Hybrid Modeling Approach Research Articles

Monte Carlo Simulations in Nanomedicine: Advancing Cancer Imaging and Therapy

Monte Carlo (MC) simulations have become important in advancing nanoparticle (NP)-based applications for cancer imaging and therapy. This review explores the critical role of MC simulations in modeling complex biological interactions, optimizing NP designs, and enhancing the precision of therapeutic and diagnostic strategies. Key findings highlight the ability of MC simulations to predict NP bio-distribution, radiation dosimetry, and treatment efficacy, providing a robust framework for addressing the stochastic nature of biological systems. Despite their contributions, MC simulations face challenges such as modeling biological complexity, computational demands, and the scarcity of reliable nanoscale data. However, emerging technologies, including hybrid modeling approaches, high-performance computing, and quantum simulation, are poised to overcome these limitations. Furthermore, novel advancements such as FLASH radiotherapy, multifunctional NPs, and patient-specific data integration are expanding the capabilities and clinical relevance of MC simulations. This topical review underscores the transformative potential of MC simulations in bridging fundamental research and clinical translation. By facilitating personalized nanomedicine and streamlining regulatory and clinical trial processes, MC simulations offer a pathway toward more effective, tailored, and accessible cancer treatments. The continued evolution of simulation techniques, driven by interdisciplinary collaboration and technological innovation, ensures that MC simulations will remain at the forefront of nanomedicine’s progress.

Liposomal Drug Delivery: Comparative Kinetics, Efficacy, and Applications in Targeted Therapeutics

During the Second World War, in order to reduce infections in soldiers wounds, nurses had to inject the injured with multiple shots of penicillin per day because one single shot of penicillin only lasts a short period of time, but the lack of human resources prevented some of the wounded soldiers from receiving the dose of penicillin that they needed[1]. To reduce the need for human labor in penicillin intake, Romansky discovered that mixing penicillin with lipids would prolong the time in which penicillin has effect. This innovation saved a lot of people from infection at the time. Lipid-based drug carriers have been developed and innovated even more throughout the years.A few years ago, the COVID-19 pandemic has facilitated advancements in vaccination technologies, including the use authorization of mRNA vaccines encapsulated in lipid nanoparticles. Traditional drug delivery methods, such as oral intake, injection, and transdermal applications, usually face challenges like low accuracy, toxicity, and variable effectiveness. However, liposomes, discovered in the 1960s, emerged as a drug carrier that, due to their specific structure, allowed for prolonged and site-specific drug release. Liposomes can encapsulate drugs of different molecular qualities, allowing lipid-based drug carriers to have excellent performance in carrying both hydrophobic and hydrophilic drugs. This paper examines the composition of liposomes, the different factors of the lipid bilayers, and the release kinetics in drug delivery. Using a hybrid modeling approach of first-order kinetics and the Higuchi model, the study simulates drug release profiles. The liposomal formulation of drugs demonstrates the potential of lipid-based delivery systems in enhancing the efficacy while minimizing side effects of treatments.

Combined statistical-biophysical modeling links ion channel genes to physiology of cortical neuron types.

Neural cell types have classically been characterized by their anatomy and electrophysiology. More recently, single-cell transcriptomics has enabled an increasingly fine genetically defined taxonomy of cortical cell types, but the link between the gene expression of individual cell types and their physiological and anatomical properties remains poorly understood. Here, we develop a hybrid modeling approach to bridge this gap. Our approach combines statistical and mechanistic models to predict cells' electrophysiological activity from their gene expression pattern. To this end, we fit biophysical Hodgkin-Huxley-based models for a wide variety of cortical cell types using simulation-based inference, while overcoming the challenge posed by the mismatch between the mathematical model and the data. Using multimodal Patch-seq data, we link the estimated model parameters to gene expression using an interpretable sparse linear regression model. Our approach recovers specific ion channel gene expressions as predictive of biophysical model parameters including ion channel densities, directly implicating their mechanistic role in determining neural firing.

