Modeling Accuracy Research Articles

A multi-view ensemble machine learning approach for 3D modeling using geological and geophysical data

Geophysical data are often integrated into geological data for 3D modeling of underground spaces. However, the existing single-view approach means it is difficult to adequately fuse the valid information between the two types of data, and the complexity of lithological decoding and classification is high. To address this issue, a multi-view ensemble machine learning (ML) framework is proposed. Initially, the original dataset of lithology prediction is constructed by aligning geological and geophysical data with different spatial scales. Next, the dataset is divided into three datasets of structural strength, density, and moisture content according to the lithology properties of the geophysical data. The proposed framework is then used to capture the lithologic characteristics under different views to achieve the prediction of lithologic labels. In this process, a self-attentive mechanism is used to adaptively fuse the valid information under each view. To validate the proposed framework, it is applied to a project in Jiaxing, Zhejiang Province, China. Compared with existing ML methods, the proposed multi-view ensemble ML framework improves modeling accuracy and constructs models with low uncertainty. The framework can be extended to other multi-source data fusion tasks across geoscience domains.

Impact of Utilizing High-Resolution PlanetScope Imagery on the Accuracy of LULC Mapping and Hydrological Modeling in an Arid Region

Impact of Utilizing High-Resolution PlanetScope Imagery on the Accuracy of LULC Mapping and Hydrological Modeling in an Arid Region

Revisiting equivalent optical properties for cerebrospinal fluid to improve diffusion-based modeling accuracy in the brain.

The diffusion approximation (DA) is used in functional near-infrared spectroscopy (fNIRS) studies despite its known limitations due to the presence of cerebrospinal fluid (CSF). Nearly all of these studies rely on a set of empirical CSF optical properties, recommended by a previous simulation study, that were not selected for the purpose of minimizing DA modeling errors. We aim to directly quantify the accuracy of DA solutions in brain models by comparing those with the gold-standard solutions produced by the mesh-based Monte Carlo (MMC), based on which we derive updated recommendations. For both a 5-layer head and Colin27 atlas models, we obtain DA solutions by independently sweeping the CSF absorption ( ) and reduced scattering ( ) coefficients. Using an MMC solution with literature CSF optical properties as reference, we compute the errors for surface fluence, total brain sensitivity and brain energy-deposition, and identify the optimized settings where the such error is minimized. Our results suggest that previously recommended CSF properties can cause significant errors (8.7% to 52%) in multiple tested metrics. By simultaneously sweeping and , we can identify infinite numbers of solutions that can exactly match DA with MMC solutions for any single tested metric. Furthermore, it is also possible to simultaneously minimize multiple metrics at multiple source/detector separations, leading to our new recommendation of setting = 0.15 mm-1 while maintaining physiological for CSF in DA simulations. Our new recommendation of CSF equivalent optical properties can greatly reduce the model mismatches between DA and MMC solutions at multiple metrics without sacrificing computational speed. We also show that it is possible to eliminate such a mismatch for a single or a pair of metrics of interest.

Bearing Dynamics Modeling Based on the Virtual State-Space and Hammerstein-Wiener Model.

This study investigates a novel approach for assessing the health status of rotating machinery transmission systems by analyzing the dynamic degradation of bearings. The proposed method generates multi-dimensional data by creating virtual states and constructs a multi-dimensional model using virtual state-space in conjunction with mechanism model analysis. Innovatively, the Hammerstein-Wiener (HW) modeling technique from control theory is applied to identify these dynamic multi-dimensional models. The modeling experiments are performed, focusing on the model's input and output types, the selection of nonlinear module estimators, the configuration of linear module transfer functions, and condition transfer. Dynamic degradation response signals are generated, and the method is validated using four widely recognized databases consisting of accurate measurement signals collected by vibration sensors. Experimental results demonstrated that the model achieved a modeling accuracy of 99% for multiple bearings under various conditions. The effectiveness of this dynamic modeling method is further confirmed through comparative experimental data and signal images. This approach offers a novel reference for evaluating the health status of transmission systems.

