Data-driven reduced-order modeling framework for blunt-body aerodynamic characterization

Green infrastructures are decentralized semi-natural solutions for managing stormwater runoff. To assess their effectiveness in urban drainage, many process-based hydrological models have been developed. However, these models sometimes fail to deliver satisfactory results due to inadequate representations of the involved hydrological processes or due to limited field measurements for model setup. Data-driven modelling simulates directly the connections between the state variables of the system (such as the input variable and the output variable), and thus reduces the need for hydrological process characterization. Yet the usefulness of this modelling approach in green infrastructure related studies has not been fully explored. To demonstrate its effectiveness, two bioretention systems in the U.S. are studied. The designs of these two systems are unique, making them difficult to be modelled directly using the standard process-based models. In one site, the observations are also censored, i.e., only the overflow/no overflow binary outcomes are being monitored, with which the model calibration is inhibited. We showed that using the state-of-the-art data-driven modelling framework (e.g., CARET and MXNET), the occurrence or the outflow discharge rate of the bioretention systems at a given time can be accurately simulated only using the rainfall, evapotranspiration and the inflow time series. We conclude that data-driven modelling can be useful for simulating the hydrologic performance of green infrastructures, especially when the existing process-based models are inadequate in representing the design variabilities or the data for model setup is limited.

Accurate identification of process parameters from in-mold sensing signals is essential for advancing intelligent and adaptive injection molding systems. This study proposes a data-driven inverse modeling framework that infers key process parameters directly from cavity pressure curves. A stage-wise Autoencoder (AE) is employed to perform nonlinear feature extraction by segmenting the pressure curve into filling, packing, and cooling stages, thereby capturing process-dominant dynamics. The encoded latent features are subsequently mapped to injection speed, packing pressure, nozzle temperature, and mold temperature using a multilayer perceptron (MLP). Eighty-one full-factorial parameter combinations were experimentally conducted, generating 810 molding cycles on an industrial injection molding machine. An independent validation dataset was collected from separate production runs to evaluate generalization capability. The proposed AE–MLP framework achieved high predictive accuracy on unseen data, with R² values of 0.9979 for injection speed, 0.9926 for packing pressure, 0.9571 for mold temperature, and 0.9296 for nozzle temperature. The corresponding RMSE values remained below 1.6 across all parameters. Comparative analysis against PCA–MLP and direct MLP models demonstrates that nonlinear manifold representation significantly improves inverse regression robustness, particularly for thermally coupled parameters. Furthermore, the stability of inverse modeling is analyzed from the perspective of parameter identifiability and many-to-one mapping characteristics inherent in injection molding processes. Results indicate that stage-wise nonlinear feature encoding enhances separability in the latent space and mitigates ambiguity in parameter inference. The proposed framework provides a robust and physically interpretable approach for real-time process parameter estimation, contributing to the development of adaptive and self-optimizing manufacturing systems. Infers molding parameters directly from multi-sensor pressure features. AE–MLP framework learns nonlinear relations between pressure and parameters. Parameter recommendation enables adaptive process condition adjustment. 810-cycle full-factorial experiments confirm accuracy and generalization. Supports smart manufacturing through real-time parameter tuning.

STEAM: A scalable data-driven surrogate modeling framework for part-scale scanwise thermal process simulation of laser powder bed fusion

Data-driven intelligent modeling framework for the steam cracking process

In response to the tenets of Industry 4.0, operation optimization in industrial processes has become a significant research topic. However, the uncertainties prevailing in the process pose challenges to production operations, especially the feedstock properties. In this work, the operation optimization study is performed on a distillation unit (DU), a typical plant in the industrial process. To enhance production performance, a modeling and operation optimization strategy based on feedstock property and production features is presented. One of the difficulties is how to uncover features from high-dimensional and imperfect data, where imperfect data refers to product quality data that is unavailable online. In the strategy, we inject the inherent characteristic of the process into the data-driven method to extract the feedstock property in a data-based and knowledge-oriented manner. Further, optimal feature representation and process modeling can be achieved by customizing the network structure. The operation optimization problem is formulated to adjust the top temperature of the distillation column (TTDC) to achieve satisfactory production under varying feedstock properties. Experimental results illustrate that the process model based on feedstock property and production features (PM-FP-PF) can better fit the physical process mechanism even based on incomplete information in industrial data. Industrial experiments have shown the proposed strategy has advanced generalization ability to the different feedstock properties. The proposed operation optimization strategy (OOS) improves the product qualification rate and has broad application prospects in industrial processes with similar features. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Industrial processes suffer from a variety of disturbances that interrupt the smooth operation of the system, such as varying feedstock properties. How to deal with them is the key to improve the product qualification rate. In this work, we propose a data-driven modeling and operation optimization framework to improve product quality under varying feedstock properties. The dynamic variation characteristics of the feedstock properties can be obtained by analyzing the physical properties of the production unit. This is used as a basis for representing and extracting feedstock properties in a data-driven way. Further, a process model based on feedstock property and production features (PM-FP-PF) is built to predict product quality. An operation optimization strategy with production capacity consideration is established. It can determine the optimal operation action required by the current system, mitigating the uncertainty of feedstock property. This operation optimization system has been applied to a distillation unit in the hydrofining process. The application results show that the process model achieves satisfactory estimation accuracy, and the operation optimization strategy has improved production performance.