A comparison of physics‐based, data‐driven, and hybrid modeling approaches for rice phenology prediction

A comparison of physics‐based, data‐driven, and hybrid modeling approaches for rice phenology prediction

Automated diagnosis of respiratory diseases from lung ultrasound videos ensuring XAI: an innovative hybrid model approach

Automated diagnosis of respiratory diseases from lung ultrasound videos ensuring XAI: an innovative hybrid model approach

Prediction of manhole-cover skid-resistance performance using decision trees and regression analysis

This study conducts skid-resistance coefficient tests on 3,600 manhole covers and collects data on various influencing factors, such as surface conditions, pattern types, starting zones, turning zones, usage duration, wheel track locations, and surrounding traffic volume. A preliminary classification analysis of the data is performed using decision trees to identify key factors affecting manhole-cover skid resistance. Subsequently, a multivariate nonlinear regression model is applied to examine the impact of these factors on the target variables. By integrating decision trees and nonlinear regression in a hybrid modeling approach, the study aims to reveal complex patterns in the data and generate reliable predictive results. The decision-tree analysis using non-continuous variables reveals that manhole covers located at turns and starting zones, and those with worn surfaces are more likely to fail to meet safety standards for skid resistance. The multivariate nonlinear regression model, which compares the predicted values against the actual British Pendulum Number (BPN) test results, achieves an accuracy of 82.9%.

Hybrid model approach for hilly sub-watershed prioritization using morphometric parameters: a case study from Bakkhali river watershed in Cox’s Bazar, Bangladesh

ABSTRACT This study investigates the morphometry of the Bakkhali watershed (BW) in the hilly districts of Cox’s Bazar and Bandarban, Bangladesh, to analyze its hydrological characteristics. Morphometric parameters were utilized to prioritize sub-watersheds (SWs) through a hybrid approach combining principal component analysis (PCA) and the weighted-sum approach (WSA). Using ArcGIS Pro 2.7.0, streams, the watershed, and SWs were delineated from a 30-m resolution COP30 DEM. Preliminary priority ranks (PPR) were determined based on direct and inverse relationships of morphometric parameters to soil erodibility. Weighted compound factors (CF) were calculated from PCA results for final prioritization. The BW, a fifth-order watershed with a drainage area of 571.52 km², shows a consistent decrease in the number of streams with increasing stream order, indicating an erosional landform. The mean bifurcation ratio of 4.09 suggests a higher tendency for soil erosion. Shape factors indicate an elongated watershed with less pronounced peak flow characteristics. The analysis identified SW2 and SW3 as high-erosion zones, SW4 and SW9 as medium-erosion zones, and SW1 as a low-erosion zone. The study demonstrates the efficacy of combining geospatial and statistical tools for SW prioritization.

Reliability analysis of phased mission systems based on generalized stochastic Petri nets under mixed uncertainty

Phased mission systems (PMS) are widely applied across diverse industrial systems. Technological advancements in these systems have markedly improved their performance. However, fault characteristics such as uncertainty and common cause failure (CCF) frequently emerge during failures, which significantly raises new challenges in reliability analysis. A novel system reliability analysis framework is proposed to address the mixed uncertainty and CCF in PMS. Specifically, a hybrid modeling approach that combines dynamic fault trees and generalized stochastic Petri nets (GSPN) is employed to accurately model PMS containing CCF. This approach integrates predicates and assertions from GSPN to define four reusable sub-Petri net models at different hierarchical levels, including module, phase, CCF, and overall mission levels. Furthermore, interval theory is incorporated into the framework to manage imprecise component lifetime data. For uncertainty quantification, a synergistic approach combining genetic algorithm and Monte Carlo simulation is utilized. Additionally, a simplified approach is introduced to reduce the complexity of computing the reliability boundary values of PMS. Finally, the proposed method is applied to conduct reliability analysis of a phased altitude and orbit control system. The analysis results validate its effectiveness and applicability in addressing the mixed uncertainty and CCF of PMS.

Integration of Neural Networks and First-Principles Model for Optimizing l-Lactide Branched Polymerization.

