Hybrid Modeling Approach Research Articles

An Efficient Neuroimaging in Parkinson’s Disease Detection with A Hybrid Model Approach

An Efficient Neuroimaging in Parkinson’s Disease Detection with A Hybrid Model Approach

Enhancing groundwater quality assessment in coastal area: A hybrid modeling approach

Monitoring of groundwater (GW) resources in coastal areas is vital for human needs, agriculture, ecosystems, securing water supply, biodiversity, and environmental sustainability. Although the utilization of water quality index (WQI) models has proven effective in monitoring GW resources, it has faced substantial criticism due to its inconsistent outcomes, prompting the need for more reliable assessment methods. Therefore, this study addressed this concern by employing the data-driven root mean squared (RMS) models to evaluate groundwater quality (GWQ) in the coastal Bhola district near the Bay of Bengal, Bangladesh. To enhance the reliability of the RMS-WQI model, the research incorporated the extreme gradient boosting (XGBoost) machine learning (ML) algorithm. For the assessment of GWQ, the study utilized eleven crucial indicators, including turbidity (TURB), electric conductivity (EC), pH, total dissolved solids (TDS), nitrate (NO3−), ammonium (NH4+), sodium (Na), potassium (K), magnesium (Mg), calcium (Ca), and iron (Fe). In terms of the GW indicators, concentration of K, Ca and Mg exceeded the guideline limit in the collected GW samples. The computed RMS-WQI scores ranged from 54.3 to 72.1, with an average of 65.2, categorizing all sampling sites' GWQ as “fair.” In terms of model reliability, XGBoost demonstrated exceptional sensitivity (R2 = 0.97) in predicting GWQ accurately. Furthermore, the RMS-WQI model exhibited minimal uncertainty (<1 %) in predicting WQI scores. These findings implied the efficacy of the RMS-WQI model in accurately assessing GWQ in coastal areas, that would ultimately assist regional environmental managers and strategic planners for effective monitoring and sustainable management of coastal GW resources.

Prediction of the river water environment carrying capacity using LSTM networks

ABSTRACT River basins receive wastewater from socio-economic activities. In such a context, a comprehensive assessment and forecast of load-bearing capacity needs to be developed. This capacity depends on many complex factors, such as hydrology, hydraulics, and environment, leading to applying a modelling approach. This study aims to propose a hybrid modelling approach to evaluate and predict the river water environmental capacity (RWEC) in a basin. Big data technology with Python is applied to process modelling results and RWEC forecasts. The long short-term memory (LSTM) model predicts RWEC on each reach of the river channel network. The {RWECP, i, P = Nitrate, BOD, Phosphate, i = hourly} data set and related factors form a time series of data used for the LSTM forecasting model. Forecast results are evaluated through the root mean square error (RMSE) and mean absolute error (MAE). The results show that the average level over all 24 reaches for 7 forecast days: RMSENitrate = 22.16 (kg/day), RMSEBOD = 38.92 (kg/day), and RMSEPhosphate = 0.79 (kg/day). This is an acceptable result for a complex system and 7-day forecast. The results of the study help significantly with pollution control.

Investigating older driver crashes on high-speed roadway segments: a hybrid approach with extreme gradient boosting and random parameter model

Older drivers are often more susceptible to crashes due to age-related physical and cognitive limitations, particularly in complex driving environments. Considering the limited research in this area, this study focuses on investigating crashes involving older drivers on high-speed roadways (≥ 45 mph). The analysis is based on data collected from Louisiana State, encompassing 18,300 older driver-involved crashes (2017-2021). For analysis, a two-step hybrid modelling approach is employed: a) Extreme Gradient Boosting (XGBoost) is used to classify top variable features and b) Correlated Random Parameter Ordered Probit with Heterogeneity in Means (CRPOP-HM) is used to predict the likelihood of crash injury severity. . Some of the critical factors increasing the likelihood of fatal-severe or injury crashes involving older drivers on high-speed segments include the manner of collision (rear-end, right-angle, single-vehicle), primary contributing factor (violation, pedestrian action), presence of passenger (s), location type (open country, residential, business with mixed residential), and weekend.

