Output Variables Research Articles

Assessing key parameters in simultaneous simulation of rapid kinetics of chlorophyll a fluorescence and trans-thylakoid electric potential difference.

Our study attempts to address the following questions: among numerous photosynthetic modules, which parameters notably influence the rapid chlorophyll fluorescence (ChlF) rise, the so-called O-J-I-P transient, in conjunction with the P515 signal, as these two records are easily obtained and widely used in photosynthesis research, and how are these parameters ranked in terms of their importance? These questions might be difficult to answer solely through experimental assays. Therefore, we employed an established photosynthesis model. Firstly, we utilized the model to simulate the measured rapid ChlF rise and P515 kinetics simultaneously. Secondly, we employed the sensitivity analysis (SA) tool by randomly altering model parameters to observe their effects on model output variables. Thirdly, we systematically identified significant parameters for both or one of the kinetics across various scenarios. A novel aspect of our study is the application of the Morris method, a global SA tool, to simultaneously assess the significance of model parameters in shaping both or one of the kinetics. The Morris SA technique enables the quantification of how much a specific parameter affects O-J-I-P transient during particular time intervals (e.g., J, I, and P steps). This allowed us to theoretically analyze which step is more significantly influenced by the parameter. In summary, our study contributes to the field by providing a comprehensive analysis of photosynthesis kinetics and emphasizing the importance of parameter selection in modelling this process. These findings can inform future research efforts aimed at improving photosynthesis models and advancing our understanding of photosynthetic processes.

Development of a System for Predicting Hospitalization Time for Patients With Traumatic Brain Injury Based on Machine Learning Algorithms: User-Centered Design Case Study.

Currently, the treatment and care of patients with traumatic brain injury (TBI) are intractable health problems worldwide and greatly increase the medical burden in society. However, machine learning-based algorithms and the use of a large amount of data accumulated in the clinic in the past can predict the hospitalization time of patients with brain injury in advance, so as to design a reasonable arrangement of resources and effectively reduce the medical burden of society. Especially in China, where medical resources are so tight, this method has important application value. We aimed to develop a system based on a machine learning model for predicting the length of hospitalization of patients with TBI, which is available to patients, nurses, and physicians. We collected information on 1128 patients who received treatment at the Neurosurgery Center of the Second Affiliated Hospital of Anhui Medical University from May 2017 to May 2022, and we trained and tested the machine learning model using 5 cross-validations to avoid overfitting; 28 types of independent variables were used as input variables in the machine learning model, and the length of hospitalization was used as the output variables. Once the models were trained, we obtained the error and goodness of fit (R2) of each machine learning model from the 5 rounds of cross-validation and compared them to select the best predictive model to be encapsulated in the developed system. In addition, we externally tested the models using clinical data related to patients treated at the First Affiliated Hospital of Anhui Medical University from June 2021 to February 2022. Six machine learning models were built, including support vector regression machine, convolutional neural network, back propagation neural network, random forest, logistic regression, and multilayer perceptron. Among them, the support vector regression has the smallest error of 10.22% on the test set, the highest goodness of fit of 90.4%, and all performances are the best among the 6 models. In addition, we used external datasets to verify the experimental results of these 6 models in order to avoid experimental chance, and the support vector regression machine eventually performed the best in the external datasets. Therefore, we chose to encapsulate the support vector regression machine into our system for predicting the length of stay of patients with traumatic brain trauma. Finally, we made the developed system available to patients, nurses, and physicians, and the satisfaction questionnaire showed that patients, nurses, and physicians agreed that the system was effective in providing clinical decisions to help patients, nurses, and physicians. This study shows that the support vector regression machine model developed using machine learning methods can accurately predict the length of hospitalization of patients with TBI, and the developed prediction system has strong clinical use.