Addressing the growing demand for sustainable materials, this research paves the way for the efficient consumption and sustainable production of branched polylactide (PLA). A novel hybrid modeling approach combines first-principles (FP) model with artificial neural network (ANN) for ring-opening polymerization (ROP). The hybrid ANN, trained with FP model data, demonstrated optimal performance with a hidden layer of 20 neurons, achieving a root mean square error (RMSE) of 0.004 and a regression coefficient (R2) of 0.99. The hybrid model accurately predicted key polymer properties, including average molecular weights (Mn and Mw), polydispersity index (PDI), degree of branching (DB), monomer conversion, and polymerization time. Validation was performed on various branched PLA compositions (PLLH80, PLLH94, and PLLH97). Multiobjective optimization (MOO) using NSGA-II showed strong agreement between FP model and hybrid ANN across six case studies, highlighting their effectiveness in predicting polymerization outcomes.

Hybrid Model Approaches for Accurate Time Series Predicting of COVID-19 Cases

This study compares the performance of ARIMA, LSTM, and hybrid models in predicting COVID-19 cases and analyzing forecast errors. Utilizing real-world data, the models were assessed for accuracy and trend prediction over numerous months. Heatmaps of prediction errors revealed that the hybrid model reliably outperformed ARIMA and LSTM by accomplishing lower error extents. The findings highlight the preferences of combining statistical and deep learning approaches for time series predicting. The results contribute to progressing predicting accuracy, which is basic for pandemic response arranging and public health administration.

Physics-based and data-driven modelling and simulation of Solid Oxide Fuel Cells

This paper presents a comprehensive approach to multiscale and multiphysics modelling of Solid Oxide Fuel Cells (SOFCs) by combining physics-based simulations with data-driven techniques. The modelling approach is tailored to specific end-use scenarios, ensuring that parameter selection aligns with operational requirements for accurate and efficient SOFC design. The study begins by constructing Representative Volume Elements (RVEs) from reconstructed microstructures, applying first-order homogenisation to upscale material properties, which are then incorporated into a macroscopic SOFC model. A major contribution is the structured model definition based on physical process entities, using a graphical representation of model topology. This approach simplifies complex system interactions by representing capacities (such as reservoirs, distributed systems, and interfaces) and transport processes (e.g., diffusion, convection, thermal diffusion), thereby enhancing clarity and improving the accuracy of SOFC performance simulations.A machine learning framework complements the physics-based modelling by training Artificial Neural Networks (ANNs) on simulation-generated datasets, delivering fast and reliable performance predictions. The study compares two optimisation techniques — Levenberg–Marquardt (LM) and Adam optimiser — demonstrating that LM is more effective for sparse datasets and smaller networks, whereas Adam performs better with large datasets and higher learning capacities. This hybrid modelling approach not only boosts predictive accuracy for SOFC performance but also lowers computational costs. By integrating physics-based simulations, machine learning, and a knowledge-driven simulation platform, this work advances SOFC design and optimisation, contributing to more efficient and cost-effective clean energy solutions.Additionally, the paper introduces a knowledge-driven simulation platform to enhance data management and integrate multiscale, multiphysics models. The platform leverages structured data models and ontological mappings to improve semantic interoperability, allowing for dataset reuse and validation across different simulation stages. This ensures a robust, reusable, and well-organised workflow, facilitating large-scale simulations and improving overall modelling accuracy.

Performance Evaluation of Battery Swapping Stations for EVs: A Multi-Method Simulation Approach

This study presents an optimisation framework for operating a battery swapping station (BSS) to enhance efficiency and sustainability in electric vehicle (EV) infrastructure. A hybrid modelling approach combines agent-based discrete event simulation and linear programming to model the dynamic behaviour of batteries and operational processes within the BSS. The model considers factors such as charging speed, battery degradation, grid power constraints, customer behaviour, and range anxiety. The agent-based model simulates the interaction between vehicles, batteries, and the station, capturing the stochastic nature of EVs’ arrivals and battery demand with the discrete event simulation. The linear programming component optimises battery state transitions to minimise degradation and ensure that the demand is met while respecting the power limits of the grid. Different battery types are considered based on vehicle category, each with specific capacity and usage patterns, reflecting real-world market conditions. The results demonstrate that the proposed optimisation framework can effectively manage the complex operational needs of a BSS. The proposed framework effectively balances service quality with resource efficiency by employing a strategic mix of charging modes and inventory management, reducing operational and degradation costs. This approach supports a more sustainable EV infrastructure, highlighting BSS as a viable solution to enhance the efficiency and sustainability of EV operations. Furthermore, the analysis highlights the critical role of power limits in determining charging strategies and their impact on operational efficiency. The findings suggest that with optimised operations, BSS can play a critical role in accelerating the adoption of EVs by offering a faster, more reliable, and sustainable alternative.

