Feature Importance Analysis Research Articles

Machine-learning oxybarometer developed using zircon trace-element chemistry and its applications

Abstract Magmatic oxygen fugacity (fO2) is a fundamental property to understanding the long-term evolution of the Earth’s atmosphere and the formation of magmatic-hydrothermal mineral deposits. Classically, the magmatic fO2 is estimated using mineral chemistry, such as Fe-Ti oxides, zircon, and hornblende. These methods, however, are only valid within certain limits and/or require a significant amount of a priori knowledge. In this contribution, a new oxybarometer, constructed by data-driven machine learning algorithms using trace elements in zircon and their corresponding independent fO2 constraints, is provided. Seven different algorithms are initially trained and then validated on a data set that was never utilized in the training processes. Results suggest that the oxybarometer constructed by the extremely randomized trees model has the best performance, with the largest R2 value (0.91 ± 0.01), smallest RMSE (0.45 ± 0.03), and low propagated analytical error (~0.10 log units). Feature importance analysis demonstrates that U, Ti, Th, Ce, and Eu in zircon are the key trace elements that preserve fO2 information. This newly developed oxybarometer has been applied in diverse systems, including arc magmas and mid-ocean ridge basalts, fertile and barren porphyry systems, and global S-type detrital zircon, which provide fO2 constraints that are consistent with other independent methods, suggesting that it has wide applicability. To improve accessibility, the oxybarometer was developed into a software application aimed at enabling more consistent and reliable fO2 determinations in magmatic systems, promoting further research.

In-depth insight into the driving factors of the compressive strength development of MKPC based on interpretable machine learning methods

Magnesium potassium phosphate cement (MKPC) is a kind of Mg-chemically bonded phosphate ceramic commonly used for rapidly repairing dilapidated structures. In this study, a compressive strength dataset of MKPC was constructed, and four advanced machine learning (ML) algorithms (XGBoost, RF, GBDT and ANN) were selected to establish a high-precision compressive strength prediction model of MKPC. The SHAP and PDP methods are also used for interpretability analysis of ML-MKPC models. The XGBoost model has good generalizability and reliability while achieving high prediction accuracy. The RF and GBDT models performed similarly to the XGBoost model on the training set but performed poorly on the testing set. The ANN model is poorly trained on both the training and testing sets, with a risk of underfitting. The R2 of the XGBoost model at the different compressive strength stages still reaches above 0.80, indicating that it not only captures the complex relationships of the overall dataset well but also effectively predicts the staged strength dataset. Feature importance analysis revealed that the curing age (T), water-to-binder ratio (W/B), mineral admixtures-to-binder ratio (MA/B) and phosphate-to-magnesium ratio (P/M) are the principal variables affecting the compressive strength of MKPC. The partial interpretation shows that the optimum value range is determined when W/B is 0.10–0.18, MA/B is 0–0.20, P/M is 0.40–1.0, and R/M is 0–0.12. The composition of mineral admixtures with high-Ca, high-Si and low-Al systems seems to be more conducive to participating in the hydration reaction of MKPC. The ML-MKPC compressive strength prediction model developed in this study can provide theoretical support for the subsequent composition design and performance optimization of MKPC.

Cabin air dynamics: Unraveling the patterns and drivers of volatile organic compound distribution in vehicles.

Volatile organic compounds (VOCs) are ubiquitous in vehicle cabin environments, which can significantly impact the health of drivers and passengers, whereas quick and intelligent prediction methods are lacking. In this study, we firstly analyzed the variations of environmental parameters, VOC levels and potential sources inside a new car during 7 summer workdays, indicating that formaldehyde had the highest concentration and about one third of the measurements exceeded the standard limit for in-cabin air quality. Feature importance analysis reveals that the most important factor affecting in-cabin VOC emission behaviors is the material surface temperature rather than the air temperature. By introducing the attention mechanism and ensemble strategy, we present an LSTM-A-E deep learning model to predict the concentrations of 12 observed typical VOCs, together with other five deep learning models for comparison. By comparing the prediction-observation discrepancies and five evaluation metrics, the LSTM-A-E model demonstrates better performance, which is more consistent with field measurements. Extension of the developed model for predicting the 10-day VOC concentrations in a realistic residence further illustrates its excellent environmental adaptation. This study probes the not-well-explored in-cabin VOC dynamics via observation and deep learning approaches, facilitating rapid prediction and exposure assessment of VOCs in the vehicle micro-environment.