Combining descriptive and predictive modeling to systematically design depth filtration-based harvest processes for biologics.

Advances in upstream production of biologics-particularly intensified fed-batch processes beyond 10% cell solids-have severely strained harvest operations, especially depth filtration. Bioreactors containing high amounts of cell debris (more than 40% particles <10 µm in diameter) are increasingly common and drive the need for more robust depth filtration processes, while accelerated timelines emphasize the need for predictive tools to accelerate development. Both needs are constrained by the current limited mechanistic understanding of the harvest filter-feedstream system. Historically, process development relied on screening scale-down depth filter devices and conditions to define throughput before fouling, indicated by increasing differential pressure and/or particle breakthrough (measured via turbidity). This approach is straightforward, but resource-intensive, and its results are inherently limited by the variability of the feedstream. Semi-empirical models have been developed from first principles to describe various mechanisms of filter fouling, that is, pore constriction, pore blocking, and/or surface deposit. Fitting these models to experimental data can assist in identifying the dominant fouling mechanism. Still, this approach sees limited application to guide process development, as it is descriptive, not predictive. To address this gap, we developed a hybrid modeling approach. Leveraging historical bench scale filtration process data, we built a partial least squares regression model to predict particle breakthrough from filter and feedstream attributes, and leveraged the model to demonstrate prediction of filter performance a priori. The fouling models are used to interpret and provide physical meaning to these computational models. This hybrid approach-combining the mechanistic insights of fouling models and the predictive capability of computational models-was used to establish a robust platform strategy for depth filtration of Chinese hamster ovary cell cultures. As new data continues to teach the computational models, in silico tools will become an essential part of harvest process development by enabling prospective experimental design, reducing total experimental load, and accelerating development under strict timelines.

Prioritization of sub-watershed in Eastern Jeddah using PCA-WSA hybrid modeling approach

Prioritization of sub-watershed in Eastern Jeddah using PCA-WSA hybrid modeling approach

Multiscale estimation of the cooling effect of urban greenspace in subtropical and tropical cities

Urban greenspace has been widely recognized for its beneficial role in mitigating the urban heat island (UHI) effect and enhancing human thermal comfort. However, understanding on the thermal effects of greenspace still remains limited, particularly in the areas of regional differences, scale issues, and modeling approaches. This study employs a multiscale approach to evaluate the cooling effect of greenspace in Hong Kong and Singapore by combining remote sensing techniques at the territory level, a hybrid modeling approach at the urban district level, and field measurements at the micro level. Results demonstrate that the approach generally performed well in evaluating the relationship between cooling effect and various explanatory variables. At the city scale, the average reduction in LST by greenspace (△LSTG−UF) was found to be 3.08 ℃ in Hong Kong and 2.84 ℃ in Singapore, respectively. However, the cooling effect of greenspace is much reduced at the urban district level. Of the evaluated urban districts, greenspace was found to have a LST reduction effect ranging from 0.27 to 1.56 ℃ in Hong Kong and from −0.02–2.69 ℃ in Singapore, respectively. At the micro level, the study reveals that building height and greenspace volume have the most significant influence on ambient temperature variations during the hottest time of the summer season. These findings not only highlight the importance of considering scale and time variations when evaluating the thermal effects of greenspace but also help identify effective greenspace deployment strategies to combat excessive urban heat.

Simmering tensions on the Russia–Ukraine border and natural gas futures prices: identifying the impact using new hybrid GARCH

Focusing on the Russia–Ukraine war, this paper investigates natural gas futures volatilities. Applying several hybrid GARCH and EGARCH models, which innovatively incorporate both fat-tailed distribution errors and structural breaks, we derive the following new evidence. First, our hybrid modeling approach is effective in timely capturing the natural gas futures volatility spike when tensions simmered on the Russia–Ukraine border. Second, the hybrid modeling approach is effective for not only GARCH modeling but also EGARCH modeling. Third, the volatility estimates from our hybrid models have predictive power for the volatilities of nonhybrid models. Fourth, the volatility estimates from the nonhybrid models lag behind the volatilities of our hybrid models.