Hybrid modelling framework for ozonation and biological activated carbon in tertiary wastewater treatment.

Despite water being a significant output of water and resource recovery facilities (WRRFs), tertiary wastewater treatment processes are often underrepresented in integrated WRRF models. This study critically reviews the approaches used in comprehensive models for ozone (O3) and biological activated carbon (BAC) operation units for wastewater tertiary treatment systems. The current models are characterised by limitations in the mechanisms that describe O3 disinfection and disinfection by-product formation, and BAC adsorption in multi-component solutes. Drawing from the insights from the current O3, BAC, and WRRF modelling approaches, we propose an integrated O3-BAC model suitable for simulating dissolved organic carbon (DOC) and micropollutants removal in the O3-BAC systems. We recommend a hybrid modelling approach in which data-driven models can be integrated to compensate for structural limitations in mechanistic models. The model is developed within the activated sludge model (ASM) framework for flexibility in coupling with other WRRF models and hence facilitates developing system-wide WRRF models for wastewater reclamation and reuse systems.

A hybrid approach to enhance streamflow simulation in data-constrained Himalayan basins: combining the Glacio-hydrological Degree-day Model and recurrent neural networks

Abstract. The Glacio-hydrological Degree-day Model (GDM) is a distributed model, but it is prone to uncertainties due to its conceptual nature, parameter estimation, and limited data in the Himalayan basins. To enhance accuracy without sacrificing interpretability, we propose a hybrid model approach that combines GDM with recurrent neural networks (RNNs), hereafter referred to as GDM–RNN. Three RNN types – a simple RNN model, a gated recurrent unit (GRU) model, and a long short-term memory (LSTM) model – are integrated with GDM. Rather than directly predicting streamflow, RNNs forecast GDM's residual errors. We assessed performance across different data availability scenarios, with promising results. Under limited-data conditions (1 year of data), GDM–RNN models (GDM–simple RNN, GDM–LSTM, and GDM–GRU) outperformed standalone GDM and machine learning models. Compared with GDM's respective Nash–Sutcliffe efficiency (NSE), R2, and percent bias (PBIAS) values of 0.80, 0.63, and −4.78, the corresponding values for the GDM–simple RNN were 0.85, 0.82, and −6.21; for GDM–LSTM, they were 0.86, 0.79, and −6.37; and for GDM–GRU, they were 0.85, 0.8, and −5.64. Machine learning models yielded similar results, with the simple RNN at 0.81, 0.7, and −16.6; LSTM at 0.79, 0.65, and −21.42; and GRU at 0.82, 0.75, and −12.29, respectively. Our study highlights the potential of machine learning with respect to enhancing streamflow predictions in data-scarce Himalayan basins while preserving physical streamflow mechanisms.

Quantifying uncertainty in neural network predictions of forced vibrations

AbstractThe prediction of forced vibrations in nonlinear systems is a common task in science and engineering, which can be tackled using various methodologies. A classical approach is based on solving differential (algebraic) equations derived from physical laws ('first principles'). Alternatively, Artificial Neural Networks (ANNs) may be applied, which rely on learning the dynamics of a system from given data. However, a fundamental limitation of ANNs is their lack of transparency, making it difficult to understand and trust the model's predictions. In this contribution, we follow a hybrid modelling approach combining a data‐based prediction using a stabilised Autoregressive Neural Network (s‐ARNN) with a priori knowledge from first principles. Moreover, aleatoric and epistemic uncertainty is quantified by a combination of mean‐variance estimation (MVE) and deep ensembles. Validating this approach for a classical Duffing oscillator suggests that the MVE ensemble is the most accurate and reliable method for prediction accuracy and uncertainty quantification. These findings underscore the significance of understanding uncertainties in deep ANNs and the potential of our method in improving the reliability of predictive nonlinear system modelling. We also demonstrate that including partially known dynamics can further increase accuracy, highlighting the importance of combining ANNs and physical laws.

