Individualized treatment rule characterization via a value function surrogate.

Precision medicine is a promising framework for generating evidence to improve health and health care. Yet, a gap persists between the ever-growing number of statistical precision medicine strategies for evidence generation and implementation in real-world clinical settings, and the strategies for closing this gap will likely be context-dependent. In this paper, we consider the specific context of partial compliance to wound management among patients with peripheral artery disease. Using a Gaussian process surrogate for the value function, we show the feasibility of using Bayesian optimization to learn optimal individualized treatment rules. Further, we expand beyond the common precision medicine task of learning an optimal individualized treatment rule to the characterization of classes of individualized treatment rules and show how those findings can be translated into clinical contexts.

An integrated finite element method and machine learning algorithm for brain morphology prediction.

The human brain development experiences a complex evolving cortical folding from a smooth surface to a convoluted ensemble of folds. Computational modeling of brain development has played an essential role in better understanding the process of cortical folding, but still leaves many questions to be answered. A major challenge faced by computational models is how to create massive brain developmental simulations with affordable computational sources to complement neuroimaging data and provide reliable predictions for brain folding. In this study, we leveraged the power of machine learning in data augmentation and prediction to develop a machine-learning-based finite element surrogate model to expedite brain computational simulations, predict brain folding morphology, and explore the underlying folding mechanism. To do so, massive finite element method (FEM) mechanical models were run to simulate brain development using the predefined brain patch growth models with adjustable surface curvature. Then, a GAN-based machine learning model was trained and validated with these produced computational data to predict brain folding morphology given a predefined initial configuration. The results indicate that the machine learning models can predict the complex morphology of folding patterns, including 3-hinge gyral folds. The close agreement between the folding patterns observed in FEM results and those predicted by machine learning models validate the feasibility of the proposed approach, offering a promising avenue to predict the brain development with given fetal brain configurations.

Mitigating Measurement Inaccuracies in Digital Twins of Construction Machinery through Multi-Objective Optimization.

The advent of digital twins facilitates the generation of high-fidelity replicas of actual systems or assets, thereby enhancing the design's performance and feasibility. When developing digital twins, precise measurement data is essential to ensure alignment between the actual and digital models. However, inherent uncertainties in sensors and models lead to disparities between observed and predicted (simulated) behaviors. To mitigate these uncertainties, this study originally proposes a multi-objective optimization strategy utilizing a Gaussian process regression surrogate model, which integrates various uncertain parameters, such as load angle, bucket cylinder stroke, arm cylinder stroke, and boom cylinder stroke. This optimization employs a genetic algorithm to indicate the Pareto frontiers regarding the pressure exerted on the boom, arm, and bucket cylinders. Subsequently, TOPSIS is applied to ascertain the optimal candidate among the identified Pareto optima. The findings reveal a substantial congruence between the experimental and numerical outcomes of the devised virtual model, in conjunction with the TOPSIS-derived optimal parameter configuration.

Fatigue reliability analysis of aeroengine blade-disc systems using physics-informed ensemble learning.

For the fatigue reliability analysis of aeroengine blade-disc systems, the traditional direct integral modelling methods or separate independent modelling methods will lead to low computational efficiency or accuracy. In this work, a physics-informed ensemble learning (PIEL) method is proposed, i.e. firstly, based on the physical characteristics of blade-disc systems, the complex multi-component reliability analysis is split into a series of single-component reliability analyses; moreover, the PIEL model is established by introducing the mapping of multiple constitutive responses and the multi-material physical characteristics into the ensemble learning; finally, the PIEL-based system reliability framework is established by quantifying the failure correlation with the Copula function. The reliability analysis of a typical aeroengine high-pressure turbine blade-disc system is regarded as an example to verify the effectiveness of the proposed method. Compared with the direct Monte Carlo, support vector regression, neural network, ensemble learning and physics-informed neural network, the proposed method exhibits the highest computing accuracy and efficiency, and is validated to be an efficient method for the reliability analysis of blade-disc systems. The current work can provide a novel insight for physics-informed modelling and fatigue reliability analyses. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.

