Gaussian Process Optimization Research Articles

Assessment of the Choked Flow Model of RELAP5 for Application of Inverse Quantification Methods

In the framework of deterministic safety analysis, best estimate plus uncertainty methodologies can provide a more informative detailed analysis of transients than conservative approaches. However, one important step in the application of such methodologies is derivation of uncertainty of the physical models. Probability density functions of the physical model parameters are obtained by applying inverse uncertainty quantification (IUQ) methods to experimental data. The present work deals with evaluation of the experimental database and assessment of the simulation model, which are required steps prior to the application of IUQ methods. The U.S. Nuclear Regulatory Commission system code RELAP5 has been applied for simulation of three experimental databases on choked/critical flow: Sozzi-Sutherland, Super MobyDick, and Marviken Critical Flow Tests. First, the adequacy of the experimental data to the specific target domain is carried out, to then proceed to calibration of the input model parameters by combining the use of Gaussian Process metamodels and optimization schemes. The assessment of the simulation models is performed by evaluating independently accuracy, precision, and consistency through four statistical indicators, including a novel indicator to evaluate the consistency of the results. The final results indicate that the model is capable of reproducing the selected experimental database and overall average accuracy, precision, and consistency below the 10% threshold and can be used for application of IUQ methods.

Gaussian process-based online sensor selection for source localization

This paper addresses the sensor selection problem for source localization within cyber–physical systems (CPSs). While recent machine learning and reinforcement learning approaches aim to optimize sensor selection and placement within the Area of Interest (AoI), their need for intensive data collection and training precludes online operation. Furthermore, these methods often require prior knowledge of the unknown source’s characteristics and lack adaptability to the dynamic nature of CPSs, leading to inefficiencies in unseen environments. This paper addresses these shortcomings using Gaussian process Optimization coupled with an active sensor selection mechanism to locate the unknown source within the AoI. The proposed approach first builds a probabilistic model of the environment, which is discretized into a grid, without prior training using a Gaussian Process surrogate model. Next, the model iteratively and systematically learns the underlying spatial phenomenon using Gaussian Process optimization. Concurrently, the approach selects a subset of sensors by optimizing a fitness function that advocates selecting informative and energy-efficient sensors. Next, the probabilistic model, having accurately learned the environment, directs the algorithm to the unknown source by identifying the cell with the highest likelihood of containing it. Finally, a peak refinement step is performed, which computes the exact location of the source within the designated cell. The proposed method’s efficacy is validated through experiments in radioactive source localization, validation studies, and adaptability assessments across various environments. In terms of quality of localization (QoL), it outperforms recent localization benchmarks, such as a reinforcement learning-based approach and DANS, by around 18% and 100%, respectively.

Nonlinear optimization for a low-emittance storage ring.

A multi-objective genetic algorithm (MOGA) is a powerful global optimization tool, but its results are considerably affected by the crossover parameter ηc. Finding an appropriate ηc demands too much computing time because MOGA needs be run several times in order to find a good ηc. In this paper, a self-adaptive crossover parameter is introduced in a strategy to adopt a new ηc for every generation while running MOGA. This new scheme has also been adopted for a multi-generation Gaussian process optimization (MGGPO) when producing trial solutions. Compared with the existing MGGPO and MOGA, the MGGPO and MOGA with the new strategy show better performance in nonlinear optimization for the design of low-emittance storage rings.

Accurate Memory Kernel Extraction from Discretized Time-Series Data.

Memory effects emerge as a fundamental consequence of dimensionality reduction when low-dimensional observables are used to describe the dynamics of complex many-body systems. In the context of molecular dynamics (MD) data analysis, accounting for memory effects using the framework of the generalized Langevin equation (GLE) has proven efficient, accurate, and insightful, particularly when working with high-resolution time series data. However, in experimental systems, high-resolution data are often unavailable, raising questions about the impact of the data resolution on the estimated GLE parameters. This study demonstrates that direct memory extraction from time series data remains accurate when the discretization time is below the memory time. To obtain memory functions reliably, even when the discretization time exceeds the memory time, we introduce a Gaussian Process Optimization (GPO) scheme. This scheme minimizes the deviation of discretized two-point correlation functions between time series data and GLE simulations and is able to estimate accurate memory kernels as long as the discretization time stays below the longest time scale in the data, typically the barrier crossing time.