Development of a fuzzy logic-based model for assessing the reliability of relay protection systems

This article presents a reliability assessment model for relay protection devices using fuzzy logic. It introduces an algorithm for simulating these devices, employing the Mamdani model with an "if-then" rule base. Inputs include the percentage of correct operation and the frequency of correct and incorrect operations. Implemented in Matlab with 21 rules, the fuzzy logic model uses triangular membership functions for input and output variables, with defuzzification via the center of gravity method. The model was tested using statistical data from SIEMENS SIPROTEC terminals, specifically distance protection and differential protection devices for transformers and autotransformers. The assessment considers operation frequencies for 1 to 3 devices, combining statistical and simulation data for a comprehensive analysis. Results show that including operation frequencies improves evaluation accuracy. The proposed model not only assesses current reliability but also predicts future behavior, aiding in the planning and optimization of relay protection systems. This model is valuable for professionals in generating companies, grid organizations, and operational dispatch control entities, helping them analyze relay protection performance and develop strategies to ensure reliable operation. The research focuses on the reliability of relay protection devices in power systems, addressing the need for a more accurate and comprehensive evaluation method. Traditional methods may not fully account for the complexities in modern microprocessor-based protections. This study aims to enhance reliability assessments through a model that integrates statistical data and simulation techniques, ultimately supporting better planning and optimization of relay protection systems

Robust batch-to-batch optimization with global sensitivity analysis for microbial fermentation processes under model-plant mismatch

This paper studies the optimization of product yield for the microbial fermentation process in the presence of model-plant mismatch. The typical “two-step” optimization method involves modifying the model by adjusting its parameters and subsequently utilizing the updated model to optimize product output. However, due to estimability and overfitting problems, it is often impractical to update all available parameters. Therefore, we propose a robust batch-to-batch optimization method with global sensitivity analysis. First, the parameters to be identified are determined through global sensitivity analysis. Then, the robust batch-batch optimization method is employed to optimize the yield of fermentation products. Compared with previous parameter selection methods, global sensitivity analysis considers the complex correlation between parameters, allowing for a more comprehensive evaluation of the impact of multiple parameters and their interactions on the model. Furthermore, compared with previous studies, the robust batch-to-batch optimization method assigns weights to each variable in the identification objective function based on experience and model output variance, significantly reducing the uncertainty of the next optimal batch run. Simultaneously, the method is robust to the uncertainty in initial conditions, ensuring a more stable process when running in large batches. A penicillin fermentation case study verifies the convergence and robustness of the method.

Synthesis and characterization of Fe(III)-doped beta-cyclodextrin-grafted chitosan cryogel beads for adsorption of diclofenac in aqueous solutions: Adsorption experiments and deep-learning modeling

Diclofenac (DCF) is frequently detected in aquatic environments, emphasizing the critical need for its efficient removal globally. Here, we present the synthesis of Fe(III)-doped β-CD-grafted chitosan (Fe/β-CD@CS) cryogel beads designed for adsorbing DCF in aqueous solutions. The beads exhibited an average size of 2.94 ± 0.66 mm and a point of zero charge of 8.03. Adsorption experiments demonstrated that the Langmuir kinetic model provided the most accurate description of the kinetic data, while the Redlich–Peterson isotherm offered the best fit for the equilibrium data. The beads showcased a theoretical maximum adsorption capacity of 712.3 mg/g for DCF, with the adsorption process being identified as exothermic. DCF adsorption on the beads was attributed to hydrogen bonding, metal cation-π interactions, and electrostatic interactions. Reusability tests exhibited that the beads could be regenerated using 0.1 M NaOH. To perform deep learning modeling, adsorption experiments (n = 17), designed utilizing central composite design (CCD), were conducted in duplicate. The CCD framework incorporated input variables such as initial DCF concentration, adsorbent dosage, and solution pH, while the output variable was the DCF removal rate. Utilizing the adsorption data, an artificial neural network (ANN) model was constructed with a topology of 3: 7:10:1, featuring 3 input variables, 7 neurons in the first hidden layer, 10 neurons in the second layer, and 1 output variable. Employing the ANN model data, 3-D response surface plots were generated to elucidate the relationship between input variables and DCF removal rate. Additional adsorption tests were conducted to evaluate the developed ANN model, affirming its reliable predictability for the DCF removal rate. Analysis of the relative importance of the input variables revealed the following order of importance: solution pH (100 %) > adsorbent dosage (75.2 %) > initial DCF concentration (57.7 %).