Heterogeneous Volatility Information Content for the Realized GARCH Modeling and Forecasting Volatility

Abstract As the demand for accuracy in volatility modeling and forecasting increases, the literature tends to incorporate different volatility measures with heterogeneous information content to construct the hybrid volatility model. This study focuses on one of the popular hybrid volatility models: the Realized Generalized Autoregressive Heteroskedasticity (Realized GARCH) and embeds various volatility measures, including the CBOE VIX, VIX1D, Realized Volatility, and Daily Range to examine their heterogeneous impact on the conditional volatility estimation and forecasting. To evaluate the impact of the volatility measures, we first construct a volatility response function. This involves calculating the difference in one-step-ahead conditional volatility forecasts that incorporate information from both return and volatility measures against the forecasts based on return innovations only. Subsequently, the variance share is calculated to evaluate its role in explaining future variations in the Realized GARCH. Our results show that among these four volatility measures, VIX is the most informative volatility. Although VIX1D is overemphasized by the literature, its significance in volatility forecasting remains substantial, confirming that risk-neutral volatility measures are generally more informative than physical measures. Finally, we also find that incorporating multiple risk-neutral volatility measures does not improve forecasting performance compared to using a single measure due to overlapping information.

Building thermal energy efficiency modeling based on light image inspection and super resolution algorithm in interior landscape design

With the intensification of global climate change and energy crisis, the thermal efficiency of buildings has become increasingly important. Interior landscape design not only affects living comfort, but also plays a key role in building energy efficiency. Therefore, it is of great practical significance to explore the modeling method of building thermal energy efficiency based on optical image inspection and super resolution algorithm. The light image inspection technique is used to obtain the data of light and temperature distribution inside the building. The super-resolution algorithm of deep learning is used to process the acquired low-resolution image to improve the clarity and detail of the image. Combined with the physical characteristics of the building, the thermal efficiency model of the building is constructed and multi-dimensional analysis is carried out. The experimental results show that the combination of optical image inspection and super resolution algorithm can effectively improve the accuracy of building thermal efficiency modeling. Compared with traditional methods, the prediction error of the model is reduced, and the recommended optimization scheme performs better in terms of energy consumption in different interior landscape design schemes. Therefore, the building thermal efficiency modeling method based on optical image inspection and super resolution algorithm provides a new idea for interior landscape design. Through accurate thermal efficiency analysis, it can provide more scientific decision-making basis for architectural designers, so as to realize the sustainable development of buildings and maximize the energy efficiency.

Digital toy design: A doll head modeling method based on model matching and texture generation

With the development of technology and the improvement of living standards, consumer demand for toy products has also changed. More people are showing strong interest and demand for digital toy products. However, in the current digital toy design process, extracting the hairstyle features of the doll’s head is still a challenge. Therefore, this study extracts the two-dimensional contour of the target hairstyle and matches it with the template hairstyle in the database. Then, combining hair texture information and hairstyle structural features, fine geometric texture details are generated on the hairstyle mesh surface. Finally, a doll head modeling method based on model matching and texture generation is proposed. The results showed that the hairstyle of the Generative model was almost the same as the real hairstyle. Compared with the modeling methods based on interactive genetic algorithm and digital image, the average F1 value of this method was 0.95, and the mean absolute error was the smallest. The accuracy of the target model modeling was 95.4%, and the area enclosed by the receiver operating characteristic curve and coordinate axis was 0.965. In summary, the doll head modeling method based on model matching and texture generation proposed in this study can generate high-precision and realistic hairstyle models corresponding to the hairstyle. The overall shape and local geometric details of the hairstyle can meet the needs of 3D printing, providing certain reference significance for hairstyle reconstruction.

