Rapid CFD Prediction Based on Machine Learning Surrogate Model in Built Environment: A Review

Batteries, recognized as effective energy storage solutions, are considered the main facilitators of the world-wide transition towards clean and renewable energy sources. Among different types of batteries, lithium-ion (Li-ion) variants offer higher energy densities and relatively longer life spans when compared to other types. Nonetheless, a primary concern with these batteries is their lifetime. Batteries undergo various degradation mechanisms under storage and use, significantly impacting their lifespan. To this end, it is crucial to predict the degradation and lifetime of Li-ion batteries under given conditions.Researchers use three main methodologies to perform battery health diagnostics and to predict the lifetime of batteries. One approach revolves around using mechanistic, first-principle electrochemical models, also known as physics-based models. If equipped with proper thermodynamic theories, such models can show promising capabilities; however, holistic degradation prediction with these models is still challenging due to the computational complexities and the multitude of parameters that need to be fine-tuned in this approach. The other common strategy is to use empirical models to predict battery degradation. These models generally entail fewer parameters to be identified and are computationally less intensive to solve. Nonetheless, empirical models can suffer from the accuracy point-of-view as they are constrained to predict degradation trends introduced by certain degradation modes. Another common technique in battery life prediction is to utilize purely data-driven methods, such as machine learning (ML) algorithms, which also have shown promising results in the literature on rapid health predictions. However, these methods require large volumes of experimental data for training and testing ML models to ensure accuracy. In addition, data-driven methods are likely to extrapolate poorly to conditions beyond their training data and are indifferent towards the underlying degradation mechanisms. Recently, physics-informed machine learning (PI-ML) methods have garnered significant attention. They integrate physics-based or empirical models (developed based on physics) with a data-driven approach and allow one to train ML models on a smaller set of experimental data.To the best of the authors’ knowledge, the performance comparison between first-principle and empirical models when integrated within PI-ML remains unclear. Therefore, in this work, we aim to compare these two models when applied to prognostics (capacity forecasting and remaining useful life prediction) of a set of Li-ion batteries. To perform this study, we generate aging data for 40 Li-ion coin cells cycled under randomized conditions. Each cell undergoes a three-step charging stage followed by a two-step discharge stage. After obtaining the aging data, we will develop two PI-ML models, one equipped with a physics-based model and another with a set of empirical models. Both PI-ML models in this work will follow the sequential integration approach, where the training data for the final PI-ML model come from both experimental and computational data, the latter of which are obtained from the physics-based or empirical models. The parameters for the physics-based and empirical models are identified from another set of experimental data. Finally, the PI-ML models will be tested with experimental data obtained at different cycling conditions. The data flow for the sequential architecture of PI-ML is shown in the attached figure. This comparative study will help identify the performance of physics-based and empirical models when integrated into PI-ML. The main performance metric considered in this work is each model’s ability to extrapolate beyond the experimental training data set, hence aiding the final PI-ML model in generalizing to conditions not covered by its experimental training data set. Figure 1

Nowadays, Computational Fluid Dynamics (CFD) simulations play an increasingly important role for turbine airfoil design. This high-fidelity approach is capable to provide accurate information of flow fields. Meanwhile, the calculation accuracy is always gained at the expense of numerical cost. This gap limits opportunities for design space exploration. To address this problem, surrogate models (also known as metamodels) are introduced to approximate high-fidelity CFD models. However, traditional surrogate models, such as Kriging or Radial Basis Function, construct response surface on a design space with limited dimensions. This prevents users from predicting the flow fields directly from the geometry and performing interactive design of airfoil. In the present work, we propose a Convolutional Neural Network (CNN) based surrogate model to predict flow properties on turbine vane airfoil surface from 3D airfoil profile defined by point cloud. The proposed CNN architecture adopts a symmetric expanding path that is similar to the so-called U-Net. The geometries in the training and testing dataset are generated via varying the parameters defined by the Free-Form Deformation approach. The corresponding flow fields are obtained through high-fidelity CFD simulations performed in a finite volume context. Furthermore, a gaussian process based Bayesian optimization technique is utilized to tune automatically the hyperparameters of the network. In this work, we trained the CNN based surrogate model with static pressure and temperature on the mean section of turbine vane airfoil surface. The trained model is able to predict in a reliable and efficient way the corresponding property directly from the 3D geometry, which allows engineers to agilely adjust their airfoil design.