Effect of temperature on transport index of fish oil-based drilling mud in high pressure high temperature well: a hybrid model approach

Diesel Oil-based drilling mud used in the oil and gas industry causes severe environmental and public health issues due to its high toxicity, especially in high-pressure, high-temperature (HPHT) wells. Therefore, easily biodegradable synthetic oil-based mud with high drilling performance is essential. Fish oil is a bio-oil known for its non-toxicity, high lubricity, thermal stability, and biodegradability. Effective hole cleaning is crucial for drilling performance and is ensured by the rheological properties of drilling mud. While rheological parameter prediction can be performed using an artificial neural network (ANN) based model, such models often fail to provide accurate predictions for unseen data. In contrast, empirical models are more robust and facilitate generalization. This study aims at assessment of the suitability of invert emulsion fish oil-based drilling mud (IEFOBDM) in HPHT wells through evaluation of hole cleaning performance (HCP) using a hybrid approach that combines an ANN with nonlinear regression (NLR) for temperatures ranging from 40 °C to 80 °C.Firstly, an ANN model was developed considering mud weight, temperature, and shear rate. Secondly, the NLR model was used in the prediction of rheological parameters, namely, Yield point (YP) and Plastic viscosity (PV), based on the predicted shear stress from the ANN model. Finally, the performance metrics of the ANN-NLR rheological model were evaluated using the root mean square error (RMSE) and correlation coefficient (R2) and comparison made with the Single ANN rheological model. The results showed the outperformance of ANN-NLR model over the ANN model for rheological parameter prediction, with R2 values of (0.99) for YP and (1) for PV. The predicted PV and YP values were then used for evaluation of transport index (TI) for HCP analysis. The effect of temperature on TI analysis showed this with increase in temperature, TI also increased, indicating the proposed mud providing good HCP under HPHT conditions.

Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networks

Improving the forecasting accuracy of agricultural commodity prices is critical for many stakeholders namely, farmers, traders, exporters, governments, and all other partners in the price channel, to evade risks and enable appropriate policy interventions. However, the traditional mono-scale smoothing techniques often fail to capture the non-stationary and non-linear features due to their multifarious structure. This study has proposed a CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise)-TDNN (Time Delay Neural Network) model for forecasting non-linear, non-stationary agricultural price series. This study has evaluated its suitability in comparison with the other three major EMD (Empirical Mode Decomposition) variants (EMD, Ensemble EMD and Complementary Ensemble EMD) and the benchmark (Autoregressive Integrated Moving Average, Non-linear Support Vector Regression, Gradient Boosting Machine, Random Forest and TDNN) models using monthly wholesale prices of major oilseed crops in India. Outcomes from this investigation reflect that the CEEMDAN-TDNN hybrid models have outperformed all other forecasting models on the basis of evaluation metrics under consideration. For the proposed model, an average improvement of RMSE (Root Mean Square Error), Relative RMSE and MAPE (Mean Absolute Percentage Error) values has been observed to be 20.04%, 19.94% and 27.80%, respectively over the other EMD variant-based counterparts and 57.66%, 48.37% and 62.37%, respectively over the other benchmark stochastic and machine learning models. The CEEMD-TDNN and CEEMDAN-TDNN models have demonstrated superior performance in predicting the directional changes of monthly price series compared to other models. Additionally, the accuracy of forecasts generated by all models has been assessed using the Diebold-Mariano test, the Friedman test, and the Taylor diagram. The results confirm that the proposed hybrid model has outperformed the alternative models, providing a distinct advantage.