Quantifying the effects of diffuse photosynthetically active radiation on water use efficiency in different ecosystems

Compared with direct radiation, diffuse radiation could be more efficiently used for photosynthesis because of the diffuse fertilization effect (DFE). Because carbon uptake and water loss are coupled through leaf stomata, DFE probably increases gross primary productivity (GPP) and evapotranspiration (ET) simultaneously. Multi-year eddy covariance flux observation data and simulated diffuse fraction of photosynthetically active radiation (PAR) for nine ecosystems across China (containing forest, grassland, wetland, and cropland) were used to quantify the impact of DFE on water use efficiency (WUE). The results showed that GPP firstly increased and then decreased with increasing diffuse fraction of PAR (kd-PAR = diffuse PAR/PAR) for each ecosystems. The kd-PAR values at which maximum GPP occurred varied between 0.34 and 0.76 across nine ecosystems. ET decreased with increasing kd-PAR in most ecosystems mainly because high kd-PAR (indicating low PAR) could reduce evaporation in most ecosystems. The relationships between WUE and kd-PAR were significantly linear with averaged slopes of forest, grassland, wetland, and cropland of 1.64, 0.96, 1.19, and 4.51 g C kg−1 H2O, respectively. A multiple linear regression method was used to analyze the effect of diffuse PAR (PARdif) and direct PAR (PARdir) on GPP and ET. The conversion efficiencies for PARdif were greater than for PARdir, and the relative differences were 178.35% and 23.77% for GPP and ET, respectively. The intensity of DFE for GPP and ET were greater for forest and cropland than for grassland and wetland. The intensity of DFE was 3.05 to 236.96 times higher for GPP than for ET. The mathematical analysis results demonstrated that the promoting effect of PARdif was greater for GPP than for ET, thereby inducing an increase in WUE with increasing kd-PAR. These results will be helpful for improving modeling accuracy of carbon and water cycles under the conditions accompanying global climate change.

PW-SMD: A Plane-Wave Implicit Solvation Model Based on Electron Density for Surface Chemistry and Crystalline Systems in Aqueous Solution.

Electron density-based implicit solvation models are a class of techniques for quantifying solvation effects and calculating free energies of solvation without an explicit representation of solvent molecules. Integral to the accuracy of solvation modeling is the proper definition of the solvation shell separating the solute molecule from the solvent environment, allowing for a physical partitioning of the free energies of solvation. Unlike state-of-the-art implicit solvation models for molecular quantum chemistry calculations, e.g., the solvation model based on solute electron density (SMD), solvation models for systems under periodic boundary conditions with plane-wave (PW) basis sets have been limited in their accuracy. Furthermore, a unified implicit solvation model with both homogeneous solution-phase and heterogeneous interfacial structures treated on equal footing is needed. In order to address this challenge, we developed a high-accuracy solvation model for periodic PW calculations that is applicable to molecular, ionic, interfacial, and bulk-phase chemistry. Our model, PW-SMD, is an extension of the SMD molecular solvation model to periodic systems in water. The free energy of solvation is partitioned into the electrostatic and cavity-dispersion-solvent structure (CDS) contributions. The electrostatic contributions of the solvation shell surrounding solute structures are parametrized based on their geometric and physical properties. In addition, the nonelectrostatic contribution to the solvation energy is accounted for by extending the CDS formalism of SMD to incorporate periodic boundary conditions. We validate the accuracy and robustness of our solvation model by comparing predicted solvation free energies against experimental data for molecular and ionic systems, carved-cluster composite energetic models of solvated reaction energies and barriers on surface systems, and deep-learning-accelerated ab initio molecular dynamics (AIMD). Our developed periodic implicit solvation model shows significantly improved accuracy compared to previous work (namely, solvation models in aqueous solution) and can be applied to simulate solvent effects in a wide range of surface and crystalline materials.

