Output Variables Research Articles

Efficient proxy for time-lapse seismic forward modeling using a U-net encoder-decoder approach

The time-lapse seismic (4D seismic) forward modeling provides crucial data for calibrating reservoir models through different data assimilation algorithms. Unfortunately, the traditional 4D seismic forward-modeling methodology is time-expensive and entails significant computational resource consumption. To address these drawbacks, in this work, our goal is to develop a proxy model for the 4D seismic forward modeling using a class of machine learning algorithm named U-Net encoder–decoder. We applied the developed proxy model to a benchmark carbonate reservoir using an ensemble of reservoir simulation models from UNISIM IV dataset (a synthetic benchmark based on real data of a Brazilian pre-salt field). Moreover, we aim to introduce seminal strategies for interpreting the proposed proxy model operation, its outputs, and possible correlations between input and output variables. To achieve this, we trained and tested two versions of U-net-based models and applied methods for explainable artificial intelligence, such as Gradient-weighted Class Activation Mapping (Grad-CAM) and Forward Feature Selection. The experiments showed good results when applied to the test dataset. The correlation coefficient (R2) values were in the range of 0.7 to 0.9, showing the efficiency of the proxy model to replace the 4D seismic forward modeling. Through qualitative analysis, it was possible to identify which input properties and regions of the reservoir are more relevant for the model’s inference. These results are a step toward robust, explainable machine learning-based proxy forward modeling.

Prediction of ketosis using radial basis function neural network in dairy cattle farming.

The purpose of the paper was to apply an Artificial Neural Networks with Radial Basis Function to develop an application model for diagnosing a subclinical ketosis type I and II in dairy cattle. While building the neural network model, applied methodology was compatible to the procedures used in Data Mining processes.The data set was created based on the composition of milk samples of 1520 Polish Holstein-Friesian cows. The milk samples were collected during test-day milkings and made available by Polish Federation of Cattle Breeders and Milk Producers. The milk composition parameters were used as the input variables for RBF network models. The value of the output variable was determined based on the content of β-hydroxybutyric acid in blood of cows. In the next stage of the work, the qualities of the pre-selected models were compared and the best ones were chosen. The sensitivity and specificity as well as the size of the AUC (Area Under the Curve) under the ROC (Receiver Operating Characteristic) were taken as the main criteria for network models evaluation. The model characterized by sensitivity of 0.86, specificity of 0.71 and AUC of 0.89 was selected for ketosis type I. The optimal for ketosis type II showed the sensitivity and specificity 0.81 and 0.75, respectively, and the size of AUC above 0.85. Chosen models were recorded using the predictive modelling markup language (PMML) for data mining models to be shared and used between the different applications.

“Advancing Ozone Forecasting with LSTM Neural Networks: A Study on Time Window Variations and Performance Metrics”

ABSTRACT In the face of growing global concern about air pollution and its adverse impacts on health and well-being, air quality forecasting has become a major focus of research. This study investigates the application of Long Short-Term Memory (LSTM) neural network models for the prediction of ozone concentrations in different time windows (7, 15 and 30 days). The LSTM models were configured with two LSTM layers and two dense layers, varying the number of neurons between 50 and 200. Predictor variables included ‘Month,’ CO_ppb,’ ‘SO2_ugm3,’ ‘temperature,’ ‘humidity’ and ‘PM2.5_ugm3,’ while the output variable was ‘O3_ppb.’ The results showed that the LSTM model with 200 LSTM units and 50 dense units had the best performance, presenting a mean absolute error (MAE) of 1.49 ppb, an RMSE of 1.91 ppb and a coefficient of determination (R2) of 0.94 for 7-day forecasts. These results outperformed traditional models such as ARMA and linear regression, highlighting the effectiveness of LSTM in capturing complex patterns in ozone time series. The research suggests that future investigations could explore hybrid techniques to further improve the accuracy of predictions.

