50 μg of adalimumab, respectively. Our quantitatively determined amount of adalimumab in Humira® was in good agreement with the specified value. This method only requires a conventional LC system, not an LC-MS/MS system. By extending the application of the König reaction, we open the door to a new surrogate peptide approach for the determination of proteins including monoclonal antibody drugs.

An integrated framework of deep learning and entropy theory for enhanced high-dimensional permeability field identification in heterogeneous aquifers

Accurately estimating high-dimensional permeability (k) fields through data assimilation is critical for minimizing uncertainties in groundwater flow and solute transport simulations. However, designing an effective monitoring network to obtain diverse system responses in heterogeneous aquifers for data assimilation presents significant challenges. To investigate the influence of different measurement types (hydraulic heads, solute concentrations, and permeability) and monitoring strategies on the accuracy of permeability characterization, this study integrates a deep learning-based surrogate modeling approach and the entropy-based maximum information minimum redundancy (MIMR) monitoring design criterion into a data assimilation framework. An ensemble MIMR-optimized method is developed to provide more comprehensive monitoring information and avoid missing key information due to the randomness of stochastic response datasets in entropy analysis. A numerical case of solute transport with log-Gaussian permeability fields is presented, with twelve scenarios designed by combining different measurement types and monitoring strategies. The results demonstrated that the proposed ensemble MIMR-optimized method significantly improved the k-field estimates compared to the conventional MIMR method. Additionally, high prediction accuracy in forward modeling is essential for ensuring reliable inversion results, especially for observation data with strong nonlinearity. The findings of this study enhance our understanding and management of k-field estimation in heterogeneous aquifers, contributing to the development of more robust inversion frameworks for general data assimilation tasks.

Dynamic data-driven multiscale modeling for predicting the degradation of a 316L stainless steel nuclear cladding material

We have developed a long short-term memory stacked ensemble (LSTM-SE) surrogate modeling approach that can provide rapid predictions of microstructural evolution and the resultant mechanical properties of American Iron and Steel Institute (AISI) 316L series stainless steel (SS316L) fuel cladding under conditions of varying temperature and radiation dose rate. To acquire training data, we developed and implemented a kinetic Monte Carlo (KMC) model to simulate precipitation kinetics of M23C6, γ’, and G phases within SS316L cladding. Experimentally reported precipitation kinetics of SS316L in literature were linked to the kinetic parameters of the simulated precipitation in our KMC model. The model was then used to simulate microstructure evolution under synthetically generated treatments of varying temperature and radiation dose rate for periods of up to 3000 h. Changes in volume fraction, number density, and particle size of precipitates were recorded, and particle area fractions were correlated using statistical methods to develop the surrogate model. Simultaneously, the mechanical properties of the simulated microstructures were evaluated using microstructure-based finite element method (FEM) analysis to determine the elastic modulus, yield stress, ultimate tensile strength, and elongation to failure of the aged microstructures. Using this approach, our surrogate model can predict precipitation behavior within 0.25 % volume fraction and mechanical properties within 6 % relative error from the values predicted by the KMC and FEM models using 50 training simulations as input. The trained recurrent neural network-based model can return estimations of precipitation kinetics and mechanical properties ∼1000 times faster than the physics-based codes. This work demonstrates, as a proof of concept, that microstructural evolution under variable conditions can be predicted using a statistics-based model informed by a practicably obtainable dataset. The potential applications of this type of modeling framework are discussed.

InfoFlowNet: A multi-head attention-based self-supervised learning model with surrogate approach for uncovering brain effective connectivity

Deciphering brain network topology can enhance the depth of neuroscientific knowledge and facilitate the development of neural engineering methods. Effective connectivity, which gauges the directional influences among brain regions, is pivotal for these studies. This research introduces InfoFlowNet, a novel self-supervised learning model designed to infer causal relationships in electroencephalogram (EEG) data, aiming at capturing the complex information flow among brain regions. Specifically, InfoFlowNet employs convolution operations and multi-head self-attention mechanisms with a masking feature, which ignores self-connections to focus on inter-regional dynamics. Additionally, a new causal magnitude estimation is introduced by assessing the impact of shuffled surrogate data on signal prediction to quantify causal influence. Experiments using synthetic data and real EEG datasets demonstrate that InfoFlowNet effectively uncovers time-varying causal relationships. Compared with the Granger causality model (GCM) and the temporal causal discovery framework (TCDF), InfoFlowNet shows superior sensitivity in detecting significant causal edges. For instance, in a psychomotor vigilance task, InfoFlowNet identified 8 out of 16 significant causal edges, significantly outperforming GCM and TCDF. Furthermore, InfoFlowNet successfully passes the whiteness test on the model's residuals, and advanced analyses illustrate the advantages of utilizing multi-head attention and masking mechanisms to capture effective connectivity. In sum, InfoFlowNet represents a significant advancement in the analysis of effective connectivity, offering a deeper understanding of brain network dynamics. The model's ability to discern complex causal interactions supports its potential application in broader neuroscientific research and applications.