Review of machine learning-based surrogate models of groundwater contaminant modeling.

Heavy computational load inhibits the application of groundwater contaminant numerical model to groundwater pollution source identification, remediation design, and uncertainty analysis, since a large number of model runs are required for these applications. Machine learning-based surrogate models are an effective approach to enhance the efficiency of the numerical models, and have recently attracted considerable attention in the field of groundwater contaminant modeling. Here, we review 120 research articles on machine learning-based surrogate models for groundwater contaminant modeling that were published between 1994 and 2022. We outline the state of the art method, identify the most significant research challenges, and suggest potential future directions. The six major applications of machine learning-based surrogate models are groundwater pollution source identification, groundwater remediation design, coastal aquifer management, uncertainty analysis of groundwater, groundwater monitoring network design, and groundwater transport parameters inversion. Together, these account for more than 90% of the studies we review. Latin hypercube sampling (LHS) is the most widely used sampling method, and artificial neural networks (ANNs) and Kriging are the two most widely used methods for constructing surrogate model. No method is universally superior, the advantages and disadvantages of different methods, as well as the applicability of these methods for different application purposes of groundwater contaminant modeling were analyzed. Some recommendations on the method selection for various application fields are given based on the reviews and experiences. Based on our review of the state-of-the-art, we suggest several future research directions to enhance the feasibility of the machine learning-based surrogate models of groundwater contaminant modeling: the alleviation of the curse of dimensionality, enhancing transferability, practical applications for real case studies, multi-source dada fusion, and real-time monitoring and prediction.

Connecting Agent-Based Models with High-Dimensional Parameter Spaces to Multidimensional Data Using SMoRe ParS: A Surrogate Modeling Approach.

Across a broad range of disciplines, agent-based models (ABMs) are increasingly utilized for replicating, predicting, and understanding complex systems and their emergent behavior. In the biological and biomedical sciences, researchers employ ABMs to elucidate complex cellular and molecular interactions across multiple scales under varying conditions. Data generated at these multiple scales, however, presents a computational challenge for robust analysis with ABMs. Indeed, calibrating ABMs remains an open topic of research due to their own high-dimensional parameter spaces. In response to these challenges, we extend and validate our novel methodology, Surrogate Modeling for Reconstructing Parameter Surfaces (SMoRe ParS), arriving at a computationally efficient framework for connecting high dimensional ABM parameter spaces with multidimensional data. Specifically, we modify SMoRe ParS to initially confine high dimensional ABM parameter spaces using unidimensional data, namely, single time-course information of in vitro cancer cell growth assays. Subsequently, we broaden the scope of our approach to encompass more complex ABMs and constrain parameter spaces using multidimensional data. We explore this extension with in vitro cancer cell inhibition assays involving the chemotherapeutic agent oxaliplatin. For each scenario, we validate and evaluate the effectiveness of our approach by comparing how well ABM simulations match the experimental data when using SMoRe ParS-inferred parameters versus parameters inferred by a commonly used direct method. In so doing, we show that our approach of using an explicitly formulated surrogate model as an interlocutor between the ABM and the experimental data effectively calibrates the ABM parameter space to multidimensional data. Our method thus provides a robust and scalable strategy for leveraging multidimensional data to inform multiscale ABMs and explore the uncertainty in their parameters.

Electromagnetic Wave Absorption in the Human Head: A Virtual Sensor Based on a Deep-Learning Model.

Determining the amount of electromagnetic wave energy absorbed by the human body is an important issue in the analysis of wireless systems. Typically, numerical methods based on Maxwell's equations and numerical models of the body are used for this purpose. This approach is time-consuming, especially in the case of high frequencies, for which a fine discretization of the model should be used. In this paper, the surrogate model of electromagnetic wave absorption in human body, utilizing Deep-Learning, is proposed. In particular, a family of data from finite-difference time-domain analyses makes it possible to train a Convolutional Neural Network (CNN), in view of recovering the average and maximum power density in the cross-section region of the human head at the frequency of 3.5 GHz. The developed method allows for quick determination of the average and maximum power density for the area of the entire head and eyeball areas. The results obtained in this way are similar to those obtained by the method based on Maxwell's equations.