Prediction of bridge structure deformation and strain based on dynamic testing and intelligent algorithms

The field load test is a direct and effective method for evaluating the performance of bridge structures. However, existing bridge field static load tests are costly and inefficient; moreover, they obstruct traffic and cause unavoidable damage to the bridge structure. As an alternative the the static load test, a random model update method based on bridge dynamic load tests and the Bayesian inference is proposed in this paper. The bridge static load test results were predicted with a high accuracy. To speed up the Bayesian method to infer the posterior probability density of the updated parameters, the Gaussian process was used in place of the finite element model, and the Bayesian inference used the Markov chain Monte Carlo method based on the delayed rejection adaptive Metropolis algorithm. First, the parameters to be modified for the bridge structure analysis model were determined based on the global sensitivity analysis method. Second, a uniform design sampling method was used to establish the Gaussian process optimization model to update the random model of the bridge structure. Finally, a reinforced concrete truss arch bridge was used to verify the correctness of the static load results of the bridge predicted by the random model update method based on dynamic load testing and Bayesian inference. The research results reveal that the prediction results of the bridge static load test based on the dynamic load test and Bayesian inference method agree with the actual test results.

Gaussian process optimization of phase change material heat sink design

Thermal management strategies based on phase change materials (PCMs) offer promising alternatives to conventional approaches, owing to their ability to absorb transient heat flows by melting. However, the design of PCM heat sinks is challenging due to the nonlinear interactions between heat flow and phase change during melting and solidification. This paper presents the design optimization of PCM heat sinks using a Gaussian Process (GP) method. We show that the GP method offers a significant decrease in computational intensity compared to conventional approaches used for optimization. We apply our method to optimize the design of a PCM-integrated heat sink for a gallium nitride (GaN) device that operates under a pulse train heat profile. Field’s metal-infused copper foam is used as the PCM. We used a reduced order model (ROM) for the PCM-integrated device, which is validated through experimental measurements and finite element simulations. We coupled the ROM with the GP optimizer to determine PCM heat sink design parameters, including geometric dimensions and the composition of the composite PCM, which minimizes both the GaN maximum junction temperature and junction temperature swing. We tested the GP optimizer under various conditions, encompassing GaN device power levels ranging from 1 to 4 W, pulse widths spanning 1 to 10 s, and duty cycles ranging from 10 to 90%. The GP optimizer produced nearly identical results to particle swarm optimization, with a mean absolute error <0.2 °C for optimal thermal performance and a reduction in computational time of 39×. Overall, our design method offers a computationally efficient approach to optimizing PCM-integrated heat sinks for the transient thermal management of electronic devices.

Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks

Data-driven materials design often encounters challenges where systems possess qualitative (categorical) information. Specifically, representing Metal-organic frameworks (MOFs) through different building blocks poses a challenge for designers to incorporate qualitative information into design optimization, and leads to a combinatorial challenge, with large number of MOFs that could be explored. In this work, we integrated Latent Variable Gaussian Process (LVGP) and Multi-Objective Batch-Bayesian Optimization (MOBBO) to identify top-performing MOFs adaptively, autonomously, and efficiently. We showcased that our method (i) requires no specific physical descriptors and only uses building blocks that construct the MOFs for global optimization through qualitative representations, (ii) is application and property independent, and (iii) provides an interpretable model of building blocks with physical justification. By searching only ~1% of the design space, LVGP-MOBBO identified all MOFs on the Pareto front and 97% of the 50 top-performing designs for the CO2 working capacity and CO2/N2 selectivity properties.