Clustering techniques performance comparison for predicting the battery state of charge: A hybrid model approach

Abstract Batteries are a fundamental storage component due to its various applications in mobility, renewable energies and consumer electronics among others. Regardless of the battery typology, one key variable from a user’s perspective is the remaining energy in the battery. It is usually presented as the percentage of remaining energy compared to the total energy that can be stored and is labeled State Of Charge (SOC). This work addresses the development of a hybrid model based on a Lithium Iron Phosphate (LiFePO4) power cell, due to its broad implementation. The proposed model calculates the SOC, by means of voltage and electric current as inputs and the latter as the output. Therefore, four models based on k-Means, Agglomerative Clustering, Gaussian Mixture and Spectral Clustering techniques have been tested in order to obtain an optimal solution.

Enhancing physically-based hydrological modeling with an ensemble of machine-learning reservoir operation modules under heavy human regulation using easily accessible data

Dams and reservoirs have significantly altered river flow dynamics worldwide. Accurately representing reservoir operations in hydrological models is crucial yet challenging. Detailed reservoir operation data is often inaccessible, leading to relying on simplified reservoir operation modules in most hydrological models. To improve the capability of hydrological models to capture flow variability influenced by reservoirs, this study proposes a hybrid hydrological modeling framework, which combines a process-based hydrological model with a machine-learning-based reservoir operation module designed to simulate runoff under reservoir operations. The reservoir operation module employs an ensemble of three machine learning models: random forest, support vector machine, and AutoGluon. These models predict reservoir outflows using precipitation and temperature data as inputs. The Soil and Water Assessment Tool (SWAT) then integrates these outflow predictions to simulate runoff. To evaluate the performance of this hybrid approach, the Xijiang Basin within the Pearl River Basin, China, is used as a case study. The results highlight the superiority of the SWAT model coupled with machine learning-based reservoir operation models compared to alternative modeling approaches. This hybrid model effectively captures peak flows and dry period runoff. The Nash-Sutcliffe Efficiency (NSE) in daily runoff simulations shows substantial improvement, ranging from 0.141 to 0.780, with corresponding enhancements in the coefficient of determination (R2) by 0.098–0.397 when compared to the original reservoir operation modules in SWAT. In comparison to parameterization techniques lacking a dedicated reservoir module, NSE enhancements range from 0.068 to 0.537, and R2 improvements range from 0.027 to 0.139. The proposed hybrid modeling approach effectively characterizes the impact of reservoir operations on river flow dynamics, leading to enhanced accuracy in runoff simulation. These findings offer valuable insights for hydrological forecasting and water resources management in regions influenced by reservoir operations.

Reliable calibration and validation of phenomenological and hybrid models of high-cell-density fed-batch cultures subject to metabolic overflow

Fed-batch cultures are the preferred operation mode for industrial bioprocesses requiring high cellular densities. Avoids accumulation of major fermentation by-products due to metabolic overflow, increasing process productivity. Reproducible operation at high cell densities is challenging (>100 gDCW/L), which has precluded rigorous model evaluation. Here, we evaluated three phenomenological models and proposed a novel hybrid model including a neural network. For this task, we generated highly reproducible fed-batch datasets of a recombinant yeast growing under oxidative, oxygen-limited, and respiro-fermentative metabolic regimes. The models were reliably calibrated using a systematic workflow based on pre-and post-regression diagnostics. Compared to the best-performing phenomenological model, the hybrid model substantially improved performance by 3.6- and 1.7-fold in the training and test data, respectively. This study illustrates how hybrid modeling approaches can advance our description of complex bioprocesses that could support more efficient operation strategies.