Hybrid Variable Renewable Power Plants: A Case Study of ROR Hydro Arbitrage

Wind and solar energy sources, while sustainable, are inherently variable in their power generation, posing challenges to grid stability due to their non-dispatchable nature. To address this issue, this study explores the synergistic optimization of wind and solar photovoltaic resources to mitigate power output variability, reducing the strain on local grids and lessening the reliance on balancing power in high-penetration renewable energy systems. This critical role of providing stability can be effectively fulfilled by run-of-river hydropower plants, which can complement fluctuations without compromising their standard operational capabilities. In this research, we employ a straightforward energy balance model to analyze the feasibility of a 100 MW virtual hybrid power plant, focusing on the northern region of Portugal as a case study. Leveraging actual consumption and conceptual production data, our investigation identifies a specific run-of-river plant that aligns with the proposed strategy, demonstrating the practical applicability of this approach.

Design of Temperature and Humidity Control System for Cocoa Bean Dryer Using Fuzzy Mamdani Method

This research aims to develop a fuzzy logic control system for optimizing temperature and humidity during cocoa bean fermentation. The study employs a literature review method and data analysis using MATLAB. A Mamdani-type fuzzy inference system is designed to control the temperature and humidity of a cocoa bean dryer. Input variables include temperature (0-65°C) and humidity (0-100%), while output variables are heater and fan settings. The system's performance is evaluated using a case study, demonstrating its ability to adjust heater and fan operations based on environmental conditions. Results show that for an input of 65°C temperature and 50% humidity, the system recommends turning off the heater (membership value 79.8) and running the fan at high speed (membership value 84.7). This fuzzy logic approach offers a promising solution for maintaining optimal conditions during cocoa bean fermentation, potentially improving the quality and consistency of the final product. Keywords: cocoa fermentation, fuzzy logic control, temperature regulation

Adaptive Sampling Limit Surface Search Application to Identify Cliff-Edge Effects in Severe Accident Uncertainty Analysis

Severe accident (SA) codes and their core degradation models have to deal with strongly nonlinear and discontinuous phenomena. In the application of uncertainty quantification to SA simulations, the combination of such phenomena may lead to a strong increase in the uncertainty propagated through the simulation, as well as to the chaotic behavior of the output variables. In this framework, the application of the limit surface search method of the RAVEN tool is proposed for a case where cliff-edge effects of SA phenomena determine a bifurcation of an output figure of merit. The algorithm is based on a predictive method making use of a support vector machine model, and it is applied with the aim of separating those input values that lead to different phenomenologies among the uncertainty calculations. The case study is in regard to the uncertainty analysis of the ASTEC code simulation of the QUENCH6 experimental test conducted in the framework of the International Atomic Energy Agency Coordinated Research Project I31033.

SWOT Analysis of Wind, Hydro, and Solar Energy Power Generation: Applications and Future Development in China

China is currently undergoing a transition in its energy structure, gradually reducing reliance on fossil fuels and increasing the proportion of clean energy sources. The government actively promotes the development of renewable energy, such as wind and solar power, while encouraging technological innovation to enhance energy efficiency. Additionally, China is exploring and promoting new energy technologies like nuclear and hydrogen power to establish a greener and low-carbon energy system in line with sustainable development goals. This paper provides a comprehensive analysis of the current status of wind, solar, and hydro energy in China using a SWOT analysis approach. It examines the strengths, weaknesses, opportunities, and threats associated with each energy source, focusing particularly on their environmental impacts, technological hurdles, and resource distribution. Wind power stands out as an essential element within China's renewable energy mix due to its substantial potential for power generation capacity - ranking second globally. However, it confronts concerns regarding its environmental implications as well as output variability. Solar energy has advantages in directing solar power conversion and easy recycling; it exhibits promising prospects. But encounters conflicts related to land use and efficiency issues. Hydropower continues to be a major contributor; nevertheless, it poses ecological and social challenges. Furthermore, this paper scrutinizes China's leadership in renewable energy while offering recommendations for sustainable development and policy improvements that can facilitate its ongoing transition towards cleaner sources of power.