Aim: The majority of machine learning (ML) models in healthcare are built on retrospective data, much of which is collected without explicit patient consent for use in artificial intelligence (AI) and ML applications. The primary aim of this study was to evaluate whether clinicians and scientific researchers themselves consent to provide their own data for the training of ML models. Materials and Methods: This survey was conducted through an anonymous online survey, utilizing platforms such as Telegram, LinkedIn, and Viber. The target audience comprised specific international groups, primarily Russian, German, and English-speaking, of clinicians and scientific researchers. These participants ranged in their levels of expertise and experience, from beginners to veterans. The survey centered on a singular, pivotal question: “Do You Consent to the Use of Your Biological and Private Data for Training Machine Learning and AI Models?” Respondents had the option to choose from three responses: “Yes” and “No”. Results: The survey was conducted in January 2024. A total of 119 unique and verified individuals participated in the survey. The results revealed that only 50% of respondents (63 persons) expressed consent to provide their own data for the training of ML and AI models. Conclusion: In the development of ML and AI models, particularly open-source ones, it is crucial to ascertain whether participants are willing to provide their private data. While ML algorithms can transform the nature of data, it is important to remember that the primary owner of this data is the individual. Our findings show that in 50% of the cases, even participants from scientific research and clinical backgrounds – individuals typically accountable for ensuring data quality in AI and ML model development – do not consent to the use of their data in AI and ML settings. This highlights the need for more stringent consent processes and ethical considerations in the utilization of personal data in AI and ML research.

Surrogate models have been used to replace computationally expensive analysis models in engineering design problems. However, time-dependent variables and historical data are usually ignored in the surrogate modeling process. For instance, in a dam network design, using hydraulic simulations to estimate the water flow is computationally expensive, and the data is in the form of time series. So, we need time-dependent surrogate models to replace these simulations and manage this computational complexity. In this paper, we describe surrogate models to predict the amount of water flow into a reservoir. The challenge is that the flow is a time-dependent variable, and we need to incorporate time series into surrogate models. Thus, there are three contributions: (1) using surrogate modeling to predict flow for dam network design, (2) incorporating time series analysis in surrogate models for water network design, (3) using an ensemble of surrogates to increase the accuracy of prediction. We also demonstrate how to integrate surrogate models and machine learning with time series analysis for more accurate and faster prediction. Due to the availability of data, we use the Buffalo Reservoir in the Red River Basin as an example. Based on the time series data for flow, evaporation, precipitation, and maximum and minimum temperature, three surrogate models are used to examine the impact of integrating time series into surrogate models. These are multivariate autoregressive integrated moving average (MARIMA), a classic time series analysis method; artificial neural network (ANN), and random forest (RF) methods, two machine learning surrogate models. We use seven different time lags as features within an RF model, as an ensemble of surrogate models, and predict the flow for seven-time steps ahead. We successfully incorporate the time series data and particularly the concept of the time lag within surrogate models. We show that RF as the ensemble of surrogates provides more accurate predictions than the other two surrogate models. Although this method has been demonstrated for the Red River Basin, it could also be applied to designing anything in which time-dependent flow is an issue, for example, in biomedical applications, the management of manufacturing processes and product sales as well as any products in which fluid flow is an issue.

The future 6G network will be able to connect massive and various unmanned vehicles (UxVs) into the network, bringing novel requirements toward UxV network security and data privacy. Deploying machine learning (ML)-based intrusion detection on UxVs can be one promising approach. The conventional approach cannot fulfill security and privacy requirements, as the structure can be more flexible, and there may be a lack of a central node in the 6G-based UxV network. Moreover, UxV clients can exhibit high heterogeneity with extremely class-imbalanced training samples. With the presence of federated learning (FL), UxVs can collaborate to train and update ML models while preserving data privacy in the UxV security critical scenario. However, most past works focused on centralized approaches, using cloud servers to assist intrusion detection and service deployments. This article introduces an FL framework with a decentralized design for training ML models on UxVs using intrusion detection as a study case. This scheme can be more flexible, as UxV clients can collaborate to train and synchronize models without the central server. Simulation experiments were conducted to evaluate the efficiency of the proposed approach. Experimental results and theoretical analysis confirm that the proposed method outperforms baseline models with FedAvg and local-trained client models.