The Application of a Topology Optimization Algorithm Based on the Kriging Surrogate Model in the Mirror Design and Optimization of an Aerial Camera.

In a Cassegrain optical system, the surface precision of the primary mirror is an important factor in the quality of the image. The design of a lightweight primary mirror with a high-quality optical surface is crucial. In this thesis, an integrated mirror light engine design optimization process is proposed for an aviation optoelectronic device. It is based on the Kriging surrogate model and nests the topology optimization algorithm, which constructs the mirror RMS value response surface and obtains the dominant relationship between mirror structure and surface accuracy. The optimal surface figure lightweight structure of the mirror is obtained by optimizing the surrogate model with an additive criterion and multi-objective optimization analysis. The root mean square value (RMS) of the corresponding primary mirror is 10.41 nm, which is better than 1/40 λ (λ = 632.8 nm). This meets the optical design specifications. The optimal primary mirror structure is analyzed by using the finite element method, which verifies the precision of the Kriging surrogate model. It has an error of 0.28%. The kinetic analysis of the primary mirror shows that the primary mirror does not yield to plastic deformation or even failure under a three-way 20 g acceleration load. This meets the environmental suitability requirements.

Bridge Model Updating Based on Wavelet Neural Network and Wind-Driven Optimization.

Aging, corrosive environments, and inadequate maintenance may result in performance deterioration of civil infrastructures, and finite element model updating is a commonly employed structural health monitoring procedure in civil engineering to reflect the current situation and to ensure the safety and serviceability of structures. Using the finite element model updating process to obtain the relationship between the structural responses and updating parameters, this paper proposes a method of using the wavelet neural network (WNN) as the surrogate model combined with the wind-driven optimization (WDO) algorithm to update the structural finite element model. The method was applied to finite element model updating of a continuous beam structure of three equal spans to verify its feasibility, the results show that the WNN can reflect the nonlinear relationship between structural responses and the parameters and has an outstanding simulation performance; the WDO has an excellent ability for optimization and can effectively improve the efficiency of model updating. Finally, the method was applied to update a real bridge model, and the results show that the finite element model update based on WDO and WNN is applicable to the updating of a multi-parameter bridge model, which has practical significance in engineering and high efficiency in finite element model updating. The differences between the updated values and measured values are all within the range of 5%, while the maximum difference was reduced from -10.9% to -3.6%. The proposed finite element model updating method is applicable and practical for multi-parameter bridge model updating and has the advantages of high updating efficiency, reliability, and practical significance.

Damage Quantification and Identification in Structural Joints through Ultrasonic Guided Wave-Based Features and an Inverse Bayesian Scheme.

In this paper, defect detection and identification in aluminium joints is investigated based on guided wave monitoring. Guided wave testing is first performed on the selected damage feature from experiments, namely, the scattering coefficient, to prove the feasibility of damage identification. A Bayesian framework based on the selected damage feature for damage identification of three-dimensional joints of arbitrary shape and finite size is then presented. This framework accounts for both modelling and experimental uncertainties. A hybrid wave and finite element approach (WFE) is adopted to predict the scattering coefficients numerically corresponding to different size defects in joints. Moreover, the proposed approach leverages a kriging surrogate model in combination with WFE to formulate a prediction equation that links scattering coefficients to defect size. This equation replaces WFE as the forward model in probabilistic inference, resulting in a significant enhancement in computational efficiency. Finally, numerical and experimental case studies are used to validate the damage identification scheme. An investigation into how the location of sensors can impact the identified results is provided as well.

Efficient Photoacoustic Image Synthesis with Deep Learning.