Multioptimization analysis of machining characteristics on spark electrical discharge machining of Al/SiC and Al/SiC/B4C composites

Abstract This study examines the machining characteristics of sintered aluminium composites, including Al+6% SiC and Al+4% SiC+2% B4C, utilising electrical discharge machining (EDM) by changing the input machining factors like current (C) in amperes, Pulse-OFF and Pulse-ON time in µs, at three distinct levels. The L9 Orthogonal array was employed to examine the influence of process factors on output variables, including Surface Roughness (SR), Material Removal Rate (MRR), and Hole Circularity (HC). An Analysis of Variance (ANOVA) was conducted to determine the percentage contribution of the input factors to the output variables. Observation implies that the GRG ANOVA for Al+6%SiC composite has achieved the most significant contribution to the total GRG, with the current contributing 86.66%, followed by the Pulse-ON at 8.52% and the Pulse-OFF at 3.63%. In contrast, the Al+4%SiC+2%B4C composite shows the current contributing 74.07%, followed by the Pulse-ON at 15.25% and the Pulse-OFF at 9.82%. The ideal input levels for Al+6%SiC and Al+4%SiC+2%B4C composites were found to be A3B3C1 and A3B3C3, correspondingly.

Identifying an Appropriate Extractant for Assessing the Presence of Available Potassium in Soils with High Mica Content: A Comprehensive Statistical Analysis

ABSTRACT The choice of extractant for estimating plant-available potassium (K) in mica-rich soil has not been universally established. In order to evaluate and monitor the complex chemical performance of K in K-rich soil, and subsequently, its availability in crops, a suitable extractant protocol that takes into consideration soil properties in relation to rice plant parts (root, shoot, and grain) uptake becomes necessary. Nine laboratory soil K extraction methods to estimate the K content using 63 soil samples collected from nearly 21 mica mines, encompassing a wide range of properties across different agricultural lands. While extraction using ammonium acetate is the widely used for soil K testing, other methods have also been proposed for estimating crop-available K. Among the various extractants tested, 0.5 M sodium bicarbonate at pH 8.5 (mean 132.24 mg/kg) gave the best results for estimating the K content in mica-rich soil from agricultural areas near mica mines. Additionally, the soil water-soluble K extractant showed promise for rice plant parts such as root, shoot, and grain K uptake, as indicated by a correlation coefficient of 0.94, 0.94, and 0.93 respectively. Based on the artificial neural network (ANN) and Sobol (variance-based method for determining how different input variables contribute to the output variance of a model) methods, water-soluble K and the Mehlich 3 extraction procedure showed the best results for suitable extractable forms of K and a positive impact on K uptake by rice grain. Taylor (a graphical tool used to compare various models) diagram used for comparing multiple machine learning algorithms, multivariate adaptive regression spline and extreme gradient boosting (XGBoost) emerged as the best-fit models for determining the contribution of each extractant to rice K uptake. Considering soils derived from weathered parent materials often have negative K balances, which could lead to negative of plant-available K.

Craniofacial growth prediction models based on cephalometric landmarks in Korean and American children.

To compare differences in craniofacial growth prediction results for Korean and American children according to growth prediction models developed using Korean and American longitudinal growth data. Growth prediction models based on cephalometric landmarks were built for each population using longitudinally taken lateral cephalograms of Korean children and American children of northern European origin. The sample sizes of the serial datasets were 679 and 1257 for Korean and American children, respectively. On each cephalogram, 78 cephalometric landmarks were identified. The prediction models were based on the partial least squares method with 160 input and 154 output variables. For each group, growth was predicted by applying the prediction models developed using data from the same and different populations. The growth prediction results were compared and analyzed. The growth prediction results obtained with the prediction model developed using data from the same population were more accurate (P < .0001). The results distinctively visualized the discrepancies in the growth prediction results if different population types were not considered. Applying a growth prediction model generated using data from the same population may be desirable.

Understanding Trigger Linkage Dynamics in Energetic Materials Using Mixed Picramide Nitrate Ester Explosives.