Accurate Prediction of Compression Index of Normally Consolidated Soils Using Artificial Neural Networks

The compression index (Cc) serves as a crucial parameter in predicting consolidation settlement in fine-grained soils, representing the slope of the void ratio logarithmic effective stress curve obtained from oedometer tests. However, traditional consolidation testing methods are notably time-consuming, typically spanning a 15-day period for preparation, execution, and parameter calculation, leading to significant delays in civil engineering projects. Therefore, there is an urgent need for effective methodologies to determine consolidation parameters within a shorter timeframe. Although various empirical formulas have been proposed over the years to correlate compressibility with soil parameters, none have reliably predicted the Cc across different datasets. In this study, to overcome this challenge, an alternative approach using artificial neural network (ANN) methodology to predict the compression index of fine-grained soils based on index properties is proposed. For this purpose, an ANN was trained and validated using a dataset consisting of 560 high and low- plasticity soil samples obtained from construction sites in various regions of Turkey over the last forty years, as well as soil borings in Istanbul. The modeling of artificial neural networks was performed using the Regression Learner program, which integrates with the Matlab 2023a software package and offers a user-friendly graphical interface for AI model development without coding. The data set, which was structured as a matrix with dimensions of 458 × 6, included input parameters such as the natural water content, liquid limit, plastic limit, plastic index and initial void ratio, as well as information on the compression index, which was the output variable. The developed ANN model showed an outstanding predictive performance when predicting the output of the test data, achieving an outstanding R2 score of 0.81. This underlines the potential of ANN methodologies to efficiently extract important data with fewer experiments and in less time, and offers promising applications in the field of geotechnical engineering.

Smart Grid Technologies: Advancements and Applications in Nigeria

This study explores the impact of smart grid technologies on the modernization of power grids in response to evolving energy demands and the integration of renewable energy sources in Nigeria. It aims to empirically assess advancements in smart grid technologies, focusing on four key objectives: eval_uating the impact of smart meters on energy consumption and peak demand reduction, analyzing the effectiveness of Advanced Distribution Management Systems (ADMS) in enhancing grid reliability and efficiency, assessing the role of demand response programs in balancing supply and demand, and examining the integration and management of Distributed Energy Resources (DERs) within smart grids. The research employs a quantitative methodology, collecting and analyzing data from utility companies that have implemented smart grid technologies. Key findings reveal that smart meters significantly reduce energy consumption and peak demand by providing real-time monitoring, while ADMS improves grid reliability and operational efficiency through enhanced fault detection and automated control. Demand response programs effectively balance energy supply and demand, reducing peak loads and energy costs. The integration of DERs increases renewable energy utilization and grid stability but also presents challenges related to variability in power output and management complexity. The study concludes that smart grid technologies play a crucial role in achieving a more resilient and efficient power grid, though addressing challenges related to DER integration and system management is essential for maximizing their benefits.

Breeding phenology drives variation in reproductive output, reproductive costs and offspring fitness in a viviparous ectotherm.

Phenological advances are a widespread response to global warming and can contribute to determine the climate vulnerability of organisms, particularly in ectothermic species which are highly dependent on ambient temperatures to complete their life cycle. Yet, the relative contribution of breeding dates and temperature conditions during gestation on fitness of females and their offspring is poorly documented in reptiles. Here, we exposed females of the common lizard Zootoca vivipara to contrasting thermal scenarios (cold versus hot treatment) during gestation and quantified effects of parturition dates and thermal treatment on life-history traits of females and their offspring for one year. Overall, our results suggest that parturition date has a greater impact than thermal conditions during gestation on life history strategies. In particular, we found positive effects of an earlier parturition date on juvenile survival, growth and recruitment suggesting that environmental dependent selection and/or differences in parental quality between early and late breeders underlie seasonal changes in offspring fitness. Yet, an earlier parturition date compromised the energetic condition of gravid females, which suggests the existence of a mother-offspring conflict regarding the optimisation of parturition dates. While numerous studies focused on the direct effects of alterations in incubation temperatures on reptile life-history traits, our results highlight the importance of considering the role of breeding phenology in assessing the short- and long-term effects of thermal developmental plasticity.

Generative models for synthetic data generation: application to pharmacokinetic/pharmacodynamic data.