Application of Feature Engineering Techniques and Machine Learning Algorithms for Property Price Prediction

This research applies feature engineering techniques and machine learning algorithms to predict property prices using a dataset from Kaggle. Three models were implemented: Linear Regression, Decision Tree, and Random Forest. The Random Forest model demonstrated the best performance with an average Mean Absolute Error (MAE) of 16472.76, Mean Squared Error (MSE) of 457407807.78, and R-squared (R²) of 0.83. Key features influencing property prices were identified through feature importance analysis, providing valuable insights for enhancing property appraisals and investment decisions.

Sentiment Analysis on 'HelloTalk' App Reviews Using NRC Emotion Lexicon and GoEmotions Dataset

During the post-pandemic period, the interest in foreign language learning surged, leading to increased usage of language-learning apps. With the rising demand for these apps, analyzing app reviews becomes essential, as they provide valuable insights into user experiences and suggestions for improvement. This research focuses on extracting insights into users' opinions, sentiments, and overall satisfaction from reviews of HelloTalk, one of the most renowned language-learning apps. We employed topic modeling and emotion analysis approaches to analyze reviews collected from the Google Play Store. Several experiments were conducted to evaluate the performance of sentiment classification models with different settings. In addition, we identified dominant emotions and topics within the app reviews using feature importance analysis. The experimental results show that the Random Forest model with topics and emotions outperforms other approaches in accuracy, recall, and F1 score. The findings reveal that topics emphasizing language learning and community interactions, as well as the use of language learning tools and the learning experience, are prominent. Moreover, the emotions of 'admiration' and 'annoyance' emerge as significant factors across all models. This research highlights that incorporating emotion scores into the model and utilizing a broader range of emotion labels enhances model performance.

Comparative analysis of machine learning models for efficient low back pain prediction using demographic and lifestyle factors.

Low back pain (LBP) is one of the most frequently occurring musculoskeletal disorders, and factors such as lifestyle as well as individual characteristics are associated with LBP. The purpose of this study was to develop and compare efficient low back pain prediction models using easily obtainable demographic and lifestyle factors. Data from adult men and women aged 50 years or older collected from the Korean National Health and Nutrition Examination Survey (KNHANES) were used. The dataset included 22 predictor variables, including demographic, physical activity, occupational, and lifestyle factors. Four machine learning algorithms, including XGBoost, LGBM, CatBoost, and RandomForest, were used to develop predictive models. All models achieved an accuracy greater than 0.8, with the LGBM model outperforming the others with an accuracy of 0.830. The CatBoost model had the highest sensitivity (0.804), while the LGBM model showed the highest specificity (0.884) and F1-Score (0.821). Feature importance analysis revealed that EQ-5D was the most critical variable across all models. In this study, an efficient LBP prediction model was developed using easily accessible variables. Using this model, it may be helpful to identify the risk of LBP in advance or establish prevention strategies in subjects who have difficulty accessing medical facilities.

Factors, Prediction, and Explainability of Vehicle Accident Risk Due to Driving Behavior through Machine Learning: A Systematic Literature Review, 2013–2023

Road accidents are on the rise worldwide, causing 1.35 million deaths per year, thus encouraging the search for solutions. The promising proposal of autonomous vehicles stands out in this regard, although fully automated driving is still far from being an achievable reality. Therefore, efforts have focused on predicting and explaining the risk of accidents using real-time telematics data. This study aims to analyze the factors, machine learning algorithms, and explainability methods most used to assess the risk of vehicle accidents based on driving behavior. A systematic review of the literature produced between 2013 and July 2023 on factors, prediction algorithms, and explainability methods to predict the risk of traffic accidents was carried out. Factors were categorized into five domains, and the most commonly used predictive algorithms and explainability methods were determined. We selected 80 articles from journals indexed in the Web of Science and Scopus databases, identifying 115 factors within the domains of environment, traffic, vehicle, driver, and management, with speed and acceleration being the most extensively examined. Regarding machine learning advancements in accident risk prediction, we identified 22 base algorithms, with convolutional neural network and gradient boosting being the most commonly used. For explainability, we discovered six methods, with random forest being the predominant choice, particularly for feature importance analysis. This study categorizes the factors affecting road accident risk, presents key prediction algorithms, and outlines methods to explain the risk assessment based on driving behavior, taking vehicle weight into consideration.