Emission Rate Estimation of Industrial Air Pollutant Emissions Based on Mobile Observation

Mobile observation has been widely used in the monitoring of air pollution. However, studies on pollution sources and emission characteristics based on mobile navigational observation are rarely reported in the literature. A method for quantitative source analysis for industrial air pollutant emissions based on mobile observations is introduced in this paper. NOx pollution identified in mobile observations is used as an example of the development of the method. A dispersion modeling scheme that fine-tuned the meteorological parameters according to the actual meteorological conditions was adopted to minimize the impact of uncertainties in meteorological conditions on the accuracy of small-scale dispersion modeling. The matching degree between simulated and observed concentrations was effectively improved through this optimization search. In response to the efficiency requirements of source resolution for multiple sources, a random search algorithm was first used to generate candidate solution samples, and then the solution samples were evaluated and optimized. Meanwhile, the new index Smatch was established to evaluate the quality of candidate samples, considering both numerical error and spatial distribution error of concentration, in order to address the non-uniqueness of the solution in the multi-source problem. Then, the necessity of considering the spatial distribution error of concentration is analyzed with the case study. The average values of NOx emission rates for the two study cases were calculated as 69.8 g/s and 70.8 g/s. The Smatch scores were 0.92–0.97 and 0.92–0.99. The results were close to the online monitoring data, and this kind of pollutant emission monitoring based on the mobile observation experiment was initially considered feasible. Additional analysis and clarifications were provided in the discussion section on the impact of uncertainties in meteorological conditions, the establishment of a priori emission inventories, and the interpretation of inverse calculation results.

Geotechnical risk modeling using an explainable transfer learning model incorporating physical guidance

While Artificial intelligence (AI) has been successfully applied in assessing geotechnical risk, such methods heavily rely on data quality to achieve satisfactory performance, and their results hardly can be interpreted due to their opaque design. With this in mind, this paper aims to address the following research gap: How can we accurately model geotechnical risks using limited data and domain knowledge, and efficiently explain the results of AI model? We develop a physics-guided transfer learning (PGTL) model to enhance the explainability and accuracy of geotechnical risk modeling. With the help of a physical model that simulates the tunnel excavation, a physics-guided dataset with 1000 samples is established and used to train a deep neural network. On these bases, transfer learning is adopted to fuse the features of physics mechanisms and monitoring data, constructing an explainable prediction model of geotechnical risk. To further support risk decision-making, feature relevance techniques are employed to assess the contribution of input parameters to risk. A shield tunnel construction in Wuhan is selected as a case to validate the effectiveness of the proposed method. The PGTL exhibits a more promising accuracy with R2 of 0.777 in contrast to three popular machine learning approaches, and provides insights into parameters that significantly induce risk, enhancing site managers’ understanding of tunnel construction and being conducive to tunnel safety.

Runoff Prediction of Tunxi Basin under Projected Climate Changes Based on Lumped Hydrological Models with Various Model Parameter Optimization Strategies

Runoff is greatly influenced by changes in climate conditions. Predicting runoff and analyzing its variations under future climates are crucial for ensuring water security, managing water resources effectively, and promoting sustainable development within the catchment area. As the key step in runoff modeling, the calibration of hydrological model parameters plays an important role in models’ performance. Identifying an efficient and reliable optimization algorithm and objective function continues to be a significant challenge in applying hydrological models. This study selected new algorithms, including the strategic random search (SRS) and sparrow search algorithm (SSA) used in hydrology, gold rush optimizer (GRO) and snow ablation optimizer (SAO) not used in hydrology, and classical algorithms, i.e., shuffling complex evolution (SCE-UA) and particle swarm optimization (PSO), to calibrate the two-parameter monthly water balance model (TWBM), abcd, and HYMOD model under the four objective functions of the Kling–Gupta efficiency (KGE) variant based on knowable moments (KMoments) and considering the high and low flows (HiLo) for monthly runoff simulation and future runoff prediction in Tunxi basin, China. Furthermore, the identified algorithm and objective function scenario with the best performance were applied for runoff prediction under climate change projections. The results show that the abcd model has the best performance, followed by the HYMOD and TWBM models, and the rank of model stability is abcd > TWBM > HYMOD with the change of algorithms, objective functions, and contributing calibration years in the history period. The KMoments based on KGE can play a positive role in the model calibration, while the effect of adding the HiLo is unstable. The SRS algorithm exhibits a faster, more stable, and more efficient search than the others in hydrological model calibration. The runoff obtained from the optimal model showed a decrease in the future monthly runoff compared to the reference period under all SSP scenarios. In addition, the distribution of monthly runoff changed, with the monthly maximum runoff changing from June to May. Decreases in the monthly simulated runoff mainly occurred from February to July (10.9–56.1%). These findings may be helpful for the determination of model parameter calibration strategies, thus improving the accuracy and efficiency of hydrological modeling for runoff prediction.