The 2010-2011 Canterbury Earthquake sequence (CES) led to unprecedented building damage in the Canterbury region, New Zealand. Commercial and residential buildings were significantly affected. Due to New Zealand’s unique insurance setting, around 80% of the losses were covered by insurance (Bevere & Balz, 2012; King et al., 2014). The Insurance Council of New Zealand (ICNZ) estimated the total economic losses to be more than NZ$40 billion, with the Earthquake Commission (EQC) and private insurers covering NZ$10 billion and NZ$21 billion of the losses, respectively (ICNZ, 2021). As a result of the CES and the 2016 Kaikoura earthquake, EQC’s Natural Disaster Fund was depleted (EQC, 2022). This highlighted the need for improved tools enabling damage and loss analysis for natural hazards.This research project used residential building claims collected by EQC following the CES to develop a rapid seismic loss prediction model for residential buildings in Christchurch. Geographic information systems (GIS) tools, data science techniques, and machine learning (ML) were used for the model development. Before the training of the ML model, the claims data was enriched with additional information from external data sources. The seismic demand, building characteristics, soil conditions, and information about the liquefaction occurrence were added to the claims data. Once merged and pre-processed, the aggregated data was used to train ML models based on the main events in the CES. Emphasis was put on the interpretability and explainability of the model. The ML model delivered valuable insights related to the most important features contributing to losses. Those insights are aligned with engineering knowledge and observations from previous studies, confirming the potential of using ML for disaster loss prediction and management. Care was also put into the retrainability of the model to ensure that any new data from future earthquake events can rapidly be added to the model. 

Optimization methods have been widely applied to the aerodynamic design of gas turbine blades. While applying optimization to high-fidelity computational fluid dynamics (CFD) simulations has proven capable of improving engineering design performance, a challenge has been overcoming the prolonged run-time due to the computationally expensive CFD runs. Reduced-order models and, more recently, machine learning methods have been increasingly used in gas turbine studies to predict performance metrics and operational characteristics, model turbulence, and optimize designs. The application of machine learning methods allows for utilizing existing knowledge and datasets from different sources, such as previous experiments, CFD, low-fidelity simulations, 1D or system-level studies. The present study investigates inserting a machine learning model that utilizes such data into a high-fidelity CFD driven optimization process, and hence effectively reduces the number of required evaluations of the CFD model. Artificial Neural Network (ANN) models were trained on data from over three thousand two-dimensional (2D) CFD analyses of turbine blade cross-sections. The trained ANN models were then used as surrogates in a nested optimization process alongside a full three-dimensional Navier–Stokes CFD simulation. The much lower evaluation cost of the ANN model allows for tens of thousands of design evaluations to guide the search of the best blade profiles to be used in the more expensive, high-fidelity CFD runs, improving the progress of the optimization while reducing the required computation time. It is estimated that the current workflow achieves a five-fold reduction in computational time in comparison to an optimization process that is based on three-dimensional (3D) CFD simulations alone. The methodology is demonstrated on the NASA/General Electric Energy Efficient Engine (E3) high pressure turbine blade and found Pareto front designs with improved blade efficiency and power over the baseline. Quantitative analysis of the optimization data reveals that some design parameters in the present study are more influential than others, such as the lean angle and tip scaling factor. Examining the optimized designs also provides insight into the physics, showing that the optimized designs have a lower amount of pressure drop near the trailing edge, but have an earlier onset of pressure drop on the suction side surface when compared to the baseline design, contributing to the observed improvements in efficiency and power.

<p><strong>Abstract: </strong></p> <p><strong> </strong>The increasing development of GNSS techniques enables solving geodetic problems on both local and global scales. Parallelly, complex algorithms have been proposed and can also be solved well by Machine Learning (ML). However, ML techniques are sometimes not sensitive enough to gain results with a high probability for some cases, like sparse data or non-stationary GNSS time series. In this study, we use a combination of Human and Machine learning (H&M) to improve the classification performance of continuous GNSS stations. First, 427 permanent GNSS stations are obtained from the EUREF network to train ML models. The models are then applied to classify the quality of 939 continuous observation stations from two projects, EIFEL and IPOC, carried out by the German Research Centre for Geosciences (GFZ), Potsdam, Germany. Next, we independently validate the ML models' reality through a MATLAB program, GNSS metadata, and seismic data. Finally, all data of these 1366 stations are used to re-train the ML models. The main criteria to classify are the number of outliers, jumps in GNSS time series, root mean square errors, observation time-spans, and stability of the crustal motion velocity fields. Applying the approach of the H&M combination improves the performance of the ML models up to 92% while using only ML methods remains ~68%. These ML-based classification models can be applied to estimate the quality of permanent GNSS stations and to manage big databases. The result is the basis for selecting suitable control and monitoring stations in crustal deformation monitoring as well as in civil and industrial applications.</p> <p><strong>Keywords: </strong></p> <p>GNSS station classification, Machine learning, Human & Machine learning combination.</p>

