Average R2 Value Research Articles

Hybrid multi-stage steel footprinting unveils a more interdependent material foundation of the global economy

Steel is foundational to modern society, yet tracking its socio-economic metabolism is challenging due to the complex global trade networks. Traditional indicators, such as domestic material consumption (DMC) and consumption-based material footprints (MF), typically focus on metal ore extraction, overlooking the multiple stages of steel production and consumption. To address this, we integrate multi-national anthropogenic steel cycles and international trade networks of steel-containing products into a global monetary multi-regional input-output (MRIO) model. We construct material efficiency indicators based on footprints of iron ores, crude steel, castings, finished steel, and fabricated steel products, comparing them with conventional economy-wide material flow indicators like domestic material production (DMP) and DMC. Our findings reveal that per capita multi-stage MF indicators exhibit more robust log-linear relationships with per capita GDP with an average R2 value of 0.72 compared to 0.10 and 0.18 for DMP and DMC. Shares of Embodied trade in total global production exceed direct trade by 24 percentage points on average, emphasizing the significance of international embodied metal transfers. Using multi-stage MF indicators also reduces disparities in material efficiency between developed and developing countries. This study unravels the intricacies of global steel supply chains and the true interdependencies of steel-containing products among countries.

Data driven approach for state-of-charge estimation of lithium-ion cell using stochastic variational Gaussian process

Modern electric vehicles rely on lithium-ion batteries. Electric vehicles (EVs) utilize intricate battery packs that require the oversight of a battery management system (BMS) to ensure safe, reliable, and efficient operation. The state estimation of the battery pack is an important responsibility carried out by the BMS. Accurately estimating the State-of-Charge (SOC) poses a considerable engineering challenge since it cannot be directly measured at the battery terminals. This study introduces a novel data-driven methodology for accurately estimating the SOC in Lithium-ion batteries, with a particular focus on its relevance in EV contexts. The framework is built upon the Stochastic Variational Gaussian Process (SVGP)—an improved version of the conventional Gaussian Process (GP). Unlike GP, It can scale up to very large datasets. Furthermore, SVGP uses variational inference to estimate the posterior instead of calculating, making it computationally efficient. The model training process involves using laboratory test data from an 18650 Lithium-ion Nickel Manganese Cobalt (NMC) cell that has gone through eight dynamic drive cycles. The findings showcase a remarkable level of precision in estimation, as indicated by an average R2 value of 0.99 and a Mean Square Error (MSE) as low as 0.02.

Numerical and machine learning models for concentrically and eccentrically loaded CFST columns confined with FRP wraps

AbstractPrevious research largely concentrated on predicting load‐carrying capacities of concrete‐filled steel tubes (CFST) confined with fiber‐reinforced polymer (FRP) wraps under pure concentric loads, neglecting the more complex failure mechanisms that occur under real‐life eccentric loading conditions. This study, therefore, employs both finite element modeling (FEM) and machine learning methods to accurately predict the load‐bearing capacities under both concentric and eccentric loading conditions. This research analyzed a comprehensive dataset comprising 128 experimental tests and an equivalent number of FEM simulations designed to evaluate their eccentric performance. These models have been thoroughly generated and validated against existing literature. Additionally, the developed ML models, particularly a hybrid deep learning model, demonstrated significant predictive accuracy, with an average R2 value of 0.969 across all model folds. Partial dependence analysis further highlighted the significant influence of concrete strength and the interactive effects of steel tube area and FRP wrap thickness on the load‐carrying capacity of the columns. Furthermore, to enhance cost‐efficiency and resource management compared with traditional laboratory testing, a user‐friendly graphical user interface (GUI) has been developed and hosted on an open‐source platform such as GitHub. This interface supports real‐time, precise predictive capabilities and promotes a collaborative environment for ongoing model refinement and improvement.

Data-driven energy consumption prediction of a university office building using machine learning algorithms

Redundant consumption of energy in buildings is an important issue that causes increasing problems of climate change and global warming in the world. Therefore, it is necessary to develop efficient energy management approaches in buildings. Accurate prediction of energy consumption plays an important role to obtain energy-efficient buildings. Data-driven methods gained attention for estimation of energy consumption in buildings which would provide more accurate prediction results. In this study, hourly energy consumption prediction is performed on a university office building to increase energy efficiency in the building using machine learning algorithms. A new parameter is proposed, air conditioning demand, to improve accuracy of the algorithms. Moreover, temporal parameters, i.e. day of week, month of year, and hour of day, were used along with meteorological parameters to improve prediction performance of the algorithms. Experimental results show that hourly energy consumption of the building could be predicted using machine learning algorithms with high performance. When the results were analysed, Deep Neural Network (DNN) achieved better performance among other alternative algorithms. The average values of R2, RMSE and MAPE for DNN were 0.959, 4.796 kWh, and 5.738 %, respectively. Also, the addition of proposed air conditioning demand parameter provided improved performance to the algorithms.