Enhancing Microkinetic Modeling for CO2 Reduction Reaction: Integrating Electrolyte Effects

In the current landscape of escalating global environmental challenges, the development of sustainable energy solutions has become increasingly critical. A pivotal area in this endeavor is the carbon dioxide reduction reaction (CO2RR) technology, which holds the promise of converting CO2, a major greenhouse gas, into valuable chemicals and fuels. The intricate nature of CO2RR, characterized by complex reaction pathways and a plethora of intermediates, presents significant scientific and engineering challenges. Key to surmounting these challenges is the accurate and comprehensive modeling of CO2RR processes. However, traditional computational models often overlook a crucial aspect – the influence of electrolyte interactions with CO2RR intermediates. This omission leads to models that inadequately capture the true dynamics of the electrochemical environment, resulting in less accurate predictions. In this work, we introduce CatEnergy, a Python module that enhances our existing microkinetic modeling tool, CatMAP[1], focusing on CO2RR. CatEnergy specifically addresses the complexity of CO2RR by integrating electrolyte interaction data. This integration enables a more accurate representation of the electrochemical environment, improving the predictive power and efficacy of CO2RR models. By generating essential electrolyte interaction data for microkinetic modeling, it facilitates more effective catalyst design and optimization of reaction conditions. This development is key in advancing the accuracy of microkinetic modeling for CO2RR and underscores our commitment to sophisticated tool development in sustainable energy research. [1] Medford, A. J. et al. CatMAP: A Software Package for Descriptor-Based Microkinetic Mapping of Catalytic Trends. Catal. Lett. 145, 794–807 (2015).

N-level complex helical structure modeling method

This paper primarily explores the modeling method of n-level complex helical structures with coal mining machine cables as the research object. The paper first elaborately introduces the modeling method of n-level helix curves based on parametric equations and coordinate transformations, and compensates for the n-level helix curves with corrected pitch, which can obtain more accurate n-level helix curves and improve the accuracy of n-level helix curves modeling. Subsequently, based on this high-precision n-level helix curves modeling method, the paper elaborates on the method of solving pitch and twisting radius of multi-layer helical structure. Calculation scripts were written based on the above methods, which can be used to batch calculate the twisting radius and pitch of each layer structure in multi-layer structures when satisfying the conditions of in-layer tangency, inter-layer tangency, and extrusion deformation, and retain the actual results through logical judgment. Then, based on the above two methods, the paper developed a modeling method for braided structures based on piecewise functions containing fifth-order polynomials, which can effectively avoid the problem of insufficiently dense arrangement of braided lines and easy interference in traditional methods. Finally, a set of modeling tools was developed using C# and Python in Grasshopper to implement the modeling algorithm. Taking the MCPT-1.9/3.3 3120 + 170 + 4 * 10 coal mining machine cable as an example. The cable was modeled using both the method proposed in this paper and the traditional method. Comparative data shows that the method proposed in this paper can reduce errors by 3.31E6 times in the second-level and above helical structures. In addition this paper compares the standard line length, measured line length, and the line length established by the proposed model, showing that the relative errors are both less than 0.1941%. This paper provides a new, systematic, high-precision, and full-process cable modeling method, in which all parameters except the process parameters are accurately solved by equations. It lays a theoretical foundation for the high-precision simulation and intelligent sensing cables, which is of great significance for improving the safety, stability, and efficient development of the coal mining industry. The research results of the paper can not only be applied to the modeling of coal mining machine cables but also can be extended to the modeling of other complex multi-layer helical structures.