The ability to predict the handling sensitivity of new organic energetic materials has been a longstanding goal. We report the synthesis and characterization of six new nitropicramide energetic materials with mixed functional groups that mimic known explosives such as nitroglycerin, erythritol tetranitrate (ETN), and pentaerythritol tetranitrate (PETN). The molecules have been studied theoretically using quantum molecular dynamics (QMD) simulations and density functional theory (DFT) calculations to identify the weakest bond in the reactants - the trigger-linkages - which control handling sensitivity, and to quantify their specific enthalpies of explosion. In good accord with the drop weight impact sensitivity data, our calculations predict that the sensitivities of the molecules are very similar owing to the small variations of the energy output and rates of trigger linkage rupture. In addition, both the QMD and DFT calculations point to the nitropicramide N-NO2 bonds as the trigger linkages rather than the more typical O-NO2 bonds. We propose that the switch of the trigger linkage from the nitrate esters to the nitramine groups arises from the strongly electron withdrawing character of the adjacent trinitrobenzene groups.

TCN-Transformer Deep Network with Random Forest for Prediction of the Chemical Synthetic Ammonia Process.

It is of great significance to realize the accurate prediction of the key output response of the chemical synthetic ammonia process for optimizing system performance and operation monitoring. Because many key intermediate variables of complex systems are difficult to measure comprehensively, there are great difficulties and errors in mechanism analysis and identification modeling techniques. Based on random forest (RF) variable selection, a deep neural network combining temporal convolutional network (TCN) and transformer is proposed to predict the output variables of the synthetic ammonia process. The RF technique is used to select the principal input variables to increase the computational efficiency and the generalization ability of the network. A self-attention mechanism is used to assign biased weights to the data of the key feature variables. A TCN-Transformer network with encoding and decoding techniques is first designed to enhance the correlation of information between variable data, which can extract features of input variables and achieve dynamic modeling of multivariate feature sequences. The network is optimized using a multihead attention mechanism, and the key features are enhanced by probabilistic weight assignment to improve the prediction accuracy. Finally, by comparing with existing methods, the merit and applicability of the proposed network, R 2 = 0.8233, RMSE = 0.0032, and MAE = 0.0024, are verified for predicting the key output of carbon monoxide using offline data generated.

LabVIEW Venus Flytrap ANFIS Inverse Control System for Microwave Heating Cavity

Growing interests in nature-inspired computing and bio-inspired optimization techniques have led to powerful tools for solving learning problems and analyzing large datasets. Several methods have been utilized to create superior performance-based optimization algorithms. However, certain applications, like nonlinear real-time, are difficult to explain using accurate mathematical models. Such large-scale combination and highly nonlinear modeling problems are solved by usage of soft computing techniques. So, in this paper, the researchers have tried to incorporate one of the most advanced plant algorithms known as Venus Flytrap Plant algorithm (VFO) along with soft-computing techniques and, to be specific, the ANFIS inverse model-Adaptive Neural Fuzzy Inference System for controlling the real-time temperature of a microwave cavity that heats oil. The MATLAB was integrated successfully with the LabVIEW platform. Wide ranges of input and output variables were experimented with. Problems were encountered due to heating system conditions like reflected power, variations in oil temperature, and oil inlet absorption and cavity temperatures affecting the oil temperature, besides the temperature's effect on viscosity. The LabVIEW design followed and the results figure in the performance of the VFO- Inverse ANFIS controller.

Optimization of the green synthesis of gold nanorods using aqueous extract of peeled sour guava as a source of antioxidants.