Static Behavior Prediction of Concrete Truss Arch Bridge Based on Dynamic Test Data and Bayesian Inference

The field load test is a direct and effective method for evaluating the performance of bridge structures. However, the existing bridge static load tests on site are costly, inefficient, and obstruct traffic; moreover, improper loading may also cause some damage to the bridge structure. This paper proposes a random model update method based on bridge dynamic load tests and the Bayesian inference as an alternative to the static load test. The Gaussian process model was used instead of the finite element model to reduce the cost of model calculation. Furthermore, choose the Markov Chain Monte Carlo (MCMC) method based on delay rejection adaptive Metropolis algorithm for Bayesian inference to improve the speed of the Bayesian method inferring the posterior probability density of updated parameters. First, the parameters to be updated for the bridge structure analysis model were determined based on the global sensitivity analysis method. Second, a uniform design sampling method was used to establish the Gaussian process optimization model to update the random model of the bridge structure. Finally, a reinforced concrete truss arch bridge was used to verify the correctness of the static load results of the bridge predicted by the random model update method based on dynamic load testing and Bayesian inference. The results show that the predicted results of the bridge static load test based on the dynamic load test and Bayesian reasoning method have an excellent agreement with the measured results, and this method can effectively overcome the adverse effects of the existing bridge static load test.

A hybrid-model optimization algorithm based on the Gaussian process and particle swarm optimization for mixed-variable CNN hyperparameter automatic search

A hybrid-model optimization algorithm based on the Gaussian process and particle swarm optimization for mixed-variable CNN hyperparameter automatic search

OCIF: automatically learning the optimized clinical information fusion method for computer-aided diagnosis tasks.

In computer-aided diagnosis, the fusion of image features extracted from neural networks and clinical information is crucial to improve diagnostic accuracy. How to integrate low-dimensional clinical information (LDCF) with high-dimensional network features (HDNF) is an urgent problem to be solved. We offer a new network search framework to address this problem, which can provide optimized LDCF fusion and efficient dimensionality reduction in HDNF. OCIF innovatively uses Gaussian process optimization to explore the search space for the number of fully connected (FC) layers, the number of neurons in each FC layer, the activation function, the dropout factor, and whether to add clinical information to each FC layer. Moreover, OCIF employs transfer learning to reduce the training parameter space and improve search efficiency. To evaluate the effectiveness of the proposed OCIF, we utilized three popular end-to-end overall survival (OS) time prediction models to predict the three classes. Our experimental results show that applying OCIF to a classical computer-aided diagnosis neural network can improve classification accuracy. Experiments on the 2020 BRATS dataset prove that OCIF achieves satisfactory performance, with an accuracy of 0.684, precision of 0.735, recall of 0.684, and F1-score of 0.675 on the OS time prediction task. OCIF effectively and creatively combines clinical information and network features, leveraging both clinical information and image features to enhance the accuracy of the final diagnosis. Our experiments demonstrate that the use of OCIF can significantly improve computer-aided diagnosis accuracy, and the approach has the potential to be extended to other medical classification tasks as well.

Improved Neurophysiological Process Imaging Through Optimization of Kalman Filter Initial Conditions

Recent work presented a framework for space-time-resolved neurophysiological process imaging that augments existing electromagnetic source imaging techniques. In particular, a nonlinear Analytic Kalman filter (AKF) has been developed to efficiently infer the states and parameters of neural mass models believed to underlie the generation of electromagnetic source currents. Unfortunately, as the initialization determines the performance of the Kalman filter, and the ground truth is typically unavailable for initialization, this framework might produce suboptimal results unless significant effort is spent on tuning the initialization. Notably, the relation between the initialization and overall filter performance is only given implicitly and is expensive to evaluate; implying that conventional optimization techniques, e.g. gradient or sampling based, are inapplicable. To address this problem, a novel efficient framework based on blackbox optimization has been developed to find the optimal initialization by reducing the signal prediction error. Multiple state-of-the-art optimization methods were compared and distinctively, Gaussian process optimization decreased the objective function by 82.1% and parameter estimation error by 62.5% on average with the simulation data compared to no optimization applied. The framework took only 1.6[Formula: see text]h and reduced the objective function by an average of 13.2% on 3.75[Formula: see text]min 4714-source channel magnetoencephalography data. This yields an improved method of neurophysiological process imaging that can be used to uncover complex underpinnings of brain dynamics.