A Data-driven Causality Modeling Framework: An Empirical Study of Modeling the Effect of Indoor Air Quality Perception on Students' Cognitive Performance

This paper proposes a generic data-driven crowd modeling framework to generate crowd behaviors that can match the video data. The proposed framework uses a dual-layer mechanism to model the crowd behaviors. The bottom layer models the microscopic collision avoidance behaviors, while the top layer models the macroscopic crowd behaviors such as the goal selection patterns and the path navigation patterns. Based on the dual-layer mechanism, an automatic learning method is proposed to learn the model components from video data. To validate its effectiveness, the proposed framework is applied to generate the crowd behaviors in New York Grand Central Terminal. The simulation results demonstrate that the proposed method is able to construct effective model that can generate the desired emergent crowd behaviors and can offer promising prediction performance.

BackgroundThe rising prevalence of multi-drug resistant organisms (MDROs), such as Methicillin-resistant Staphylococcus aureus (MRSA), Vancomycin-resistant Enterococci (VRE), and Carbapenem-resistant Enterobacteriaceae (CRE), is an increasing concern in healthcare settings.Materials and MethodsLeveraging data from electronic healthcare records and a unique MDRO universal screening program, we developed a data-driven modeling framework to predict MRSA, VRE, and CRE colonization upon intensive care unit (ICU) admission, and identified the associated socio-demographic and clinical factors using logistic regression (LR), random forest (RF), and XGBoost algorithms. We performed threshold optimization for converting predicted probabilities into binary predictions and identified the cut-off maximizing the sum of sensitivity and specificity.ResultsFour thousand six hundred seventy ICU admissions (3,958 patients) were examined. MDRO colonization rate was 17.59% (13.03% VRE, 1.45% CRE, and 7.47% MRSA). Our study achieved the following sensitivity and specificity values with the best performing models, respectively: 80% and 66% for VRE with LR, 73% and 77% for CRE with XGBoost, 76% and 59% for MRSA with RF, and 82% and 83% for MDRO (i.e., VRE or CRE or MRSA) with RF. Further, we identified several predictors of MDRO colonization, including long-term care facility stay, current diagnosis of skin/subcutaneous tissue or infectious/parasitic disease, and recent isolation precaution procedures before ICU admission.ConclusionOur data-driven modeling framework can be used as a clinical decision support tool for timely predictions, characterization and identification of high-risk patients, and selective and timely use of infection control measures in ICUs.

This paper presents development of accurate turbulence closures for wake mixing prediction by integrating a machine-learning approach with Reynolds Averaged Navier-Stokes (RANS)-based computational fluid dynamics (CFD). The data-driven modeling framework is based on the gene expression programming (GEP) approach previously shown to generate non-linear RANS models with good accuracy. To further improve the performance and robustness of the data-driven closures, here we exploit that GEP produces tangible models to integrate RANS in the closure development process. Specifically, rather than using as cost function a comparison of the GEP-based closure terms with a frozen high-fidelity dataset, each GEP model is instead automatically implemented into a RANS solver and the subsequent calculation results compared with reference data. By first using a canonical turbine wake with inlet conditions prescribed based on high-fidelity data, we demonstrate that the CFD-driven machine-learning approach produces non-linear turbulence closures that are physically correct, i.e. predict the right downstream wake development and maintain an accurate peak wake loss throughout the domain. We then extend our analysis to full turbine-blade cases and show that the model development is sensitive to the training region due to the presence of deterministic unsteadiness in the near wake region. Models developed including this region have artificially large diffusion coefficients to over-compensate for the vortex shedding steady RANS cannot capture. In contrast, excluding the near wake region in the model development produces the correct physical model behavior, but predictive accuracy in the near-wake remains unsatisfactory. We show that this can be remedied by using the physically consistent models in unsteady RANS, implying that the non-linear closure producing the best predictive accuracy depends on whether it will be deployed in RANS or unsteady RANS calculations. Overall, the models developed with the CFD-assisted machine learning approach were found to be robust and capture the correct physical behavior across different operating conditions.