The generation of synthetic patient data that reflect the statistical properties of real data plays a fundamental role in today's world because of its potential to (i) be enable proprietary data access for statistical and research purposes and (ii) increase available data (e.g., in low-density regions-i.e., for patients with under-represented characteristics). Generative methods employ a family of solutions for generating synthetic data. The objective of this research is to benchmark numerous state-of-the-art deep-learning generative methods across different scenarios and clinical datasets comprising patient covariates and several pharmacokinetic/pharmacodynamic endpoints. We did this by implementing various probabilistic models aimed at generating synthetic data, such as the Multi-layer Perceptron Conditioning Generative Adversarial Neural Network (MLP cGAN), Time-series Generative Adversarial Networks (TimeGAN), and a more traditional approach like Probabilistic Autoregressive (PAR). We evaluated their performance by calculating discriminative and predictive scores. Furthermore, we conducted comparisons between the distributions of real and synthetic data using Kolmogorov-Smirnov and Chi-square statistical tests, focusing respectively on covariate and output variables of the models. Lastly, we employed pharmacometrics-related metric to enhance interpretation of our results specific to our investigated scenarios. Results indicate that multi-layer perceptron-based conditional generative adversarial networks (MLP cGAN) exhibit the best overall performance for most of the considered metrics. This work highlights the opportunities to employ synthetic data generation in the field of clinical pharmacology for augmentation and sharing of proprietary data across institutions.

Decision Tree Regression vs. Gradient Boosting Regressor Models for the Prediction of Hygroscopic Properties of Borassus Fruit Fiber

This research focuses on the environmental-friendly production of Borassus fruit fibers (BNF), its characterization, and hygroscopic properties determination via Dynamic Vapor Sorption (DVS). The experimental results obtained from the hygroscopic behavior analysis were used to create a primary dataset to train and test Decision Tree Regression (DTR) and Gradient Boosting Regressor (GBR) models. The created primary dataset comprised 294 observations, from which 80% were used to train the models, and the remaining 20% were used for the testing of the two models. The models exhibited high accuracy, easy interpretability on the small-size dataset, and flexibility with regards to the nature of the relationship between the input and output variable. Both models successfully predicted the hygroscopic behavior with the Gradient Boosting Regressor outperforming Decision Tree Regression by indicating values of 0.012, 0.109, 0.059, and 0.999 for MSE, RMSE, MAE, and R2, respectively, during the desorption of the BNF, and values of 0.012, 0.109, 0.059, and 0.999 for MSE, RMSE, MAE, and R2, respectively, during the desorption of the BNF. This suggests that the Gradient Boosting Regressor illustrated the maximum accuracy. The outcomes can be utilized to provide an alternative for traditional methods, which can often be costly and time-consuming by improving the engineering properties of BNF. The models can be used in the construction sector to lower costs as they are able to pinpoint elements influencing the characteristics for specific applications to grasp its various properties through the prediction of its hygroscopic properties.

Control approach to well-posedness and asymptotic behavior of a queueing system

In this paper, we investigate well-posedness and asymptotic behavior of an M/G/1 retrial queueing system characterized by reserved idle time and setup time. This system is intricately described by an infinite system of integro-partial differential equations. Our methodology is rooted in the feedback theory of well-posed and regular infinite-dimensional linear systems. Firstly, we convert the system into a control framework, incorporating both input and output variables. Subsequently, we establish its well-posedness by leveraging the feedback theory specific to regular infinite-dimensional linear systems. Secondly, by scrutinizing the spectral distribution of the system operator along the imaginary axis, we demonstrate that the time-evolving solution of the system converges robustly to its steady-state solution. Lastly, we also discuss the essential properties of the semigroup induced by the system operator, encompassing stability and hyperbolicity, thereby shedding light on its regularity.