CO2 solubility in aqueous solution of salts: Experimental study and thermodynamic modelling

AbstractThere are many economic obstacles and complex engineering problems associated with CO2 capture and storage in saline aquifers that need to be addressed. Overcoming such challenges requires precise knowledge on the fluid phase equilibria of CO2‐brine systems. Having accurate CO2 solubility data over a wide range of temperature and pressure can greatly assist in resolving these obstacles by improving the performance and accuracy of the thermodynamic modeling and subsequent CCS engineering success.CO2 solubility in pure water and NaCl solutions has been widely studied in the literature, however, there is a lack of data on CO2 solubility at lower temperatures (below 298 K). Furthermore, limited phase equilibria data are available for CO2 solubility in CaCl2, MgCl2, and KCl solutions at elevated temperatures (i.e., T > 323.15 K).In this work, the phase equilibria of CO2 and brine systems are investigated experimentally and theoretically. In this study, solubilities of CO2 in pure water and various concentrations of NaCl (10, 15, 20, and 22 wt%), KCl (10, 15, and 22 wt%), CaCl2 (7.5, 10, 15.7, and 23.4 wt%), and MgCl2 (6.7, 11, 18, and 29 wt%) aqueous solutions are reported. All CO2 solubilities were measures at 323.15, 373.15, and 423.15 K and over various pressure ranges, while solubilities in 10 and 20 wt% NaCl aqueous solutions were also measured over the temperature range of 263 to 298 K and pressures up to the hydrate dissociation pressure of each system. Equation of state modelling using the PC‐SAFT and the Cubic Plus Association equations of state, is performed in the theoretical part of the study to validate the measured solubility data. © 2024 The Author(s). Greenhouse Gases: Science and Technology published by Society of Chemical Industry and John Wiley & Sons Ltd.

Estimating travel time in the Helsinki region utilising sequential Bayesian inference

This paper explores application of Bayesian inference (BI) to dynamic travel time estimation in the Helsinki region. Accurate travel time prediction is crucial in a wide range of fields, including departure time and routing. Limited real-time data challenge modelling accuracy. To address this, this paper utilises BI, particularly sequential Bayesian inference (SBI) for evolving observed values. Incorporating 2018 real-time data and 2015 information as prior knowledge, travel time distribution will be updated. Validation yields a 4.0% mean absolute error between the updated 2018 distribution and actual travel time. Also, using the 2015 posterior distribution as prior by way of SBI yields a 4.6% mean absolute error. Results highlight that SBI is an effective tool for updating distributions. This paper underscores potential of BI in addressing data scarcity and enhancing accuracy of transportation models. By supplying precise travel time estimates, this approach benefits congestion relief and travel planning. With evolving travel time data, BI promises to advance transportation modelling.

Mapping agricultural tile drainage in the US Midwest using explainable random forest machine learning and satellite imagery

There has been an increase in tile drained area across the US Midwest and other regions worldwide due to agricultural expansion, intensification, and climate variability. Despite this growth, spatially explicit tile drainage maps remain scarce, which limits the accuracy of hydrologic modeling and implementation of nutrient reduction strategies. Here, we developed a machine-learning model to provide a Spatially Explicit Estimate of Tile Drainage (SEETileDrain) across the US Midwest in 2017 at a 30-m resolution. This model used 31 satellite-derived and environmental features after removing less important and highly correlated features. It was trained with 60,938 tile and non-tile ground truth points within the Google Earth Engine cloud-computing platform. We also used multiple feature importance metrics and Accumulated Local Effects to interpret the machine learning model. The results show that our model achieved good accuracy, with 96 % of points classified correctly and an F1 score of 0.90. When tile drainage area is aggregated to the county scale, it agreed well (r2 = 0.69) with the reported area from the Ag Census. We found that Land Surface Temperature (LST) along with climate- and soil-related features were the most important factors for classification. The top-ranked feature is the median summer nighttime LST, followed by median summer soil moisture percent. This study demonstrates the potential of applying satellite remote sensing to map spatially explicit agricultural tile drainage across large regions. The results should be useful for land use change monitoring and hydrologic and nutrient models, including those designed to achieve cost-effective agricultural water and nutrient management strategies. The algorithms developed here should also be applicable for other remote sensing mapping applications.