Data-driven prediction of continuous renal replacement therapy survival

Continuous renal replacement therapy (CRRT) is a form of dialysis prescribed to severely ill patients who cannot tolerate regular hemodialysis. However, as the patients are typically very ill to begin with, there is always uncertainty whether they will survive during or after CRRT treatment. Because of outcome uncertainty, a large percentage of patients treated with CRRT do not survive, utilizing scarce resources and raising false hope in patients and their families. To address these issues, we present a machine learning-based algorithm to predict short-term survival in patients being initiated on CRRT. We use information extracted from electronic health records from patients who were placed on CRRT at multiple institutions to train a model that predicts CRRT survival outcome; on a held-out test set, the model achieves an area under the receiver operating curve of 0.848 (CI = 0.822–0.870). Feature importance, error, and subgroup analyses provide insight into bias and relevant features for model prediction. Overall, we demonstrate the potential for predictive machine learning models to assist clinicians in alleviating the uncertainty of CRRT patient survival outcomes, with opportunities for future improvement through further data collection and advanced modeling.

Classifying and Predicting the Thermal Expansion Properties of Metal-Organic Frameworks: A Data-Driven Approach.

Metal-organic frameworks (MOFs) are versatile materials for a wide variety of potential applications. Tunable thermal expansion properties promote the application of MOFs in thermally sensitive composite materials; however, they are currently available only in a handful of structures. Herein, we report the first data set for thermal expansion properties of 33,131 diverse MOFs generated from molecular simulations and subsequently develop machine learning (ML) models to (1) classify different thermal expansion behaviors and (2) predict volumetric thermal expansion coefficients (αV). The random forest model trained on hybrid descriptors combining geometric, chemical, and topological features exhibits the best performance among different ML models. Based on feature importance analysis, linker chemistry and topological arrangement are revealed to have a dominant impact on thermal expansion. Furthermore, we identify common building blocks in MOFs with exceptional thermal expansion properties. This data-driven study is the first of its kind, not only constructing a useful data set to facilitate future studies on this important topic but also providing design guidelines for advancing new MOFs with desired thermal expansion properties.

Seismic fragility analysis of RC frame structures based on IDA analysis and machine learning

This study introduces a machine learning-based methodology designed to rapidly predict the seismic responses of reinforced concrete (RC) frame structures. The research focuses on three types of RC frame structures: low-rise, multi-story, and small high-rise buildings. Ground shaking records are selected according to the conditional mean spectrum (CMS). A sample database, constructed via Incremental Dynamic Analysis (IDA), facilitates the prediction of structural responses using ground shaking intensity and structural details as inputs. Concurrently, the study performs a feature importance analysis of the model. Machine learning algorithms, including integrated learning and neural networks, are utilized to predict the seismic responses of the RC frame structures. This methodology also assists in evaluating the seismic fragility of these structures. The results show that the discrepancy between the neural network-based seismic fragility assessments and the IDA results is minimal, indicating a high degree of accuracy in the proposed methodology. Among the characteristic parameters, Average Spectral Acceleration (AvgSa) is identified as the most significant. This methodology serves as a valuable tool for the rapid prediction of seismic responses in RC frame structures, demonstrating substantial practical value.

Predicting the boron removal of reverse osmosis membranes using machine learning

Reverse osmosis (RO) is a key technology for seawater desalination, but boron removal remains challenging due to the relatively low and varying boron rejection of RO membranes. This study explored the use of machine learning (ML) to develop predictive models for boron removal of RO membranes. Data of 11 features encompassing membrane properties, testing conditions and membrane performance were collected from journal articles. Missing data were recovered using data imputation algorithms. The predictive models were developed using five regression algorithms: linear, ridge, decision tree, random forest and XGBoost regressors, and the tree-based XGBoost regressor performed the best (R2 = 0.84). Feature importance analysis and tree diagrams revealed that membrane type, feed pH and NaCl rejection as key factors in influencing boron rejection, while membrane surface properties showed minimal impact. Partial dependence plots were generated to further analyze each feature. High NaCl rejection of >99.6 % is highly desirable for SWRO membranes to achieve high boron rejection. For BWRO membranes at pH >9, a looser structure with a NaCl rejection >95 % could be applied. The study successfully applied ML to a dataset with large portion of missing values, and the results provide valuable insights for future membrane design and boron removal processes.