Hybrid modeling of karstic springs: Error correction of conceptual reservoir models with machine learning

ABSTRACT Accurate spring discharge modeling and prediction is crucial for water management, helping authorities optimize use, manage variability, and prepare for droughts. Developing reliable simulation and forecasting tools is essential for effective management of groundwater resources from karstic springs. Although hybrid modeling approaches have been explored in hydrology, their application to spring discharge modeling is underexplored. Previous studies have focused on conceptual/distributed or data-driven models separately, missing the potential advantages of combining them. This creates a research gap in exploring the benefits of hybrid models for spring discharge. This study developed a hybrid model combining a conceptual GR5J model with Random Forests to simulate spring discharge from Bordeaux's largest karst aquifer. Model performance was assessed through comparison with the individual GR5J, RF, and benchmark models (weekly average of observed values). The hybrid model outperformed all models. Evaluation using actual meteorological data found the hybrid model achieved the highest accuracy by reducing GR5J simulation errors by 22%. When considering meteorological uncertainty, the hybrid model outperformed the individual GR5J, RF and benchmark models by 11, 30 and 47% respectively. The study findings suggest combining conceptual and machine learning approaches can improve spring discharge simulations, opening promising opportunities for enhanced forecasting in karst aquifers.

Noisecut: a python package for noise-tolerant classification of binary data using prior knowledge integration and max-cut solutions

BackgroundClassification of binary data arises naturally in many clinical applications, such as patient risk stratification through ICD codes. One of the key practical challenges in data classification using machine learning is to avoid overfitting. Overfitting in supervised learning primarily occurs when a model learns random variations from noisy labels in training data rather than the underlying patterns. While traditional methods such as regularization and early stopping have demonstrated effectiveness in interpolation tasks, addressing overfitting in the classification of binary data, in which predictions always amount to extrapolation, demands extrapolation-enhanced strategies. One such approach is hybrid mechanistic/data-driven modeling, which integrates prior knowledge on input features into the learning process, enhancing the model’s ability to extrapolate.ResultsWe present NoiseCut, a Python package for noise-tolerant classification of binary data by employing a hybrid modeling approach that leverages solutions of defined max-cut problems. In a comparative analysis conducted on synthetically generated binary datasets, NoiseCut exhibits better overfitting prevention compared to the early stopping technique employed by different supervised machine learning algorithms. The noise tolerance of NoiseCut stems from a dropout strategy that leverages prior knowledge of input features and is further enhanced by the integration of max-cut problems into the learning process.ConclusionsNoiseCut is a Python package for the implementation of hybrid modeling for the classification of binary data. It facilitates the integration of mechanistic knowledge on the input features into learning from data in a structured manner and proves to be a valuable classification tool when the available training data is noisy and/or limited in size. This advantage is especially prominent in medical and biomedical applications where data scarcity and noise are common challenges. The codebase, illustrations, and documentation for NoiseCut are accessible for download at https://pypi.org/project/noisecut/. The implementation detailed in this paper corresponds to the version 0.2.1 release of the software.

Hybrid modeling for carbon monoxide gas-phase catalytic coupling to synthesize dimethyl oxalate process

Ethylene glycol (EG) plays a pivotal role as a primary raw material in the polyester industry, and the syngas-to-EG route has become a significant technical route in production. The carbon monoxide (CO) gas-phase catalytic coupling to synthesize dimethyl oxalate (DMO) is a crucial process in the syngas-to-EG route, whereby the composition of the reactor outlet exerts influence on the ultimate quality of the EG product and the energy consumption during the subsequent separation process. However, measuring product quality in real time or establishing accurate dynamic mechanism models is challenging. To effectively model the DMO synthesis process, this study proposes a hybrid modeling strategy that integrates process mechanisms and data-driven approaches. The CO gas-phase catalytic coupling mechanism model is developed based on intrinsic kinetics and material balance, while a Long Short-Term Memory neural network is employed to predict the macroscopic reaction rate by leveraging temporal relationships derived from archived measurements. The proposed model is trained semi-supervised to accommodate limited-label data scenarios, leveraging historical data. By integrating these predictions with the mechanism model, the hybrid modeling approach provides reliable and interpretable forecasts of mass fractions. Empirical investigations unequivocally validate the superiority of the proposed hybrid modeling approach over conventional data-driven models and other hybrid modeling techniques.