Obtaining gold nanorods (AuNRs) through biosynthesis is an alternative that replaces the traditional use of ascorbic acid with chemical compounds such as polyphenols, owing to their notable antioxidant properties. Therefore, we developed an AuNR biosynthesis method using an aqueous extract of sour guava (Psidium araca). Initially, a study was conducted to determine the antioxidant capacity of different parts of the fruit (pulp and peel) over 14 days. Four colorimetric techniques were used: total phenol, ABTS (2,2-azino-bis-3-ethylbenzothiazoline-6-sulphonic acid), FRAP (ferric reducing antioxidant power (FRAP), and DPPH (1,1-diphenyl-2-picrylhydrazyl). Subsequently, in stage 2, the selected aqueous extract was used, and two response surface designs were performed. The objective of this study was to find a model equation that would indicate the optimal parameters for obtaining AuNRs with a surface plasmon band at 808 nm, with possible applications in the health field. The results of the antioxidant capacity experiments were analyzed in Minitab® using a multilevel factorial design, and the peel exhibited the highest antioxidant capacity. Subsequently, the biosynthesis of AuNRs proceeded using a 5-factor response surface experimental design as input variables (concentration in mM of gold, silver, extract, NaBH4, and reaction time in hours) and longitudinal plasmon (LSPR) as output variables. The AuNRs were approximately 30 nm in size with an LSPR between 700 and 800 nm. Statistical model evaluation revealed a dependence between gold and time and gold-silver factors. Finally, antioxidant capacity was used to select the part (peel or pulp) of sour guava that could be used as a weak reducing agent. Moreover, the utility of surface-response methodology was explored to optimize the synthesis of AuNRs using green agents.

Multiobjective energy management of multi-source offshore parks assisted with hybrid battery and hydrogen/fuel-cell energy storage systems

With the recent advancements in the development of hybrid offshore parks and the expected large-scale implementation of them in the near future, it becomes paramount to investigate proper energy management strategies to improve the integrability of these parks into the power systems. This paper addresses a multiobjective energy management approach using a hybrid energy storage system comprising batteries and hydrogen/fuel-cell systems applied to multi-source wind-wave and wind-solar offshore parks to maximize the delivered energy while minimizing the variations of the power output. To find the solution of the optimization problem defined for energy management, a strategy is proposed based on the examination of a set of weighting factors to form the Pareto front while the problem associated with each of them is assessed in a mixed-integer linear programming framework. Subsequently, fuzzy decision making is applied to select the final solution among the ones existing in the Pareto front. The studies are implemented in different locations considering scenarios for electrical system limitation and the place of the storage units. According to the results, applying the proposed multiobjective framework successfully addresses the enhancement of energy delivery and the decrease in power output fluctuations in the hybrid offshore parks across all scenarios of electrical system limitation and combinational storage locations. Based on the results, in addition to the increase in delivered energy, a decrease in power variations by around 40 % up to over 80 % is observed in the studied cases.

Neuromuscular Performance and the Intensity of External Training Load During the Preseason in National Collegiate Athletic Association Division I Men's Collegiate Basketball Players.

Curtis, M, Kupperman, N, Westbrook, J, Weltman, AL, Hart, J, and Hertel, J. Neuromuscular performance and the intensity of external training load during the preseason in National Collegiate Athletic Association Division I men's collegiate basketball players. J Strength Cond Res 39(1): 54-61, 2025-The aim of the study was to determine whether acute changes in neuromuscular performance can be detected through countermovement jumps (CMJs) conducted pre- and postpractice sessions in conditions of high or low intensity measured by microsensors technology. Using an observational repeated measures design, data were collected from 10 male collegiate basketball players. Countermovement jump data were collected before and after practice exposures over 4 weeks of preseason. Select CMJ kinetics were compared in conditions of high and low training load intensity to detect neuromuscular performance changes in displacement of the center of mass and kinetics. Kinetic measures were categorized as output, underpinning, and strategy-related variables. We investigated "output" defined as displacement (jump height [JH]), "underpinning" defined as force-related (mean eccentric force, mean concentric force, force at zero velocity), and "strategy" defined as time-related (countermovement depth [CMD], eccentric duration (EccDur), concentric duration [ConcDur]) variables. There were significant condition × time interactions in CMJ variables namely eccentric mean force (EccForce), force at zero velocity (Force@0), CMDepth, EccDur, and ConcDur. In conditions of high intensity, players had significant, but small decreases in EccForce and Force@0, with small increases in CMD, EccDur, and ConDur, respectively. However, there were no significant decreases in JH. High-intensity practice exposures did not impact neuromuscular performance specific to "output," suggesting that collegiate basketball athletes can maintain JH despite alterations in "underpinning" and "strategy-related" variables. This could have relevance in understanding how fatigue associated with higher-intensity training exposures may potentially alter jump strategy and force production capacities due to external load intensity in collegiate basketball athletes.