Removal of N-Nitrosodiphenylamine from contaminated water: A novel modeling framework using metaheuristic-based ensemble models

Investigating the complex interactions among physicochemical variables that influence the adsorptive removal of pollutants is a challenge for conventional one-variable-at-a-time (OVAT) batch methods. The adoption of machine learning-based chemometric prediction models is expected to be more accurate than the conventional method. This study proposed a novel modeling framework for predicting and optimizing the adsorptive removal of N-Nitrosodiphenylamine (NDPhA). Initially, models were trained by using OVAT data, with their hyperparameters subsequently fine-tuned through Bayesian optimization. In the second phase, the particle swarm optimization (PSO) technique was adopted to identify optimal parameters, specifically time, concentration, temperature, pH, and dose, to ensure the highest removal. The adopted analytical method enhances both prediction accuracy and removal efficiency. Utilizing OVAT data for NDPhA removal, the XGBoost regressor significantly outperformed other models. With a correlation coefficient of 0.9667 in the testing dataset, the XGBoost model exhibited its accuracy, emphasized by its low mean squared errors of 28.45 and mean absolute errors of 0.0982. Feature importance analysis consistently identified time and concentration as the most critical factors across all models.

Enhanced multi-horizon occupancy prediction in smart buildings using cascaded Bi-LSTM models with integrated features

Accurate occupancy prediction in smart buildings is crucial for optimizing energy management, improving occupant comfort, and effectively controlling building systems, particularly for short- and long-term horizons. Recently, deep learning-based occupancy prediction methods have gained considerable attention. However, the full potential of these methods remains under explored in terms of model architecture variations and prediction horizons. This study introduces cascaded LSTM and cascaded Bi-LSTM models for multi-horizon predictions from 10 minutes to 24 hours, integrating a modified activation function, additional input features, and optimized hyper-parameters using OPTUNA. Traditional performance metrics and various other analyses were conducted to compare the models. Both models performed well for short- and long-term predictions, with minimal differences in the results. Nevertheless, analysis focusing on non-zero data errors (accounting for approximately 11% of occupied periods) and occupancy-wise errors showed a significant performance gap between the two models. The cascaded Bi-LSTM model demonstrated consistent performance across various prediction horizons and occupancy variations, with accuracy approximately 10-15% higher than the cascaded LSTM model, highlighting its superior capability in capturing complex dataset dynamics through a bidirectional process. This study highlights the importance of additional input features, data feature analysis, and multi-perspective result analysis to select the most suitable model for occupancy prediction, validated with pre- and post-modeling feature importance analysis.

Machine learning predicts the serum PFOA and PFOS levels in pregnant women: Enhancement of fatty acid status on model performance

Human exposure to per- and polyfluoroalkyl substances (PFASs) has received considerable attention, particularly in pregnant women because of their dramatic changes in physiological status and dietary patterns. Predicting internal PFAS exposure in pregnant women, based on external and relevant parameters, has not been investigated. Here, machine learning (ML) models were developed to predict the serum concentrations of PFOA and PFOS in a large population of 588 pregnant participants. Dietary exposure characteristics, demographic parameters, and in particular, serum fatty acid (FA) data were used for the model development. The fitting results showed that the inclusion of FAs as covariates significantly improved the performance of the ML models, with the random forest (RF) model having the best predictive performance for PFOA (R2 = 0.33, MAE = 1.51 ng/mL, and RMSE = 1.89 ng/mL) and PFOS (R2 = 0.12, MAE = 2.65 ng/mL, and RMSE = 3.37 ng/mL). The feature importance analysis revealed that serum FAs greatly affected PFOA concentration in the pregnant women, with saturated FAs being associated with decreased PFOA levels and unsaturated FAs with increased levels. Comparison with one-compartment pharmacokinetic model further demonstrated the advantage of the ML models in predicting PFAS exposure in pregnant women. Our models correlate for the first time blood chemical concentrations with human FA status using ML, introducing a novel perspective on predicting PFAS levels in pregnant women. This study provides valuable insights concerning internal exposure of PFASs generated from external exposure, and contributes to risk assessment and management in pregnant populations.