Numerical investigation and rapid prediction of the erosion rate of gate valve in gas-solid flow

Gate valves are essential control components in pneumatic conveying systems and often experience erosion on their sealing structures due to impacts from solid particles. The erosion leads to a degradation of the sealing effectiveness and, in severe cases, system malfunction. To address this issue, a numerical model based on computational fluid dynamics (CFD) is developed for the simplified two-dimensional gate valve. The two-way Euler-Lagrange method is utilized to investigate the characteristics of gas-solid two-phase flow and erosion rate. The simulation procedure is verified by comparing the simulation results with experimental data. Results show that the sealing surface separates the free shear layer above the cavity and a low-velocity zone is created on the sealing surface. The particles moving at the downstream bottom are the main particles that impact the sealing surface. The erosion results show that the maximum erosion rate occurs near the top of the sealing surface. And the low-velocity zone reduces the erosion rate within that region. Particle diameter, gas velocity, and valve opening have an important effect on erosion on the sealing surface. The erosion rate increases as the valve opening decreases. The value of the maximum erosion rate increases with particle diameter and gas velocity, and its position changes. Finally, based on the established numerical model, a prediction model for the sealing surface erosion rate is constructed using the surrogate model approach.

On the Solute-Induced Structure-Making/Breaking Phenomena: Myths, Verities, and Misuses in Solvation Thermodynamics

We review the statistical mechanic foundations of the fundamental structure-making/breaking functions, leading to the rigorous description of the solute-induced perturbation of the solvent environment for the understanding of the solvation process of any species regardless of the type and nature of the solute–solvent interactions. Then, we highlight how these functions are linked to unambiguous thermodynamic responses resulting from changes in state conditions, composition, and solute–solvent intermolecular interaction asymmetries. Finally, we identify and illustrate the pitfalls behind the use of surrogate approaches to structure-making/breaking markers, including those based on Jones–Dole’s B-coefficient and Hepler’s isobaric-thermal expansivity, while highlighting their ambiguities and lack of consistency and the sources of misinterpretations.

Output power prediction of stratospheric airship solar array based on surrogate model under global wind field

Stratospheric airships are lighter-than-air vehicles capable of continuous flying for months. The energy balance of the airship is the key to long-duration flights. The stratospheric airship is entirely powered by the solar array. It is necessary to accurately predict the output power of the array for any flight state. Because of the uneven solar radiation received by the solar array, the traditional model based on components has a slow simulation speed. In this study, a data-driven surrogate modeling approach for prediction the output power of the solar array is proposed. The surrogate model is trained using the samples obtained from the high-accuracy simulation model. By using the input parameter preprocessor, the accuracy of the surrogate model in predicting the output power of the solar array is improved to 98.65%. In addition, the predictive speed of the surrogate model is ten million times faster than the traditional simulation model. Finally, the surrogate model is used to predict the energy balance of stratospheric airships flying throughout the year under actual global wind fields.

A Surrogate Model's Decision Tree Method Evaluation for Uncertainty Quantification on a Finite Element Structure via a Fuzzy-Random Approach

A novel additive manufacturing method (AM)) constructs a three-dimensional model from a computer-aided design by adding material layer by layer. This technique produces a lightweight end product with complex geometries and has gained recognition among industrial players. Nonetheless, the mechanical properties and geometry components are the uncertainties that prevail in its structures. An alternative approach using the Finite Element Method (FEM) to analyse these uncertainties demands extensive computational effort and time consumption. Therefore, a machine learning (ML) tool using the surrogate modelling technique offers an alternative way to provide and predict simulation outcomes. This study applies two surrogate modeling approaches, the decision tree (DT) and the Gaussian process regression (GPR) methods. Output data from a FEM simulation with uncertainty elements are obtained for the training purposes of the surrogate models. Both ML methods can predict simulation results with high precision. Both approaches obtained an excellent coefficient of determination value, R2 of 0.998, and Root Mean Square Error, RMSE of 0.012, successfully reducing time consumption and computational effort. The DT method shows better robustness when compared to the GPR method. A value change in the input parameter significantly impacts the surrogate model's prediction performance. An adequate quantity of data input for the training phase of both surrogate models exhibits the FEM results with the presence of uncertainty and robustness.