This study examines how urban morphology, road configurations, and meteorological factors shape fine particulate matter (PM2.5) dispersion in high-density urban environments, addressing a gap in block-level air quality analysis. While previous research has focused on individual street canyons, this study highlights the broader influence of building arrangement and height. Integrating computational fluid dynamics (CFD) simulations with interpretable machine learning (ML) models quantifies PM2.5 concentrations across various urban configurations. CFD simulations were conducted on different road layouts, block height configurations, and aspect ratio (AR) levels. The resulting dataset trained five ML models with Extreme Gradient Boosting (XGBoost), achieving the highest accuracy (91–95%). Findings show that road-specific mitigation strategies must be tailored. In loop-road networks, centrally elevated buildings enhance ventilation, while in grid-road networks, taller perimeter buildings shield inner blocks from arterial emissions. Additionally, this study identifies a threshold effect of AR, where values exceeding 2.5 improve PM2.5 dispersion under high wind velocity. This underscores the need for wind-sensitive designs, including optimized wind corridors and building alignments, particularly in high-density areas. The integration of ML with CFD enhances predictive accuracy, supporting data-driven urban planning strategies to optimize road layouts, zoning regulations, and aerodynamic interventions for improved air quality.

Predicting combined tidal and pluvial flood inundation using a machine learning surrogate model

Development of advanced hybrid computational model for description of molecular separation in liquid phase via polymeric membranes

The expansion of electronic payments in the retail sector has been accompanied by an increase in advanced payment frauds. Traditional rule based legacy static fraud detection methods, in most cases, proved inadequate to address dynamically changing and constantly evolving fraudster practices. This paper discusses an efficient real time fraud detection system through a combination of Machine Learning (ML) algorithms and real time data stream processing technology. The study is helpful in the sense that it has a constructed synthetic transaction data set which was specially designed and built to be utilized for the very specific purpose of simulating real retail payment scenarios. The data have 489 samples with columns of transaction amount, merchant category, time of day, and frequency of transactions. We test and use a subset of the ML algorithms, like Random Forest and Gradient Boosting, to identify fraud effectively with very low latency. The solution takes consumption transaction as an Apache Kafka stream simulated, real time feature creation, and scoring of transactions using trained ML models. It depicts how ensemble methods, of which Gradient Boosting is a fair example, are more precise in recall and accuracy and minimize false negatives and false positives to a significant degree. This research acknowledges the prospect of a streaming paradigm and sophisticated ML in developing adaptive and real time fraud detection systems of high value addition to the security framework of modern retail payment systems.

A surrogate model assisted with a subdomain model for permanent-magnet machine

While designing the power requirements of a ship, the most important factor to be considered is the ship resistance, or the sea drag forces acting on the ship. It is important to have an estimate of the ship resistance while designing the propulsion system since the power required to overcome the sea drag forces contribute to ‘losses’ in the propulsion system. There are three main methods to calculate ship resistance: Statistical methods like the Holtrop-Mennen (HM) method, numerical analysis or CFD (Computational Fluid Dynamics) simulations, and model testing, i.e. scaled model tests in towing tanks. At the start of the design stage, when only basic ship parameters are available, only statistical models like the HM method can be used. Numerical analysis/ CFD simulations and model tests can be performed only when the complete 3D design of the ship is completed. The present paper aims at predicting the calm water ship resistance using CFD simulations, using the Flow-3D software package. A case study of a roll-on/roll-off passenger (RoPax) ferry was investigated. Ship resistance was calculated at various ship speeds. Since the mesh affects the results in any CFD simulation, multiple meshes were used to check the mesh sensitivity. The results from the simulations were compared with the estimate from the HM method. The results from simulations agreed well with the HM method for low ship speeds. The difference in the results was considerably high compared to the HM method for higher ship speeds. The capability of Flow-3D to perform ship resistance analysis was demonstrated.

Aerodynamic optimization of aircraft wings using machine learning