Theoretical model of honing force in bore honing

Honing force is one of the key output variables to evaluate the machining performance of the honing process. However, the measurement of honing force during small-bore honing is difficult. The research on and modeling of honing force can help analyze the mechanism of material removal in the honing process, control the material removal rate, and improve the shape accuracy of the workpiece hole after honing. Recent research on the modeling of single-stone honing tools does not reflect reality well. In this study, a model to predict the honing force of a force-controlled, single-stone honing tool is built. The model is established through a mechanical analysis of the honing tool. This study is the first to propose that the initial shape of the workpiece bore considerably affects honing force due to the self-locking effect of honing tool. The model is verified by experiments, and the honing force predicted by the model fits the measured honing force well. The model can be applied to different sizes of single- or multi-stone tools with the same working principle and therefore has a wide range of applicability. It can guide the selection of honing parameters. Moreover, it can help build a more realistic-fitting model for the prediction of the material removal distribution and is crucial to improving the shape accuracy of the bore.

Evaluation of the IMTAQ Religious Development Program Using SEM Approach in Asahan Regency

&lt;p class="Default"&gt;&lt;span lang="IN"&gt;The IMTAQ program, implemented by the Asahan Regency Government since 2011, aims to shape community character based on religious values. This study evaluates its effectiveness by analyzing input variables (socialization, training, funding, information media, technical guidelines, human resources, facilities, and implementing organizations), process variables (fund allocation, monitoring, administration, financial management, workshops), and output variables (internalization of IMTAQ values, preservation of Islamic cultural arts, Quranic development). Involving 552 participants from various community sectors, the findings highlight that information media, financial administration, and facilities are key success factors, with Quranic development and cultural preservation as main indicators. Using Structural Equation Modeling (SEM), the evaluation revealed an 11% annual improvement in implementation. The results provide guidance for optimizing the program’s Management Information System (MIS), including human resources, technology, data, and communication networks.&lt;/span&gt;&lt;/p&gt;

Low carbon economic dispatch for virtual power plant considering energy storage

ABSTRACT Virtual power plant (VPP) amalgamates diverse distributed resources, thereby unlocking the full potential of distributed energy’s dispatch capabilities. Energy storage is an effective means to address the uncertainty of renewable energy and achieve energy complementarity. This study meticulously evaluates the finite nature of traditional energy within VPP, the unpredictability associated with renewable energy outputs, and the constraints faced by energy storage devices. It introduces strategic operational frameworks for VPP through cooperation between VPP operator and energy storage provider managing new type of electric energy storage systems. With the dual objectives of amplifying the economic gains for VPP operator and maximizing benefits for energy storage provider, this research formulates a VPP economic low-carbon dispatch model, guided by a carbon tax framework. The improved particle swarm optimization algorithm is used to solve the proposed dispatch model. The numerical results confirmed that the collaboration between the VPP operator and the energy storage provider mitigates the issues caused by the variability of renewable energy outputs on the VPP, resulting in a mutually beneficial scenario for both the operator and the storage provider. Additionally, carbon emissions have been drastically decreased in response to low carbon targets.

Internal model control based sliding mode controller design for unstable second order delayed processes with a case study on CSTR

Controlling the unstable processes is challenging since one or more poles are located on the right side of the s-plane. The existence of dead time in these systems makes control much more difficult. In this paper, internal model control based sliding mode control has been proposed for the control of unstable processes with dead time. Two sliding surfaces based on PID and PIDPI are used to design of the proposed controller. The parameters of continuous and discontinuous control law are obtained using differential evolution optimization technique. An objective function is constituted in terms of performance measure (integral absolute error) and control effort measure (total variation of controller output). Illustrative examples demonstrate the superiority of the proposed controller over earlier reported work in this realm, especially in terms of load disturbance rejection. A case study on temperature management of a continuous stirred tank reactor during an irreversible exothermic process also serves to highlight the applicability of the proposed system. Furthermore, robustness of the proposed controller is also investigated by inclusion of perturbations in the parameters. The obtained results clearly show how well the suggested controller works.