Determination of Gas–Oil minimum miscibility pressure for impure CO2 through optimized machine learning models

Minimum miscibility pressure (MMP) is one of the most important parameters for designing CO2 enhanced oil recovery (EOR) and associated storage in depleted oil reservoirs. The injection gas stream often contains a certain concentration of impurities such as N2, H2S, and CH4 depending on the source of CO2. These impurities have different effects on CO2 MMP, but there is a lack of widely accepted approaches to account for these effects on MMP calculation. In this study, a series of activities were conducted to develop a machine learning (ML)-based methodology for determining MMP for CO2 with various impurities. A database containing 234 CO2 MMP test sets with around 5000 data points was built based on the reported experimental measurements in the public domain. The database was then subgrouped by three specific criteria: CO2 concentration in the injection gas, type of impurities in the injection gas, and heavier hydrocarbon content in the oil. This subgrouping was essential to capture the impact of different factors on CO2 MMP. An ensemble ML approach with seven ML models, including random forest, adaptive boosting, light gradient boosting machine, extreme gradient boosting (XGBoost), stacking, artificial neural network, and voting regressor, was employed to calculate MMP based on the subgrouped database. The hyperparameters of these ML models were optimized by the grid search technique to minimize the relative errors between calculated and measured MMP values. The performance of each algorithm was assessed using three regression metrics: average absolute relative error (AARE), R-squared score (R2), and root mean square error (RMSE). All of these metrics exhibited satisfactory values for the optimized ML models. The average values of R2, RMSE, and AARE were 0.962, 1.571, and 4.55%, respectively, for the three subgroups, indicating a high accuracy of MMP calculations using the optimized ML models. The XGBoost model emerged as the top performer across the three metrics, with an R2 of 0.979, an AARE of 2.835%, and an RMSE of 1.183 for a dataset with 190 cases. The overall high level of accuracy confirmed the reliability of these ML models in calculating MMP for CO2 with different impurities as well as the importance of optimization in the modeling process.

A deep learning-based convolutional spatiotemporal network proxy model for reservoir production prediction

Accurate production prediction is crucial in the field of reservoir management and production optimization. Traditional models often struggle with the complexities of nonlinear relationships and high-dimensional data, which hinders their ability to capture the variability of the production process efficiently and results in time-consuming calculations. To overcome these limitations, this paper introduces an innovative proxy modeling technique employing a convolutional spatiotemporal neural network. This method utilizes convolutional neural networks to extract spatial features from high-dimensional data, while the Transformer is used to model and predict complex temporal dynamics in production. To validate the effectiveness of the proposed proxy model, two case studies involving four injection and nine production wells within two-dimensional (2D) and three-dimensional (3D) non-homogeneous reservoirs were conducted, with the R2 coefficient serving as the primary evaluation metric. As the number of training iterations and data volume increase, the proxy model demonstrates rapid convergence. In tests conducted on the 2D and 3D datasets, the average R2 value exceeded 0.96 and 0.94. These results confirm the accuracy and stability of the proxy model. It also shows that the proxy model can accurately describe the geological and fluid seepage characteristics of the reservoir, which in turn can achieve a highly accurate match with the real data. In addition, the computational time is reduced by two orders of magnitude compared to traditional models. Compared with the long short-term memory method, the accuracy of the prediction results is increased by 30%, which greatly enhances efficiency and accuracy. To some extent, the presented proxy model can provide some guidance for the efficient history match of production data.

Representative Sample Size for Estimating Saturated Hydraulic Conductivity via Machine Learning: A Proof‐Of‐Concept Study

AbstractMachine learning (ML) has been extensively applied in various disciplines. However, not much attention has been paid to data heterogeneity in databases and number of samples used to train ML models in hydrology. In this study, we addressed these issues and their impacts on the accuracy and reliability of ML models in the estimation of saturated hydraulic conductivity, Ks. We selected 17,990 soil samples from the USKSAT database and created random subsets N = 2,000, 4,000, 6,000, 8,000, 10,000, 12,000, 14,000, 16,000, and 17,990, 80% of which were used for training. The random subset selection was repeated 50 times. The extreme gradient boosting (XGBoost) algorithm was used to estimate Ks from other soil properties, such as bulk density, soil depth, texture, and organic content. For each subset, we conducted the learning curve analysis on the training and cross‐validation data sets. Results showed that for all training sample sizes the number of samples was not enough for the training and cross‐validation curves to reach a plateau. We also applied the concept of representative elementary volume by plotting the average coefficient of determination, R2, and root mean square log‐transformed error, RMSLE, against the training sample size. For the testing data set, as the number of training sample size increased from 1,600 to 14,392 the average R2 value increased from 0.74 to 0.90, while the average RMSLE value decreased from 1.08 to 0.69. Either the learning curve or representative sample size analysis is required to investigate whether the number of samples is enough or not.