Photoacoustic imaging potentially allows for the real-time visualization of functional human tissue parameters such as oxygenation but is subject to a challenging underlying quantification problem. While in silico studies have revealed the great potential of deep learning (DL) methodology in solving this problem, the inherent lack of an efficient gold standard method for model training and validation remains a grand challenge. This work investigates whether DL can be leveraged to accurately and efficiently simulate photon propagation in biological tissue, enabling photoacoustic image synthesis. Our approach is based on estimating the initial pressure distribution of the photoacoustic waves from the underlying optical properties using a back-propagatable neural network trained on synthetic data. In proof-of-concept studies, we validated the performance of two complementary neural network architectures, namely a conventional U-Net-like model and a Fourier Neural Operator (FNO) network. Our in silico validation on multispectral human forearm images shows that DL methods can speed up image generation by a factor of 100 when compared to Monte Carlo simulations with 5×108 photons. While the FNO is slightly more accurate than the U-Net, when compared to Monte Carlo simulations performed with a reduced number of photons (5×106), both neural network architectures achieve equivalent accuracy. In contrast to Monte Carlo simulations, the proposed DL models can be used as inherently differentiable surrogate models in the photoacoustic image synthesis pipeline, allowing for back-propagation of the synthesis error and gradient-based optimization over the entire pipeline. Due to their efficiency, they have the potential to enable large-scale training data generation that can expedite the clinical application of photoacoustic imaging.

Machine learning-based surrogate model assisting stochastic model predictive control of urban drainage systems.

Quantifying the uncertainty of stormwater inflow is critical for improving the resilience of urban drainage systems (UDSs). However, the high computational complexity and time consumption obstruct the implementation of uncertainty-addressing methods for real-time control of UDSs. To address this issue, this study developed a machine learning-based surrogate model (MLSM) that maintains high-fidelity descriptions of drainage dynamics and meanwhile diminishes the computational complexity. With stormwater inflow and controls as inputs and system overflow as the output, MLSM is able to fast evaluate system performance, and therefore stochastic optimization becomes feasible. Thus, a real-time control strategy was built by combining MLSM with the stochastic model predictive control. This strategy used stochastic stormwater inflow scenarios as input and aimed to minimize the expected overflow under all scenarios. An ensemble of stormwater inflow scenarios was generated by assuming the forecast errors follow normal distributions. To downsize the ensemble, representative scenarios with their probabilities were selected using the simultaneous backward reduction method. The proposed control strategy was applied to a combined UDS of China. Results are as follows. (1) MLSM fit well with the original high-fidelity urban drainage model, while the computational time was reduced by 99.1%. (2) The proposed strategy consistently outperformed the classical deterministic model predictive control in both magnitude and duration dimensions of system resilience, when the consumed time compatible is with the real-time operation. It is indicated that the proposed control strategy could be used to inform the real-time operation of complex UDSs and thus enhance system resilience to uncertainty.

Surrogate-Assisted Hybrid Meta-Heuristic Algorithm with an Add-Point Strategy for a Wireless Sensor Network.

Meta-heuristic algorithms are widely used in complex problems that cannot be solved by traditional computing methods due to their powerful optimization capabilities. However, for high-complexity problems, the fitness function evaluation may take hours or even days to complete. The surrogate-assisted meta-heuristic algorithm effectively solves this kind of long solution time for the fitness function. Therefore, this paper proposes an efficient surrogate-assisted hybrid meta-heuristic algorithm by combining the surrogate-assisted model with gannet optimization algorithm (GOA) and the differential evolution (DE) algorithm, abbreviated as SAGD. We explicitly propose a new add-point strategy based on information from historical surrogate models, using information from historical surrogate models to allow the selection of better candidates for the evaluation of true fitness values and the local radial basis function (RBF) surrogate to model the landscape of the objective function. The control strategy selects two efficient meta-heuristic algorithms to predict the training model samples and perform updates. A generation-based optimal restart strategy is also incorporated in SAGD to select suitable samples to restart the meta-heuristic algorithm. We tested the SAGD algorithm using seven commonly used benchmark functions and the wireless sensor network (WSN) coverage problem. The results show that the SAGD algorithm performs well in solving expensive optimization problems.

Evolution of SIVmac239 following serial passaging in humanized mice.

Serial passage of SIVmac239 allows for greater understanding of the genetic changes necessary for cross-species transmission of primate lentiviruses into humans. Using humanized mice, we show that adaptive mutations continue to accumulate in SIVmac239 during four serial passages, with persistent CD4+ T cell decline and increases in plasma viral loads.