Modeling and design optimization of the performance of stone matrix asphalt mixtures containing low-density polyethylene and waste engine oil using the response surface methodology

In recent years, the use of waste plastic materials such as low-density polyethylene (LDPE) to modify asphalt binders and enhance mixture performance has garnered significant attention. One major concern with using such materials is the higher production temperature required, which necessitates the use of a bitumen extender agent, such as waste engine oil (WEO), to reduce the viscosity and mixing temperature. Therefore, using these stabilizing additives can reduce the consumption of virgin binder, especially for Stone Matrix Asphalt (SMA) mixtures, which require higher asphalt content. This study aimed to optimize the design of SMA modified by LDPE and WEO to minimize the optimum asphalt content (OAC) and mixing temperature while maximizing SMA performance. To achieve this, Response Surface Methodology (RSM) was utilized to develop the necessary models for optimizing design and predicting performance. The selected independent variables (factors) for the design include LDPE content, WEO content, OAC, and mixing temperature. Meanwhile, the responses (dependent variables) consist of Marshall stability, rut depth, tensile strength ratio, and resilient modulus, which were used to determine the best mix design. The findings demonstrated that the suggested models for the output variables can predict performance with a higher level of confidence. The Analysis of variance (ANOVA) demonstrated that predictive models were significant and well-fitted, with a coefficient of determination (R2) of higher than 0.80, an adequate precision value of greater than 4, and a low p-value (less than 0.05). The error percentage between the RSM-predicted and actual values was less than 5 %, indicating that RSM-established models can accurately and efficiently predict the SMA performance. The best mix design of the SMA mixture modified by LDPE and WEO was found to be 10 % LDPE, 3.91 % WEO, 5.92 % OAC, and mixing temperature of 152.24°C with a combined desirability of 82.8 %.

Prediction of secondary metabolites in maize under different nitrogen inputs by hyperspectral sensing and machine learning

Flavonoids are compounds resulting from secondary plant metabolism that provide benefits to human health by food. This study aimed to accuracy of predicting flavonoids in maize plants subjected to different nitrogen rates using hyperspectral reflectance and machine learning (ML) algorithms. The experiment was carried out in randomized blocks in a 4 × 5 factorial design (four N inputs: 0; 30; 60 and 120 % of the recommended N input; and five readings of the reflectance spectra in maize leaves from different vegetative stages: V6, V8, V10, V12 and V14, in four replications, totaling 80 treatments. N rates were applied in the V4 and V8 phenological stages, using urea as the N source. For hyperspectral analysis, four leaves from each treatment were collected and analyzed using a spectroradiometer (FieldSpec 4 HRes, Analytical Spectral Devices), capturing the spectrum in the 350 to 2500 nm range. Subsequently, the leaf samples used in the reflectance readings were dried, ground and subjected to isoflavone quantification, analyzed by ultra-performance liquid chromatography in three repetitions, quantifying daidzein 1 (D1), daidzein 2 (D2), genistein 1 (G1), genistein 2 (G2), and total isoflavones. Data obtained was subjected to machine learning analysis, testing two data set input configurations: wavelengths (WL) and calculated spectral bands (B), and D1, D2, G1, G2 and total isoflavones as output variables. The ML algorithms tested were artificial neural networks (ANN), REPTree (DT), M5P decision tree (M5P), ZeroR (R), Random Forest (RF) and support vector machine (SVM), evaluated according to their performance by the correlation coefficient (r) and mean absolute error (MAE). The results show that the SVM algorithm had the highest accuracy in predicting the variables D1, D2, G1, G2 and total isoflavones, outperforming the other algorithms when WL was used as input in dataset.

Sensitivity analysis of models of gas exchange for lung hyperpolarised 129Xe MR.

Sensitivity analysis enables the identification of influential parameters and the optimisation of model composition. Such methods have not previously been applied systematically to models describing hyperpolarised 129Xe gas exchange in the lung. Here, we evaluate the current 129Xe gas exchange models to assess their precision for identifying alterations in pulmonary vascular function and lung microstructure. We assess sensitivity using established univariate methods and scatter plots for parameter interactions. We apply them to the model described by Patz et al and the Model of Xenon Exchange (MOXE), examining their ability to measure: i) importance (rank), ii) temporal dependence and iii) interaction effects of each parameter across healthy and diseased ranges. The univariate methods and scatter plot analyses demonstrate consistently similar results for the importance of parameters common to both models evaluated. Alveolar surface area to volume ratio is identified as the parameter to which model signals are most sensitive. The alveolar-capillary barrier thickness is identified as a low-sensitivity parameter for the MOXE model. An acquisition window of at least 200 ms effectively demonstrates model sensitivity to most parameters. Scatter plots reveal interaction effects in both models, impacting output variability and sensitivity. Our sensitivity analysis ranks the parameters within the model described by Patz et al and within the MOXE model. The MOXE model shows low sensitivity to alveolar-capillary barrier thickness, highlighting the need for designing acquisition protocols optimised for the measurement of this parameter. The presence of parameter interaction effects highlights the requirement for care in interpreting model outputs.