Enhancing runoff predictions in data-sparse regions through hybrid deep learning and hydrologic modeling

Amidst growing concerns over climate-induced extreme weather events, precise flood forecasting becomes imperative, especially in regions like the Chaersen Basin where data scarcity compounds the challenge. Traditional hydrologic models, while reliable, often fall short in areas with insufficient observational data. This study introduces a hybrid modeling approach that combines the deep learning capabilities of the Informer model with the robust hydrological simulation by the WRF-Hydro model to enhance runoff predictions in such data-sparse regions. Trained initially on the diverse and extensive CAMELS dataset in the United States, the Informer model successfully applied its learned insights to predict runoff in the Chaersen Basin, leveraging transfer learning to bridge data gaps. Concurrently, the WRF-Hydro model, when integrated with The Global Forecast System (GFS) data, provided a basis for comparison and further refinement of flood prediction accuracy. The integration of these models resulted in a significant improvement in prediction precision. The synergy between the Informer’s advanced pattern recognition and the physical modeling strength of the WRF-Hydro significantly enhanced the prediction accuracy. The final predictions for the years 2015 and 2016 demonstrated notable increases in the Nash–Sutcliffe Efficiency (NSE) and the Index of Agreement (IOA) metrics, confirming the effectiveness of the hybrid model in capturing complex hydrological dynamics during runoff predictions. Specifically, in 2015, the NSE improved from 0.5 with WRF-Hydro and 0.63 with the Informer model to 0.66 using the hybrid model, while in 2016, the NSE increased from 0.42 to 0.76. Similarly, the IOA in 2015 rose from 0.83 with WRF-Hydro and 0.84 with the Informer model to 0.87 using the hybrid approach, and in 2016, it increased from 0.78 to 0.92. Further investigation into the respective contributions of the WRF-Hydro and the Informer models revealed that the hybrid model achieved the optimal performance when the contribution of the Informer model was maintained between 60%-80%.

A Hybrid Modelling Approach Coupling Physics-based Simulation and Deep Learning for Battery Electrode Manufacturing Simulations

Lithium-ion battery (LIB) performance is significantly influenced by its manufacturing process. Manufacturing of an optimized electrode can incur high production costs such as high energy consumption, high scrap rates and emissions. This is due to the process that consists of a series of manufacturing steps presenting a complex interrelationship, thus limiting the understanding of performance as a function of manufacturing parameters. While several empirical and computational methods are employed for optimization, they are demanding in terms of resources such as materials or computational effort. By leveraging Deep Learning (DL), we can enhance our understanding of the complex manufacturing processes and accelerate its optimization. We propose a data-driven supervised DL methodology to complement physics-based LIB cathode manufacturing simulations. The trained DL-based predictive model integrates well into the manufacturing simulation framework to forecast cathode slurry microstructures. The DL model demonstrates robust predictive performance for LIB NMC-111 and LiFePO4–based slurries and slurries for a solid-state battery NMC-622/argyrodite composite electrode preparation. While the current work is focused on the cathode slurry process, the proposed methodology has potential for application to drying and calendering steps. This approach will be helpful in streamlining lab-scale electrode manufacturing, and reducing errors, waste and resource consumption.

Process-Informed Neural Networks: A Hybrid Modelling Approach to Improve Predictive Performance and Inference of Neural Networks in Ecology and Beyond.

Despite deep learning being state of the art for data-driven model predictions, its application in ecology is currently subject to two important constraints: (i) deep-learning methods are powerful in data-rich regimes, but in ecology data are typically sparse; and (ii) deep-learning models are black-box methods and inferring the processes they represent are non-trivial to elicit. Process-based (= mechanistic) models are not constrained by data sparsity or unclear processes and are thus important for building up our ecological knowledge and transfer to applications. In this work, we combine process-based models and neural networks into process-informed neural networks (PINNs), which incorporate the process knowledge directly into the neural network structure. In a systematic evaluation of spatial and temporal prediction tasks for C-fluxes in temperate forests, we show the ability of five different types of PINNs (i) to outperform process-based models and neural networks, especially in data-sparse regimes with high-transfer task and (ii) to inform on mis- or undetected processes.