Surrogate-Model-Based Interval Analysis of Spherical Conformal Array Antenna with Power Pattern Tolerance.

A method based on an interval arithmetic is proposed to analyze uncertain factors such as the curvature radii, excitation amplitude, and excitation phase of a spherical conformal array antenna. An interval description of element factors under different curvature radii of spherical substrates is established using the surrogate model based on the data obtained through a full-wave analysis method. The interval formula of the spherical curvature radius and array element position error is derived and the effects of the spherical radius tolerance, excitation amplitude tolerance, and excitation phase tolerance on the antenna power pattern are studied. To evaluate the effectiveness and reliability of the proposed method, a set of representative numerical results are reported and discussed and a comparison with the Monte Carlo methods and full-wave simulation is described. This method can be widely used during the antenna design and before the antenna prototyping/manufacturing to predict the effects, on the radiation performance, of possible errors/tolerances in the antenna structure to guarantee the antenna working 'in operation'.

Data-driven Uncertainty Quantification in Computational Human Head Models.

Computational models of the human head are promising tools for estimating the impact-induced response of the brain, and thus play an important role in the prediction of traumatic brain injury. The basic constituents of these models (i.e., model geometry, material properties, and boundary conditions) are often associated with significant uncertainty and variability. As a result, uncertainty quantification (UQ), which involves quantification of the effect of this uncertainty and variability on the simulated response, becomes critical to ensure reliability of model predictions. Modern biofidelic head model simulations are associated with very high computational cost and high-dimensional inputs and outputs, which limits the applicability of traditional UQ methods on these systems. In this study, a two-stage, data-driven manifold learning-based framework is proposed for UQ of computational head models. This framework is demonstrated on a 2D subject-specific head model, where the goal is to quantify uncertainty in the simulated strain fields (i.e., output), given variability in the material properties of different brain substructures (i.e., input). In the first stage, a data-driven method based on multi-dimensional Gaussian kernel-density estimation and diffusion maps is used to generate realizations of the input random vector directly from the available data. Computational simulations of a small number of realizations provide input-output pairs for training data-driven surrogate models in the second stage. The surrogate models employ nonlinear dimensionality reduction using Grassmannian diffusion maps, Gaussian process regression to create a low-cost mapping between the input random vector and the reduced solution space, and geometric harmonics models for mapping between the reduced space and the Grassmann manifold. It is demonstrated that the surrogate models provide highly accurate approximations of the computational model while significantly reducing the computational cost. Monte Carlo simulations of the surrogate models are used for uncertainty propagation. UQ of the strain fields highlights significant spatial variation in model uncertainty, and reveals key differences in uncertainty among commonly used strain-based brain injury predictor variables.

A Mahalanobis Surrogate-Assisted Ant Lion Optimization and Its Application in 3D Coverage of Wireless Sensor Networks.

Metaheuristic algorithms are widely employed in modern engineering applications because they do not need to have the ability to study the objective function's features. However, these algorithms may spend minutes to hours or even days to acquire one solution. This paper presents a novel efficient Mahalanobis sampling surrogate model assisting Ant Lion optimization algorithm to address this problem. For expensive calculation problems, the optimization effect goes even further by using MSAALO. This model includes three surrogate models: the global model, Mahalanobis sampling surrogate model, and local surrogate model. Mahalanobis distance can also exclude the interference correlations of variables. In the Mahalanobis distance sampling model, the distance between each ant and the others could be calculated. Additionally, the algorithm sorts the average length of all ants. Then, the algorithm selects some samples to train the model from these Mahalanobis distance samples. Seven benchmark functions with various characteristics are chosen to testify to the effectiveness of this algorithm. The validation results of seven benchmark functions demonstrate that the algorithm is more competitive than other algorithms. The simulation results based on different radii and nodes show that MSAALO improves the average coverage by 2.122% and 1.718%, respectively.

Active learning for efficiently training emulators of computationally expensive mathematical models.