A novel method for correcting dew point protection data of heavy-duty diesel vehicles based on random forest

On-board diagnostics (OBD) remote monitoring technology is essential for continuously tracking emissions from heavy-duty diesel vehicles (HDDVs) in operation. However, the dew point protection (DPP) mechanism of nitrous oxides (NOx) sensors frequently results in invalid measurement data, impeding effective NOx emissions monitoring. Current research has yet to offer a practical solution to this challenge. To bridge this gap, a novel machine learning-driven approach has been introduced to correct faulty data. This method focuses on using characteristic data extracted from remote monitoring records to train a NOx concentration prediction model. Consequently, predicted values replace the inaccurate measurements triggered by DPP, enabling self-correction of NOx measurements. To validate the effectiveness of this approach, field tests were conducted on four HDDVs. Among the three compared prediction models, the Random Forest (RF) model demonstrated superior performance on the test dataset, achieving an impressive average R2 value of 0.706, while maintaining low RMSE and MAE values of 0.0335 and 0.0199, respectively (normalized). Post-correction analysis indicated that despite DPP being active for only 10–17% of each month, it accounts for a significant 20–50% of NOx emissions, with a relative error margin of less than 12.3% in our estimation. This research holds pivotal importance in enhancing the quality of remote monitoring data (RMD), thereby enabling seamless and efficient emissions tracking for HDDVs.

Spectro-ViT: A vision transformer model for GABA-edited MEGA-PRESS reconstruction using spectrograms

This study investigated the use of a Vision Transformer (ViT) for reconstructing GABA-edited Magnetic Resonance Spectroscopy (MRS) data from a reduced number of transients. Transients refer to the samples collected during an MRS acquisition by repeating the experiment to generate a signal of sufficient quality. Specifically, 80 transients were used instead of the typical 320 transients, aiming to reduce scan time. The 80 transients were pre-processed and converted into a spectrogram image representation using the Short-Time Fourier Transform (STFT). A pre-trained ViT, named Spectro-ViT, was fine-tuned and then tested using in-vivo GABA-edited MEGA-PRESS data. Its performance was compared against other pipelines in the literature using quantitative quality metrics and estimated metabolite concentration values, with the typical 320-transient scans serving as the reference for comparison. The Spectro-ViT model exhibited the best overall quality metrics among all other pipelines against which it was compared. The metabolite concentrations from Spectro-ViT's reconstructions for GABA+ achieved the best average R2 value of 0.67 and the best average Mean Absolute Percentage Error (MAPE) value of 9.68%, with no significant statistical differences found compared to the 320-transient reference. The code to reproduce this research is available at https://github.com/MICLab-Unicamp/Spectro-ViT

Artificial Neural Network-aided Mathematical Model for Predicting Soil Stress-strain Hysteresis Loop Evolution

This study presents a novel approach to forecasting the evolution of hysteresis stress-strain response of different types of soils under repeated loading-unloading cycles. The forecasting is made solely from the knowledge of soil properties and loading parameters. Our approach combines mathematical modeling, regression analysis, and Deep Neural Networks (DNNs) to overcome the limitations of traditional DNN training. As a novelty, we propose a hysteresis loop evolution equation and design a family of DNNs to determine the parameters of this equation. Knowing the nature of the phenomenon, we can impose certain solution types and narrow the range of values, enabling the use of a very simple and efficient DNN model. The experimental data used to develop and test the model was obtained through Torsional Shear (TS) tests on soil samples. The model demonstrated high accuracy, with an average R² value of 0.9788 for testing and 0.9944 for training.