Prediction of Cr(VI) and As(V) adsorption on goethite using hybrid surface complexation-machine learning model

This study aimed to develop surface complexation modeling-machine learning (SCM-ML) hybrid model for chromate and arsenate adsorption on goethite. The feasibility of two SCM-ML hybrid modeling approaches was investigated. Firstly, we attempted to utilize ML algorithms and establish the parameter model, to link factors influencing the adsorption amount of oxyanions with optimized surface complexation constants. However, the results revealed the optimized chromate or arsenate surface complexation constants might fall into local extrema, making it unable to establish a reasonable mapping relationship between adsorption conditions and surface complexation constants by ML algorithms. In contrast, species-informed models were successfully obtained, by incorporating the surface species information calculated from the unoptimized SCM with the adsorption condition as input features. Compared with the optimized SCM, the species-informed model could make more accurate predictions on pH edges, isotherms, and kinetic data for various input conditions (for chromate: root mean square error (RMSE) on test set = 5.90 %; for arsenate: RMSE on test set = 4.84 %). Furthermore, the utilization of the interpretable formula based on Local Interpretable Model-Agnostic Explanations (LIME) enabled the species-informed model to provide surface species information like SCM. The species-informed SCM-ML hybrid modeling method proposed in this study has great practicality and application potential, and is expected to become a new paradigm in surface adsorption model.

Uneven Usage Battery State of Health Estimation via Fractional-Order Equivalent Circuit Model and AutoML Fusion

To accurately predict the State of Health (SOH) of lithium-ion batteries under the continuously changing charging and discharging conditions in practical applications, this study proposes a hybrid modeling approach that integrates a Fractional Order Equivalent Circuit Model (F-ECM) with the AutoGluon automatic machine learning framework. By leveraging Electrochemical Impedance Spectroscopy (EIS) to capture battery frequency response characteristics, F-ECM accurately fits EIS data to extract detailed internal state parameters. The integration of AutoGluon automates the machine learning process, enhancing the precision of SOH predictions. Through testing and analysis on real battery datasets, this method has demonstrated superior prediction precision and computational efficiency compared to existing mainstream modeling approaches. Specifically, the hybrid method achieved a Root Mean Square Error (RMSE) of 2.12% and a Mean Absolute Error (MAE) of 1.67%. This study presents a highly accurate, interpretable, and adaptable predictive framework for lithium-ion battery health assessment, offering valuable insights for battery health management system development.

Numerical Modeling of Potential Large Wood Entrainment in Rivers: Application of Hybrid Modeling in the Inter‐Dam Reach of the Dyje River, Czechia

AbstractMobilization of large wood in river channels during floods represents a hazardous factor, augmenting flood risk and endangering infrastructures such as bridges, weirs, and reservoir dams. A hybrid modeling approach combining numerical models with field‐based surveys has been recently used to elucidate the processes of LW entrainment and deposition in rivers. We used two‐dimensional hydraulic modeling performed in HEC‐RAS to simulate LW entrainment in two valley bottom segments of the Dyje River, Czechia, where LW deposition is a significant hazard to the dam of the downstream Znojmo reservoir. We surveyed all LW pieces in the inundation area of the 2002 extreme (&gt;Q100) flood and simulated their entrainment for eight flood scenarios (1–100‐year recurrence interval). We used the equations of Braudrick and Grant (2000, https://doi.org/10.1029/1999WR900290) to calculate the LW entrainment threshold; we introduced coefficient k accounting for the incomplete submersion of LW pieces resting on an inclined surface into the original equations. Four entrainment categories — stable, wetted stable, wetted buoyant, and wetted entrained — were defined, and the proportion of LW pieces in each category was calculated for the flood scenarios. We found marked differences in entrainment categories for respective flood scenarios between the two valley segments. These were attributed to the differences in pieces' dimensions, their spatial distribution within the inundation area, and valley‐bottom topography, which affects the hydraulic conditions for a given discharge. The presented approach enables the calculation of the LW quantity potentially mobilized by the flood of a certain magnitude indicating the degree of potential risk for the infrastructures located downstream.