Probabilistic Conflict Detection Using Heteroscedastic Gaussian Process and Bayesian Optimization

Probabilistic Conflict Detection Using Heteroscedastic Gaussian Process and Bayesian Optimization

Comparison of the Performance of a Surrogate Based Gaussian Process, NSGA2 and PSO Multi-objective Optimization of the Operation and Fuzzy Structural Reliability of Water Distribution System: Case Study for the City of Asmara, Eritrea

Comparison of the Performance of a Surrogate Based Gaussian Process, NSGA2 and PSO Multi-objective Optimization of the Operation and Fuzzy Structural Reliability of Water Distribution System: Case Study for the City of Asmara, Eritrea

A Study for Development Suitability of Biomass Power Generation Technology Based on GHG Emission Reduction Benefits and Growth Potential.

Biomass energy can alleviate global warming and solve energy depletion, which is increasingly concerned by the world. Due to the different emission reduction benefits and growth potential of different regions and biomass power generation technologies, analyzing the suitability of these technologies combined with regional conditions can more accurately guide the long- and short-term development of biomass power industry. However, there is no comprehensive evaluation of the benefits and potential of several biomass power generation technologies in different regions. Therefore, this paper introduces development suitability indexes and constructs life-cycle environmental impact and time-value economic impact assessment models, and a growth potential dynamic assessment model based on Gaussian process and particle swarm optimization to illustrate the greenhouse gas emission reduction benefits and growth potential of biomass power generation technologies. The empirical research of China shows that biomass gasification and direct combustion power generation can bring the best environmental benefits, and biogas power generation can bring the best economic benefits. For regions with abundant biomass resources and bad air condition, it is more suitable to develop gasification and direct combustion power generation technology, while mixed-combustion and biogas power generation technology are more suitable in regions with high electricity consumption.

Optimal information perturbation for traffic congestion mitigation: Gaussian process regression and optimization

Information perturbation is an information provision strategy which strategically alters the traffic information sent to drivers, aiming to mitigate network congestion caused by selfish routing decisions. Previous works have integrated information perturbation into coordinated routing mechanisms and theoretically proved that the system performance improvement due to information perturbation is more significant than the corresponding average user optimality loss. However, they do not give direct guidance as to which perturbation level should be implemented to manage the competing effects of system performance improvement and user optimality loss most efficiently. Accordingly, the goal of this work is to uncover the optimal perturbation that should be included in the information sent to vehicles under a coordinated routing scheme under some known network condition. The optimal perturbation problem considers the tradeoff between system performance improvement and user optimality loss due to perturbation, while ensuring that no exorbitant individual user optimality loss occurs. The relationships used in the optimization models are obtained through gaussian process regression, which are trained using the output of computer experiments. We pay special attention to the input features of these models, which impact the system performance and user optimality loss in our model the most—namely the perturbation, demand, and routing competition levels. We model route competition levels through a new parameter called weighted concentration, and present a novel approach for sampling weighted competition values for a single demand level. We present several candidate gaussian process specifications which are used in the optimization, including single and multiple output. Finally, we demonstrate the merit of our methodology through a sensitivity analysis using the Sioux Falls network as a test case. Here, we find that our optimization approach can find robust solutions (in terms of their proximity to local optimums) relatively high rate, with a satisfied solution time.

Improving the Flight Endurance of a Separate-Lift-and-Thrust Hybrid through Gaussian Process Optimization

A separate-lift-and-thrust hybrid is a modified fixed-wing drone which includes quadcopter rotors. This results in the combined capability of forwarding flight as well as vertical take-off and landing (VTOL), making it a low-cost method that can deliver substantial gains in utility. Though this is a strong point compared to other types of VTOL drones, the hybrid design may incur a significant trade-off because added weight and drag can severely reduce the drone's flight endurance. This study attempts to mitigate the impact by improving the configuration of the selection and positioning parameters. Since drag estimations are costly, a Gaussian process optimization method was performed, as it is economical with respect to the required number of iterations. A set of arbitrarily selected components was prepared for use with the optimization method, recording the relevant performance data and constructing the CAD models of the components for use in simulations. The optimization method was able to increase the estimated flight endurance to 27.99 minutes, a significant improvement compared to a set of random configurations, which only yielded 9.54 minutes at best. The respectable result was obtained even though difficulties were experienced regarding the infeasible regions that arise from the many constraints. Future implementation of this optimization approach can be further improved. It may be worthwhile to utilize a low-fidelity model from the base fixed-wing drone simulations, in contrast with using an initial zero mean for the prior of the Gaussian process.