Machine learning predict the degradation efficiency of aqueous refractory organic pollutants by ultrasound-based advanced oxidation processes

Ultrasound based advanced oxidation processes (AOPs) are effective for removing refractory organic pollutants by generating reactive species. Machine learning (ML) can systematically provide an excellent opportunity to determine the relationship between feature variables and output variables through large amounts of data, thereby reducing the need for experimental measurements. In this study, a ML approach was applied for the first time to predict the degradation efficiency of aqueous refractory organic pollutants by ultrasound-based AOPs. The obtained dataset was normalized and introduced into four ML models. Among them, Random Forest Regressor and XGB Regressor models had the best fit with 0.9546 and 0.9749 for training set R2 and 0.9548 and 0.9740 for test set R2, respectively. Relative importance analysis and SHAP analysis showed that catalyst type, oxidant concentration, reaction time, and catalyst dosage are the important variables affecting the degradation efficiency of refractory organic pollutants. In addition, excessive ultrasonic intensity, ultrasonic frequency, oxidant concentration, and catalyst dosage had little effect on the increase of degradation efficiency. Based on the descriptive data analysis, high degradation efficiency was obtained with ultrasonic intensity of 2 W·mL−1, ultrasonic frequency of 20–40 kHz, reaction time of 60–90 min, pH 3–7, oxidant concentration of ∼7.5 mmol·L−1, and catalyst dosage of >0.4 g·L−1. This work demonstrated a new predictive method to understand the comprehensive influence of operative factors on degradation efficiency in US-based AOPs, guiding parameter and process optimization.

An assessment methodology for the flexibility capacity of new power system based on two-stage robust optimization

The inherent variability in wind and solar power output presents a significant challenge to the flexibility balance of power systems. This paper introduces an innovative method for evaluating the flexibility capacity of a new power system, employing a two-stage robust optimization approach. Firstly, a power system flexibility supply and demand balance mechanism model is constructed and quantitatively characterized for the power system flexibility shortfalls set. Subsequently, taking into account timescale characteristics and directionality, the time series production simulation technique is applied to establish the effective ramping and flexibility supply distribution model of thermal power and energy storage units, enabling an analysis of the power system's supply regulation capabilities. On this basis, a power system flexibility capacity assessment method is proposed, which divides the system regulation resources into demand set and supply set, and constructs a power system flexibility capacity assessment model to ensure that the maximum system flexibility margin and the lowest operating cost are taken as the optimization objectives under the system security operation constraints. The column and constraint generation (C&CG) robust optimization algorithm is used to decompose the master problem and the max-min dual-layer subproblems for iterative solving, and the optimal capacity of each unit of the system in terms of output and flexibility is derived. Finally, the effectiveness and superiority of the proposed method is verified through case analysis, which shows that the method can improve the flexibility capacity by 14.9% and reduce the operating cost by 15.83% compared with the traditional proportional allocation method.

Recursive identification of kernel-based hammerstein model for online energy efficiency estimation of large-scale chemical plants

Accurate energy efficiency prediction is crucial for decision-making in large-scale chemical production, especially considering energy management and environmental concerns. The complexity of chemical processes, characterized by strong nonlinearities, dynamics, and uncertainties, challenges traditional prediction methods. This paper introduces KHSM (Kernel-based Hammerstein Subspace Model), which models nonlinear static and linear dynamic processes in series by embedding kernel function-based nonlinear mapping into subspace modeling for energy efficiency estimation. KHSM identifies nonlinear process models without explicit nonlinear mapping functions, constructing dynamic models that encompass both energy input and product output variables. An adaptive KHSM variant dynamically updates the energy efficiency model, improving accuracy by iteratively selecting and excluding samples. Comparative analysis shows KHSM outperforms existing methods, achieving a coefficient of determination (R2) closest to 1 and reducing the root-mean-square error (RMSE) by up to an order of magnitude, with the smallest mean and standard deviation. Additionally, modeling efficiency increases by an order of magnitude. The developed model enables ongoing energy efficiency estimation and proactive identification of efficiency trends. Validation through mathematical and real-world ethylene process cases demonstrates KHSM's efficacy and applicability. These estimates facilitate informed adjustments to energy management strategies and optimization of production approaches in energy-intensive chemical processes.