Assessment of Multifidelity Surrogate Approaches for Expedient Loads Prediction in High-Speed Flows

Fast and accurate predictions about the flowfield surrounding a hypersonic flight vehicle are necessary for both early design phases and autonomous vehicle control. Data-driven model reduction presents an opportunity to harness the accuracy of high-fidelity techniques for expedient online application. Surrogate modeling is one approach that seeks to emulate the response of a system with evaluation times much faster than the data source. Multifidelity surrogate modeling seeks to reduce the amount of high-fidelity data needed for a sufficiently accurate online model. The objective of this paper is to assesses the tradeoffs between a kriging-based multifidelity model and a neural-network-based multifidelity model, applied to high-speed flow past a canonical flight geometry. All models studied in this work reproduce the results of the benchmark simulations with less than 100 training cases. The kriging models marginally outperform the neural-network-based models in accuracy, but requirements for training and storing the kriging models scale exponentially as the training data gets larger. Kriging models offer built-in uncertainty quantification and require significantly less decision making about hyperparameters and architecture choices. This study also indicates that the inclusion of data from classical engineering methods can improve the prediction accuracy of surrogate models at practically no cost.

Modeling for sustainable groundwater management: Interdependence and potential complementarity of process-based, data-driven and system dynamics approaches

Groundwater systems are vast natural water reservoirs used to support human water demands and ecosystem services. Various modeling approaches have been developed to help manage these complex highly-dynamic systems. This paper discusses the strengths and limitations of three modeling approaches, namely: process-based, data-driven and system dynamics modeling. For demonstration purposes, the three modeling approaches are applied to the Konya Closed Basin, a large agricultural region with semi-dry climate located in central Turkey. Process-based modeling is grounded in the theory-based representation of the governing processes but is somewhat limited by the computational effort and the difficulty of defining the required input parameters that characterize the heterogeneous aquifer system. Process-based models are shown to be powerful tools for resource management purposes provided climatic and water demand scenarios are accurately defined. Data-driven models are efficient tools for the management of groundwater resources but are highly dependent on the availability of large training data sets encompassing the spectrum of possible system responses. The high efficiency of surrogate modeling approaches makes them ideal tools for incorporation into applications such as real-time decision support systems and digital twin platforms. System dynamics modeling examines the groundwater exploitation problem within a socio-economic context that involves multiple stakeholders and their decision making. It combines groundwater flow models with socio-economics and endogenous decision rules to conduct scenario analysis and support policy development. The analyses and model demonstrations presented in this paper underscore the interconnectedness and complementarity of these three modeling approaches and the need for more integrated use of these modeling approaches for enhanced multi-sectoral management of groundwater systems.

The Interplay between Mitochondrial Metabolism and Nasal Mucociliary Function as a Surrogate Method to Diagnose Thyroid Dysfunction: Insights from a Population-Based Study.

Aim and Background. This study aims to explore alternative diagnostic methods to assess thyroid function in patients unable to undergo blood tests for thyroid-stimulating hormones (TSH) and thyroxine (T4), such as individuals with trypanophobia, severe medical conditions, or coagulopathy. Considering the impact of thyroid dysfunction on mitochondrial metabolism and the essential role of proper mitochondrial function in ciliary motility, we postulate that assessing nasal ciliary function could serve as a surrogate diagnostic approach for thyroid dysfunction. Methods. This cross-sectional study was performed on individuals with no history of thyroid diseases. The primary endpoint was the diagnostic value of the nasal mucociliary (NMC) test using Iranica Picris (Asteraceae) aqueous extract in differentiating hypo- or hyperthyroidism cases from euthyroid cases. Results. 232 individuals were recruited (71% females, 86% euthyroid). Receiver operating characteristic (ROC) analysis showed a good diagnostic value for the NMC test in differentiating overt hypothyroidism (area under the ROC curve [AUROC] = 0.82, p = 0.004) and its fair value in diagnosing subclinical hyperthyroidism (AUROC = 0.78, p = 0.01) from the euthyroid condition. The NMC test had a significant positive correlation with TSH (r = 0.47, p < 0.001) and a significant negative correlation with T4 (r = -0.32, p < 0.001). The NMC rate was significantly different in distinct thyroid function groups (p < 0.001). Compared with euthyroid cases, the post-hoc analysis showed that the NMC test is significantly higher in overt hypothyroidism (15.06 vs. 21.07 min, p = 0.003) and significantly lower in subclinical hyperthyroidism (15.05 vs. 10.9 min, p = 0.02). Conclusions. The Iranica Picris-based NMC test might serve as a diagnostic method to distinguish overt hypothyroidism and subclinical hyperthyroidism.

Development, validation and application of an LC-MS/MS method quantifying free forms of the micronutrients queuine and queuosine in human plasma using a surrogate matrix approach.