An emulator is a fast-to-evaluate statistical approximation of a detailed mathematical model (simulator). When used in lieu of simulators, emulators can expedite tasks that require many repeated evaluations, such as sensitivity analyses, policy optimization, model calibration, and value-of-information analyses. Emulators are developed using the output of simulators at specific input values (design points). Developing an emulator that closely approximates the simulator can require many design points, which becomes computationally expensive. We describe a self-terminating active learning algorithm to efficiently develop emulators tailored to a specific emulation task, and compare it with algorithms that optimize geometric criteria (random latin hypercube sampling and maximum projection designs) and other active learning algorithms (treed Gaussian Processes that optimize typical active learning criteria). We compared the algorithms' root mean square error (RMSE) and maximum absolute deviation from the simulator (MAX) for seven benchmark functions and in a prostate cancer screening model. In the empirical analyses, in simulators with greatly varying smoothness over the input domain, active learning algorithms resulted in emulators with smaller RMSE and MAX for the same number of design points. In all other cases, all algorithms performed comparably. The proposed algorithm attained satisfactory performance in all analyses, had smaller variability than the treed Gaussian Processes, and, on average, had similar or better performance as the treed Gaussian Processes in six out of seven benchmark functions and in the prostate cancer model.

Protective Headgear Attenuates Forces on the Inner Table and Pressure in the Brain Parenchyma During Blast and Impact: An Experimental Study Using a Simulant-Based Surrogate Model of the Human Head.

Military personnel sustain head and brain injuries as a result of ballistic, blast, and blunt impact threats. Combat helmets are meant to protect the heads of these personnel during injury events. Studies show peak kinematics and kinetics are attenuated using protective headgear during impacts; however, there is limited experimental biomechanical literature that examines whether or not helmets mitigate peak mechanics delivered to the head and brain during blast. While the mechanical links between blast and brain injury are not universally agreed upon, one hypothesis is that blast energy can be transmitted through the head and into the brain. These transmissions can lead to rapid skull flexure and elevated pressures in the cranial vault, and, therefore, may be relevant in determining injury likelihood. Therefore, it could be argued that assessing a helmet for the ability to mitigate mechanics may be an appropriate paradigm for assessing the potential protective benefits of helmets against blast. In this work, we use a surrogate model of the head and brain to assess whether or not helmets and eye protection can alter mechanical measures during both head-level face-on blast and high forehead blunt impact events. Measurements near the forehead suggest head protection can attenuate brain parenchyma pressures by as much as 49% during blast and 52% during impact, and forces on the inner table of the skull by as much as 80% during blast and 84% during impact, relative to an unprotected head.

ASAMS: An Adaptive Sequential Sampling and Automatic Model Selection for Artificial Intelligence Surrogate Modeling.

Surrogate Modeling (SM) is often used to reduce the computational burden of time-consuming system simulations. However, continuous advances in Artificial Intelligence (AI) and the spread of embedded sensors have led to the creation of Digital Twins (DT), Design Mining (DM), and Soft Sensors (SS). These methodologies represent a new challenge for the generation of surrogate models since they require the implementation of elaborated artificial intelligence algorithms and minimize the number of physical experiments measured. To reduce the assessment of a physical system, several existing adaptive sequential sampling methodologies have been developed; however, they are limited in most part to the Kriging models and Kriging-model-based Monte Carlo Simulation. In this paper, we integrate a distinct adaptive sampling methodology to an automated machine learning methodology (AutoML) to help in the process of model selection while minimizing the system evaluation and maximizing the system performance for surrogate models based on artificial intelligence algorithms. In each iteration, this framework uses a grid search algorithm to determine the best candidate models and perform a leave-one-out cross-validation to calculate the performance of each sampled point. A Voronoi diagram is applied to partition the sampling region into some local cells, and the Voronoi vertexes are considered as new candidate points. The performance of the sample points is used to estimate the accuracy of the model for a set of candidate points to select those that will improve more the model's accuracy. Then, the number of candidate models is reduced. Finally, the performance of the framework is tested using two examples to demonstrate the applicability of the proposed method.