Prediction of axial capacity of corrosion-affected RC columns strengthened with inclusive FRP

The primary cause behind the degradation of reinforced concrete (RC) structures is the propagation of corrosion in the steel-RC structures. Nowadays, numerous retrofitting techniques are available in the construction sector. Fiber-reinforced polymer (FRP) is one of the efficient rehabilitation measures that can be implemented on corroded structures to enhance structural capacities. However, the estimation of axial strength of FRP-strengthened columns affected by corrosion has been a challenging and tedious task in the laboratory as well as on the site. Considering such shortcomings, the prediction of axial capacity can be done using various analytical methods and artificial intelligence (AI) techniques. In this study, a comprehensive dataset of circular columns was extracted from the literature to predict the axial strength of FRP-wrapped and unstrengthened RC corroded columns. The laboratory results from the assembled dataset were compared to corresponding values estimated using relevant design codes provided by American Concrete Institute (ACI 440.2R-17 and ACI 318-19), and Bureau of Indian Standard (IS 456:2000). Five machine learning models were employed on columns to predict the axial load carrying capacity of FRP-strengthened and un-strengthened RC corroded columns. The results discovered that the extreme gradient boosting (XGBoost) model achieves superior accuracy with the least errors and could be used by the scientific community and FRP applicators to forecast the axial performance of corroded columns strengthened with and without FRP. The findings from the design codes revealed that prediction errors were available in high margins. Furthermore, feature importance analysis was conducted using the Shapley Additive exPlanation algorithm to know the contribution and influence of each input parameter on axial capacity. The feature analysis found that unconfined compressive strength of concrete plays an important role in deciding the axial capacity of columns. Moreover, to enhance the precision of axial capacity computation and improving the overall efficacy in engineering practice, a web-based user-friendly interface was developed for FRP applicators and engineers to simplify the process.

Forest Fire Prediction: A Spatial Machine Learning and Neural Network Approach

The study of forest fire prediction holds significant environmental and scientific importance, particularly in regions like South Carolina (SC) with a high incidence rate of forest fires. Despite the limited existing research on forest fires in this area, the application of machine learning and neural network techniques presents an opportunity to enhance forest fire prevention and control efforts. Utilizing data of forest fire from the SC Forestry Commission for the year 2023, prediction models were developed incorporating various factors such as meteorology, terrain, vegetation, and infrastructure—key drivers of forest fires in SC. Feature importance analysis was employed to construct the final fire prediction model using different machine learning and neural network approaches including Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Convolutional Neural Network (CNN). Correlation coefficients analysis was employed to construct the final fire hazard map using a correlation test. The evaluation of predictive performance based on accuracy scores revealed that the DT model achieved the highest accuracy of 90.58%, surpassing other models. However, based on the kernel density map of the fire data from 2000 to 2023, the correlation test gave the better fire hazard map compared to any other machine learning or neural network approach that utilized feature importance. Nonetheless, all models achieved prediction accuracies exceeding 80%. This finding directed us to the approach based on the correlation coefficients rather than to those just based on feature importance. The overlap between fire locations and carbon hotspots provided the immediate need to mitigate the carbon loss due to fire in those locations. These results serve as a valuable resource for forest fire prediction in SC, demonstrating the efficacy of the correlation test, providing a theoretical foundation and data support for future forestry applications in the region, and showing the outperforming capability of this method compared to other approaches based on feature importance and the importance to prioritize areas to mitigate the climate change impact based upon fire prediction.

Street-level temperature estimation using graph neural networks: Performance, feature embedding and interpretability

Estimating street-level air temperature is a challenging task due to the highly heterogeneous urban surfaces, canyon-like street morphology, and the diverse physical processes in the built environment. Though pioneering studies have embarked on investigations via data-driven approaches, many questions remain to be answered. In this study, we leveraged an innovative framework and redefined the street-level temperature estimation problem using Graph Neural Networks (GNN) with spatial embedding techniques. The results showed that GNN models are more capable and consistent of estimating street-level temperature among tested locations, benefiting from its unique strength in handling extensive data over unstructured graph topology. In addition, we conducted in-depth analysis of feature importance to enhance the model interpretability. Among the urban features analyzed in this study, the time-variant canopy density and meter-level land use data emerge as crucial factors. Our findings highlight GNN's high potential in capturing the complex dynamics between urban elements and their impacts on microclimate, thus offering valuable insights for comprehensive urban data collection and urban climate modeling in general. Collectively, this study also contributes to urban planning and policy by providing avenues to enhance city resilience against climate change, thereby advancing the agenda for environmental stewardship and urban sustainability.