Abstract. The documentation of architectural heritage requires interdisciplinary collaboration and advanced information management. Historic Building Information Modelling (HBIM) and Geographic Information Systems (GIS) have enhanced cultural heritage documentation, while eXtended Reality (XR) technologies have improved accessibility and interactive engagement. However, challenges persist in data acquisition, modelling, and classification, limiting the practical implementation of comprehensive heritage information systems. This study introduces a data-driven information modelling framework optimized for cultural heritage, enabling the integration of 3D survey data and heterogeneous datasets. The framework supports cost-effective reuse of existing datasets by ensuring interoperability through a Broker Database and a Web Programming Interface (Web API). The system facilitates data structure abstraction, data description, geometric management, and spatial analysis, treating diverse datasets as informative layers. Allowing coregistration/ coordinate conversion of 3D models, point clouds, and spherical images in/to a unified spatial reference system, it enhances data accessibility while reducing modelling efforts. The paper illustrates the structure and features of the proposed system, focusing on its brokering role and modular framework. Two case studies demonstrate the framework’s capability and scalability: the Parma (Italy) Cathedral and the Church of Santa Maria della Steccata in Parma (Italy). The system outputs are presented through a Virtual Reality application in Unity, providing dynamic geometry visualization, data querying, and immersive exploration.

Finite element analysis (FEA) remains the gold standard for simulating piezoelectric microactuators because it resolves coupled electromechanical fields with high fidelity. However, transient FEA becomes prohibitively expensive when thousands of actuators must be simulated. This work presents a data-driven surrogate modeling framework for tileable, PZT-5H microactuators enabling fast, dynamic, and parallel predictions of actuator displacement over multi-step horizons from short displacement history windows, augmented with the corresponding prescribed voltage and traction samples over that same history window. High-fidelity COMSOL simulations are used to generate a dataset aiming to encompass the full operational envelope of our actuator under stochastically sampled and procedurally generated input waveform families. From these families, we construct a supervised learning dataset of time histories, displacement, and applied loads. From this, we train a recurrent sequence-to-sequence neural network that predicts a multi-step open-loop displacement rollout conditioned on the most recent electromechanical history. The resulting model can be leveraged to perform batched inference for millions of actuators on GPU hardware, opening up a wide range of new applications such as reinforcement learning via digital twins, scalable design and simulation for piezoelectric artificial-muscle systems, and accelerated optimization.

This paper presents a data-driven multiple model framework for estimating the intention of a target from observations. Multiple model (MM) state estimation methods have been extensively used for intention estimation by mapping one intention to one dynamic model assuming one-to-one relations. However, intentions are subjective to humans and it is difficult to establish the one-to-one relations explicitly. The proposed framework infers the multiple-to-multiple relations between intentions and models directly from observations that are labeled with intentions. For intention estimation, both the relations and model probabilities of an Interacting Multiple Model (IMM) state estimation approach are integrated into a recursive Bayesian framework. Taking advantage of the inferred multiple-to-multiple relations, the framework incorpo-rates more accurate relations and avoids following the strict one-to-one relations. Numerical and real experiments were performed to investigate the framework through the intention estimation of a maneuvered quadrotor. Results show higher estimation accuracy and superior flexibility in designing mod-els over the conventional approach that assumes one-to-one relations.

A multi-fidelity data-driven constitutive modeling framework via physics encoding and transfer learning: application to geotechnical engineering problems

This study introduces an innovative framework designed to forecast the fluctuating short-term generation of photovoltaic (PV) energy in isolated microgrids. The framework relies entirely on solar irradiance data obtained from weather stations located far from the target microgrid. It implements a sophisticated decomposition approach to effectively extract an enriched collection of features from the dataset. Subsequently, a machine learning-based clustering method further enhances the forecasting process by accurately separating the relevant data points. The approach utilizes an advanced two-stage Hybrid Data Linked Model (HDLM) architecture, integrating a Layered Recurrent Neural Framework (LRNF) for prediction and a pattern identification network unit for pattern extraction. This paper demonstrates significant improvements in both the accuracy and effectiveness of estimating PV generation, achieving a mean absolute error of 1.02, a root mean square error of 2.176, and an R-squared score of 0.991. Additionally, the method reduces computing time by 15% after finalizing the input features. A comparative analysis evaluates the superior forecasting capabilities of the HDLM in remote microgrids by benchmarking it against other advanced hybrid deep learning models. The findings highlight the HDLM’s potential to greatly enhance and revolutionize the management and operation of renewable energy systems in remote microgrids.

Accurate forecasting of demand load is momentous for the efficient economic dispatch of generating units with enormous economic and reliability implications. However, with the high integration levels of grid-tie generations, the precariousness in demand load forecasts is unreliable. This paper proposes a data-driven stochastic ensemble model framework for short-term and long-term demand load forecasts. Our proposed framework reduces uncertainties in the load forecast by fusing homogenous models that capture the dynamics in load state characteristics and exploit model diversities for accurate prediction. The ensemble model caters for factors such as meteorological and exogenous variables that affect load prediction accuracy with adaptable, scalable algorithms that consider weather conditions, load features, and state characteristics of the load. We defined a heuristic trained combiner model and an error correction model to estimate the contributions and compensate for forecast errors of each prediction model, respectively. Acquired data from the Korean Electric Power Company (KEPCO), and building data from the Korea Research Institute, together with testbed datasets, were used to evaluate the developed framework. The results obtained prove the efficacy of the proposed model for demand load forecasting.