Surrogates: Gaussian Process Modeling, Design, and Optimization for the Applied Sciences

Surrogates: Gaussian Process Modeling, Design, and Optimization for the Applied Sciences

A data fusion approach to optimize compositional stability of halide perovskites

Summary Search for resource-efficient materials in vast compositional spaces is an outstanding challenge in creating environmentally stable perovskite semiconductors. We demonstrate a physics-constrained sequential learning framework to subsequently identify the most stable alloyed organic-inorganic perovskites. We fuse data from high-throughput degradation tests and first-principle calculations of phase thermodynamics into an end-to-end Bayesian optimization algorithm using probabilistic constraints. By sampling just 1.8% of the discretized CsxMAyFA1−x−yPbI3 (MA, methylammonium; FA, formamidinium) compositional space, perovskites centered at Cs0.17MA0.03FA0.80PbI3 show minimal optical change under increased temperature, moisture, and illumination with >17-fold stability improvement over MAPbI3. The thin films have 3-fold improved stability compared with state-of-the-art multi-halide Cs0.05(MA0.17FA0.83)0.95Pb(I0.83Br0.17)3, translating into enhanced solar cell stability without compromising conversion efficiency. Synchrotron-based X-ray scattering validates the suppression of chemical decomposition and minority phase formation achieved using fewer elements and a maximum of 8% MA. We anticipate that this data fusion approach can be extended to guide materials discovery for a wide range of multinary systems.

Advanced Prediction of Roadway Broken Rock Zone Based on a Novel Hybrid Soft Computing Model Using Gaussian Process and Particle Swarm Optimization

A simple and accurate evaluation method of broken rock zone thickness (BRZT), which is usually used to describe the broken rock zone (BRZ), is meaningful, due to its ability to provide a reference for the roadway stability evaluation and support design. To create a relationship between various geological variables and the broken rock zone thickness (BRZT), the multiple linear regression (MLR), artificial neural network (ANN), Gaussian process (GP) and particle swarm optimization algorithm (PSO)-GP method were utilized, and the corresponding intelligence models were developed based on the database collected from various mines in China. Four variables including embedding depth (ED), drift span (DS), surrounding rock mass strength (RMS) and joint index (JI) were selected to train the intelligence model, while broken rock zone thickness (BRZT) is chosen as the output variable, and the k-fold cross-validation method was applied in the training process. After training, three validation metrics including variance account for (VAF), determination coefficient (R2) and root mean squared error (RMSE) were applied to describe the predictive performance of these developed models. After comparing performance based on a ranking method, the obtained results show that the PSO-GP model provides the best predictive performance in estimating broken rock zone thickness (BRZT). In addition, the sensitive effect of collected variables on broken rock zone thickness (BRZT) can be listed as JI, ED, DS and RMS, and JI was found to be the most sensitive factor.

Fast Scanning Probe Microscopy via Machine Learning: Non-Rectangular Scans with Compressed Sensing and Gaussian Process Optimization.

Fast scanning probe microscopy enabled via machine learning allows for a broad range of nanoscale, temporally resolved physics to be uncovered. However, such examples for functional imaging are few in number. Here, using piezoresponse force microscopy (PFM) as a model application, a factor of 5.8 reduction in data collection using a combination of sparse spiral scanning with compressive sensing and Gaussian process regression reconstruction is demonstrated. It is found that even extremely sparse spiral scans offer strong reconstructions with less than 6% error for Gaussian process regression reconstructions. Further, the error associated with each reconstructive technique per reconstruction iteration is analyzed, finding the error is similar past ≈15 iterations, while at initial iterations Gaussian process regression outperforms compressive sensing. This study highlights the capabilities of reconstruction techniques when applied to sparse data, particularly sparse spiral PFM scans, with broad applications in scanning probe and electron microscopies.