A Gaussian process embedded feature selection method based on automatic relevance determination

In Gaussian Process, feature importance is inversely proportional to the corresponding length scale when applying the Automatic Relevance Determination (ARD) structured kernel function. Features can be selected by ranking them according to their importance. Among the ARD-based feature selection methods, no uniform score exists for quantifying the output variation explained by feature subsets. This study proposes two feature selection approaches using two cumulative feature importance scores, one titled derivative decomposition ratio and the other normalized sensitivity, to determine the optimal feature subset. The performance of the approaches is assessed to test if irrelevant features are accurately identified and if the feature rankings are correct. The approaches are applied to identify relevant dimensionless inputs for a hybrid model estimating liquid entrainment fraction in two-phase flow. The results reveal that the proposed methods can identify the optimal feature subset for the hybrid model without significantly worsening its Root Mean Squared Error.

Artificial Intelligence Advancements for Accurate Groundwater Level Modelling: An Updated Synthesis and Review

Artificial Intelligence (AI) methods, including Artificial Neural Networks (ANNs), Adaptive Neuro-Fuzzy Inference Systems (ANFISs), Support Vector Machines (SVMs), Deep Learning (DL), Genetic Programming (GP) and Hybrid Algorithms, have proven to be important tools for accurate groundwater level (GWL) modelling. Through an analysis of the results obtained in numerous articles published in high-impact journals during 2001–2023, this comprehensive review examines each method’s capabilities, their combinations, and critical considerations about selecting appropriate input parameters, using optimisation algorithms, and considering the natural physical conditions of the territories under investigation to improve the models’ accuracy. For example, ANN takes advantage of its ability to recognise complex patterns and non-linear relationships between input and output variables. In addition, ANFIS shows potential in processing diverse environmental data and offers higher accuracy than alternative methods such as ANN, SVM, and GP. SVM excels at efficiently modelling complex relationships and heterogeneous data. Meanwhile, DL methods, such as Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNNs), are crucial in improving prediction accuracy at different temporal and spatial scales. GP methods have also shown promise in modelling complex and nonlinear relationships in groundwater data, providing more accurate and reliable predictions when combined with optimisation techniques and uncertainty analysis. Therefore, integrating these methods and optimisation techniques (Hybrid Algorithms), tailored to specific hydrological and hydrogeological conditions, can significantly increase the predictive capability of GWL models and improve the planning and management of water resources. These findings emphasise the importance of thoroughly understanding (a priori) the functionalities and capabilities of each potentially beneficial AI-based methodology, along with the knowledge of the physical characteristics of the territory under investigation, to optimise GWL predictive models.

Hardware in the loop testing of converter control in solar PV and BESS based islanded microgrid

Over the past decades, microgrids have garnered significant attention due to their ability to offer resilient power supply and efficiently integrate renewable energy sources (RESs). The test model includes an islanded microgrid having common voltage source converter for solar photovoltaic and battery energy storage system, characterized by low inertia. To minimize the effect of reduced inertia caused by lack of synchronous generators and also to cope up with the variation in power output from different renewable energy sources, an adaptive virtual inertia and damping based control, is incorporated through voltage source converter control, utilizing swing equation of the synchronous generator. However, it is imperative to verify the proposed control strategy before implementation in an actual plant. In that direction, this paper discusses the practicality of the proposed control in the real-time using Controller Hardware-in-the-Loop (CHIL) platform. So, the plant is built in real time simulator OP4512 and the proposed control is implemented using practical microcontroller TMS320F28379D. Subsequently, configuration and modelling of ADC and EPWM are explained. CHIL testing platform demonstrates flawless compatibility with the converter control, having a system model running in real time. Simulation results are compared with that of HIL results for various loading configurations, hence proving the efficacy of the proposed control strategy.