Understanding the phytotoxic effects of organic contaminants on rice through predictive modeling with molecular descriptors: A data-driven analysis

The widespread introduction of organic compounds into environments poses significant risks to ecosystems. Assessing the adverse effects of organic contaminants on crops is crucial for ensuring food safety. However, laboratory research is often time-consuming and costly, and machine learning (ML) methods can offer a viable solution to address these challenges. This study aimed at developing a ML model that incorporates chemical descriptors to predict the phytotoxicity of organic contaminants on rice. A dataset was compiled by gathering published experimental data on the phytotoxicity of 60 organic compounds, with a focus on morphological inhibition, photosynthesis perturbation, and oxidative stress. Four ML models (RF, SVM, GBM, ANN) were developed using chemical molecular descriptors (CMD) and the Molecular ACCess System (MACCS) keys. RF-MACCS model demonstrated the highest fitness, achieving an R2 value of 0.79 and an RMSE of 0.14. Feature importance analysis highlighted nAtom, HBA, logKow, and TPSA as the most influential CMDs in our model. Additionally, substructures containing oxygen atoms, carbonyl group and carbon chains with nitrogen and oxygen atoms were identified as significant factors associated with phytotoxicity. This data-driven study could aid in predicting the phytotoxicity of organic contaminants on crops and evaluating the potential risks of emerging contaminants in agroecosystems.

A Data-Driven Approach to Predicting Recreational Activity Participation Using Machine Learning

ABSTRACT Purpose: With the popularity of recreational activities, the study aimed to develop prediction models for recreational activity participation and explore the key factors affecting participation in recreational activities. Methods: A total of 12,712 participants, excluding individuals under 20, were selected from the National Health and Nutrition Examination Survey (NHANES) from 2011 to 2018. The mean age of the sample was 46.86 years (±16.97), with a gender distribution of 6,721 males and 5,991 females. The variables included demographic, physical-related variables, and lifestyle variables. This study developed 42 prediction models using six machine learning methods, including logistic regression, Support Vector Machine (SVM), decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). The relative importance of each variable was evaluated by permutation feature importance. Results: The results illustrated that the LightGBM was the most effective algorithm for predicting recreational activity participation (accuracy: .838, precision: .783, recall: .967, F1-score: .865, AUC: .826). In particular, prediction performance increased when the demographic and lifestyle datasets were used together. Next, as the result of the permutation feature importance based on the top models, education level and moderate-vigorous physical activity (MVPA) were found to be essential variables. Conclusion: These findings demonstrated the potential of a data-driven approach utilizing machine learning in a recreational discipline. Furthermore, this study interpreted the prediction model through feature importance analysis to overcome the limitation of machine learning interpretability.

Determining water and solute permeability of reverse osmosis membrane using a data-driven machine learning pipeline

Water (A) and solute permeability (B) are the key parameters characterizing the performance of reverse osmosis (RO) membranes. However, determining A and B requires multiple times of experiments that are time-consuming. Thus, developing a method to estimate A and B quickly has been encouraged. This study introduces a data-driven machine learning (ML) pipeline designed to predict A and B for RO membranes. The ML pipeline addresses all stages for estimating A and B, from data preprocessing to practical guidance on developed models. In particular, the membrane composition data, an overlooked essential component detailing A and B, was employed as features for the ML models. Sixteen ML models were tested, and categorical boost (CatBoost) and extremely randomized trees (ET) were selected as the best models for A and B, respectively. The selected ML models were retrained using the minimum yet effective features identified through feature importance analysis. Consequently, the retrained ML models exhibited high accuracy in predicting A and B (Radj,test2 = 0.925/MAEtest = 0.246 for A; Radj,test2 = 0.986/MAEtest = 0.069 for B), demonstrating the viability of a data-driven approach for parameter estimation. Moreover, this study highlights that RO membrane performance can be gauged effectively using membrane composition data and a limited set of operating conditions.