A Hybrid Modeling Approach for Estimating the Exposure to Organophosphate Pesticide Drift in Sangamon County, Illinois

According to estimates from the World Health Organization (WHO), organophosphate pesticides are responsible for approximately 300,000 deaths worldwide. In the United States, documented cases of organophosphate pesticide exposure number around 8000, with a small number of fatalities occurring annually. The health risks associated with these pesticides affect those living in agricultural areas, as well as farmers and pesticide applicators. Despite the intervention of government agencies in Illinois to regulate pesticide application, studies have shown that these pesticides remain present in the soil, crops, water, and air. Urban-agricultural interface communities around Sangamon County exhibit significant levels of air pollution due to pesticide spray drift, although the lack of reliable pesticide data poses a challenge in estimating the extent of the problem. Therefore, developing novel strategies to reduce the impact of pesticides on environmental health is a critical and effective research area. Currently, new, dependable models and methods are being developed to calculate spray drift and mitigate its effects. The primary objective of this study was to investigate whether and to what extent organophosphate pesticide spray drifts into urban-agricultural interface communities in Sangamon County, Illinois. To achieve this, the current study employed an integrated approach that combined the capabilities of the HYSPLIT and AgDRIFT models to evaluate organophosphate pesticide spray drifting at both the field- and county-level scales. In the absence of precise pesticide quantity data, this novel approach allowed for field simulations within identified exposure drift zones. The preliminary findings indicate that all residential areas close to agricultural areas are at risk of pesticide drift, as buffer zones do not exceed 25 m. Furthermore, of the 34 water bodies (rivers, lakes, streams, and drains) in the 30,200-acre study region, 12 are within the high-drift zone for pesticide spray drift from corn and soybean fields. Finally, the potential for organophosphate pesticide drift was present in approximately 106 buildings, covering an area of 10,300 km2.

Prediction of customer demand for perishable products in retail inventory management, using the hybrid prophet-XGBoost model during the post-COVID-19 period

ABSTRACT Retail inventory management (IM) presents challenges in decision-making, especially in determining optimal inventory levels for future customer demand alignment. This study focuses on predicting dairy product demand by a significant European retail company using historical order data. As dairy products are perishable and constitute a relevant portion of retail trade volume, accurate IM is crucial to prevent wastage and meet customer needs. However, external factors like COVID-19 may impact demand volatility and seasonal patterns. Given the absence of scientific studies on predicting post-COVID-19 demand, our research aims to fill this gap by proposing alternatives, such as excluding the pandemic period and developing a historical imputation. The study employs two predictive models, Prophet and XGBoost, known for their superior performance in predicting demand. Moreover, a hybrid approach combining both models is proposed to enhance prediction accuracy by leveraging the capacity of the Prophet model to handle seasonal and holiday-period effects and XGBoost’s regularization to prevent overfitting. The results demonstrate the feasibility of historical imputation and the hybrid model approach, improving significantly individual model performance. The principal application of the study is to propose an approach to predict the shipment of other products in a post-COVID-19 context.

Improving the simulations of the hydrological model in the karst catchment by integrating the conceptual model with machine learning models

Hydrological modelling can be complex in nonhomogeneous catchments with diverse geological, climatic, and topographic conditions. In this study, an integrated conceptual model including the snow module with machine learning modelling approaches was implemented for daily rainfall-runoff modelling in mostly karst Ljubljanica catchment, Slovenia, which has heterogeneous characteristics and is potentially exposed to extreme events that make the modelling process more challenging and crucial. In this regard, the conceptual model CemaNeige Génie Rural à 6 paramètres Journalier (CemaNeige GR6J) was combined with machine learning models, namely wavelet-based support vector regression (WSVR) and wavelet-based multivariate adaptive regression spline (WMARS) to enhance modelling performance. In this study, the performance of the models was comprehensively investigated, considering their ability to forecast daily extreme runoff. Although CemaNeige GR6J yielded a very good performance, it overestimated low flows. The WSVR and WMARS models yielded poorer performance than the conceptual and hybrid models. The hybrid model approach improved the performance of the machine learning models and the conceptual model by revealing the linkage between variables and runoff in the conceptual model, which provided more accurate results for extreme flows. Accordingly, the hybrid models improved the forecasting performance of the maximum flows up to 40 % and 61 %, and minimum flows up to 73 % and 72 % compared to the CemaNeige GR6J and stand-alone machine learning models. In this regard, the hybrid model approach can enhance the daily rainfall-runoff modelling performance in nonhomogeneous and karst catchments where the hydrological process can be more complicated.