Queuosine (Q) is a hypermodified 7-deaza-guanosine nucleoside exclusively synthesized by bacteria. This micronutrient and its respective nucleobase form queuine (q) are salvaged by humans either from gut microflora or digested food. Depletion of Q-tRNA in human or mouse cells causes protein misfolding that triggers endoplasmic reticular stress and the activation of the unfolded protein responses. In vivo, this reduces the neuronal architecture of the mouse brain affecting learning and memory. Herein, a sensitive method for quantifying free q and Q in human blood was developed, optimised and validated. After evaluating q/Q extraction efficiency in several different solid-phase sorbents, Bond Elut PBA (phenylboronic acid) cartridges were found to have the highest extraction recovery for q (82%) and Q (71%) from pooled human plasma. PBS with 4% BSA was used as surrogate matrix for method development and validation. An LC-MS/MS method was validated across the concentration range of 0.0003-1 µM for both q and Q, showing excellent linearity (r2 = 0.997 (q) and r2 = 0.998 (Q)), limit of quantification (0.0003 µM), accuracy (100.39-125.71%) and precision (CV% < 15.68%). In a sampling of healthy volunteers (n = 44), there was no significant difference in q levels between male (n = 14; mean = 0.0068 µM) and female (n = 30; mean = 0.0080 µM) participants (p = 0.50). Q was not detected in human plasma. This validated method can now be used to further substantiate the role of q/Q in nutrition, physiology and pathology.

Determination of endometrial cancer molecular subtypes using a whole exome-sequencing based single-method approach

AimEndometrial cancer (EC) is heterogeneous with respect to epidemiology, clinical course, histopathology and tumor biology. Recently, The Cancer Genome Atlas (TCGA) network has identified four molecular subtypes with distinct clinical courses by an integrated multi-omics approach. These subtypes are of critical importance in the clinical management of EC. However, determination of TCGA molecular subtypes requires a complex methodological approach that is resource intensive and difficult to implement in diagnostic routine procedures. In this context, Talhouk et al. reported the precise determination of modified subtypes based on molecular surrogates obtained by a two-method approach comprising immunohistochemistry and DNA-sequence analysis (Proactive Molecular Risk Classifier for Endometrial Cancer; ProMisE). In this study, we aimed to identify EC molecular subtypes in analogy to TCGA and ProMisE applying an innovative whole exome-sequencing (WES) based single-method approach.MethodsWES was performed in a cohort comprising N = 114 EC patients. WES data were analyzed using the oncology treatment decision support software MH Guide (Molecular Health, Heidelberg, Germany) and EC molecular subtypes in analogy to TCGA and ProMisE were determined. Results from both classifications were compared regarding their prognostic values using overall survival and progression-free survival analyses.ResultsApplying a single-method WES-approach, EC molecular subtypes analogue to TCGA and ProMisE were identified in the study cohort. The surrogate marker-analogue classification precisely identified high-risk and low-risk EC, whereas the TCGA-analogue classification failed to obtain significant prognostic values in this regard.ConclusionOur data demonstrate that determination of EC molecular subtypes analogue to TCGA and ProMisE is feasible by using a single-method WES approach. Within our EC cohort, prognostic implications were only reliably provided by applying the surrogate marker-analogue approach. Designation of molecular subtypes in EC will be increasingly important in routine clinical practice. Thus, the single-method WES approach provides an important simple tool to tailor therapeutic decisions in EC.

Deep Learning-Based Multifidelity Surrogate Modeling for High-Dimensional Reliability Prediction

Abstract Multifidelity surrogate modeling offers a cost-effective approach to reducing extensive evaluations of expensive physics-based simulations for reliability prediction. However, considering spatial uncertainties in multifidelity surrogate modeling remains extremely challenging due to the curse of dimensionality. To address this challenge, this paper introduces a deep learning-based multifidelity surrogate modeling approach that fuses multifidelity datasets for high-dimensional reliability analysis of complex structures. It first involves a heterogeneous dimension transformation approach to bridge the gap in terms of input format between the low-fidelity and high-fidelity domains. Then, an explainable deep convolutional dimension-reduction network (ConvDR) is proposed to effectively reduce the dimensionality of the structural reliability problems. To obtain a meaningful low-dimensional space, a new knowledge reasoning-based loss regularization mechanism is integrated with the covariance matrix adaptation evolution strategy (CMA-ES) to encourage an unbiased linear pattern in the latent space for reliability prediction. Then, the high-fidelity data can be utilized for bias modeling using Gaussian process (GP) regression. Finally, Monte Carlo simulation (MCS) is employed for the propagation of high-dimensional spatial uncertainties. Two structural examples are utilized to validate the effectiveness of the proposed method.

Byzantine-robust and efficient distributed sparsity learning: a surrogate composite quantile regression approach

Byzantine-robust and efficient distributed sparsity learning: a surrogate composite quantile regression approach