Unveiling the environmental significance of acetylperoxyl radical: Reactivity quantification and kinetic modeling.

Acetylperoxyl radical (CH3C(O)OO•) is among highly reactive organic radicals which are known to play crucial roles in atmospheric chemistry, aqueous chemistry and, most recently, peracetic acid (PAA)-based advanced oxidation processes. However, fundamental knowledge for its reactivity is scarce and severely hampers the understanding of relevant environmental processes. Herein, three independent experimental approaches were exploited for revelation and quantification of the reaction rates of acetylperoxyl radical. First, we developed and verified laser flash photolysis of biacetyl, ultraviolet (UV) photolysis of biacetyl, and pulse radiolysis of acetaldehyde, each as a clean source of CH3C(O)OO•. Then, using competition kinetics and selection of suitable probe and competitor compounds, the rate constants between CH3C(O)OO• and compounds of diverse structures were determined. The three experimental approaches complemented in reaction time scale and ease of operation, and provided cross-validation of the rate constants. Moreover, the formation of CH3C(O)OO• was verified by spin-trapped electron paramagnetic resonance, and potential influence of other reactive species in the systems was assessed. Overall, CH3C(O)OO• displays distinctively high reactivity and selectivity, reacting especially favorably with naphthyl and diene compounds (k ∼ 107-108 M-1 s-1) but sluggishly with N- and S-containing groups. Significantly, we demonstrated that incorporating acetylperoxyl radical-oxidation reactions significantly improved the accuracy in modeling the degradation of environmental micropollutants by UV/PAA treatment. This study is among the most comprehensive investigation for peroxyl radical reactivity to date, and establishes a robust methodology for investigating organic radical chemistry. The determined rate constants strengthen kinetic databases and improve modeling accuracy for natural and engineered systems.

Kernel-based framework for improved prediction of discharge coefficient in vertically supported cylindrical weirs

ABSTRACT The present study represents the first use of kernel-based models to predict discharge coefficient (Cd) for two distinct types of cylindrical weirs, featuring vertical support and a 30-degree upstream ramp. For this purpose, kernel-based methods, including support vector machine, Gaussian process regression (GPR), Kernel extreme learning machine, and Kernel ridge regression, were used, as they offer notable advantages compared to other machine learning models, such as flexibility in handling various data patterns, robustness against overfitting, and effectiveness in high-dimensional data scenarios. The results indicated that the GPR model, with statistical metrics of R = 0.967, Nash–Sutcliffe efficiency (NSE) = 0.935, and root-mean-square error (RMSE) = 0.027, demonstrates superior accuracy in modeling the overall dataset collected from two distinct types of weirs. Through a conducted sensitivity analysis, it was identified that the upstream Froude number is pivotal in accurately predicting the Cd of a cylindrical weir. The modeling conducted for two distinct weir types revealed that a cylindrical weir with vertical support exhibits enhanced predictive capabilities (R = 0.997, NSE = 0.994, and RMSE = 0.007) for Cd. The findings indicate that the introduction of the upstream ramp alters hydraulic conditions, resulting in reduced modeling accuracy (R = 0.760, NSE = 0.529, and RMSE = 0.060).

Data-driven parameterization and development of mechanistic cell cultivation models in monoclonal antibody production processes: Shifts in cell metabolic behavior

Representative kinetic models to describe monoclonal antibody (mAb) production processes are needed for effective process design. The development of mechanistic models can be impeded by the lack of complete understanding of changes in cell metabolism, e.g., lactate metabolic shifts. State-estimation-based methods were applied to assess the fit of available kinetic models over experimental runs. The results indicated the regions where model parameter updates were required. Different clustering strategies were applied to isolate the variations in the culture environment and correlate them to the lactate shifts. Alternative formulations for the specific lactate consumption/production term were provided for each identified phase. Two case studies are presented for pilot-scale data in different reactor types. The results show the improvement in modeling accuracy and highlight the role of oxygen and nutrient levels on the shifts. The approach showcases the use of data-driven insights to effectively utilize limited experimental data to develop robust mechanistic models.