Occurrence of Wetness on the Fruit Surface Modeled Using Spatio-Temporal Temperature Data from Sweet Cherry Tree Canopies

Typically, fruit cracking in sweet cherry is associated with the occurrence of free water at the fruit surface level due to direct (rain and fog) and indirect (cold exposure and dew) mechanisms. Recent advances in close range remote sensing have enabled the monitoring of the temperature distribution with high spatial resolution based on light detection and ranging (LiDAR) and thermal imaging. The fusion of LiDAR-derived geometric 3D point clouds and merged thermal data provides spatially resolved temperature data at the fruit level as LiDAR 4D point clouds. This paper aimed to investigate the thermal behavior of sweet cherry canopies using this new method with emphasis on the surface temperature of fruit around the dew point. Sweet cherry trees were stored in a cold chamber (6 °C) and subsequently scanned at different time intervals at room temperature. A total of 62 sweet cherry LiDAR 4D point clouds were identified. The estimated temperature distribution was validated by means of manual reference readings (n = 40), where average R2 values of 0.70 and 0.94 were found for ideal and real scenarios, respectively. The canopy density was estimated using the ratio of the number of LiDAR points of fruit related to the canopy. The occurrence of wetness on the surface of sweet cherry was visually assessed and compared to an estimated dew point (Ydew) index. At mean Ydew of 1.17, no wetness was observed on the fruit surface. The canopy density ratio had a marginal impact on the thermal kinetics and the occurrence of wetness on the surface of sweet cherry in the slender spindle tree architecture. The modelling of fruit surface wetness based on estimated fruit temperature distribution can support ecophysiological studies on tree architectures considering resilience against climate change and in studies on physiological disorders of fruit.

Enhancing wind power prediction with self-attentive variational autoencoders: A comparative study

Accurate wind power prediction is critical for efficient grid management and the integration of renewable energy sources into the power grid. This study presents an effective deep-learning approach that improves short-term wind power forecasting accuracy. The method incorporates a Variational Autoencoder (VAE) with a self-attention mechanism applied in both the encoder and decoder. This empowers the model to leverage VAE's strengths in time-series modeling and nonlinear approximation while focusing on the most relevant features within the wind power data. The effectiveness of this approach is evaluated through a comprehensive comparison with eight established deep learning methods, including Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Bidirectional LSTMs (BiLSTMs), Convolutional LSTMs (ConvLSTMs), Gated Recurrent Units (GRUs), Stacked Autoencoders (SAEs), Restricted Boltzmann Machines (RBMs), and vanilla VAEs. Real-world data from five wind turbines in France and Turkey is used for the evaluation. Five statistical metrics are employed to quantitatively assess the prediction performance of each method. The results indicate that the SA-VAE model consistently outperformed other models, achieving the highest average R2 value of 0.992, demonstrating its superior predictive capability compared to existing techniques.

Genome-wide association and genomic prediction study of elite spring bread wheat (Triticum aestivum L.) genotypes under drought conditions across different locations

Abiotic stress, notably drought, impacts wheat production globally, but more so in central and South Asia, North Africa (CWANA), and sub-Saharan Africa (SSA). The current study attempts to identify significant markers linked to drought and heat tolerance and assess genomic prediction. A genome-wide association study was conducted using the 10 K wheat SNP markers for grain yield and related traits of 246 spring bread wheat genotypes from ICARDA. Traits including grain yield (GY), days to heading (DHE), days to maturity (DMA), plant height (PLH), and thousand kernel weight (TKW), were evaluated across six different locations, spanning two years 2015–2016 and 2016–2017, as per variance analysis. Grain yield and related-traits showed a considerable variation among genotypes. Moreover, GWAS using a mixed linear model (MLM), revealed 65 marker-trait associations (MTAs) across the six environments on 16 chromosomes. With an average r2 value of 0.26, Genome D has the highest linkage, followed by Genomes B and A with r2 values of 0.22 and 0.21, respectively. GY had the highest MTA rating (35), followed by TKW (9) and 3 for each of the other agronomic traits (DHE, DMA, PLH) at Merchouch station. The marker “CAP8_c1393_327” was the most significant associated marker correlated with grain yield located on chromosome 3 A across Sid El Aidi station. Additionally, the SNP markers “wsnp_Ra_c26091_35652620” displayed extremely significant and stable MTA for TKW on chromosome 5B at Merchouch station. The markers and candidate genes reported throughout this study have the potential to be used in marker-assisted selection to enhance wheat genotypes in terms of yield and resistance to drought limitations.

A Comparative Analysis of Machine Learning Approaches for Evaluating the Compressive Strength of Pozzolanic Concrete

This study leverages machine learning techniques to predict pozzolanic concrete's compressive strength accurately. Using artificial neural networks (ANN), random forest (RF), and gradient boosting regressor (GBR) models trained on a dataset of 482 samples, the study divides the data into 70% training and 30% testing subsets with seven input parameters. Model performance is assessed through metrics like coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The RF model excels, achieving R2 values of 0.976 in training and 0.964 in testing, along with the lowest RMSE (2.84 MPa) and MAE (2.05 MPa) during training and RMSE values of 7.81 MPa and MAE values of 5.89 MPa during testing, demonstrating superior predictive accuracy. Sensitivity analysis highlights the pivotal role of cement as an input parameter, contributing significantly to the model's accuracy. Employing K-fold cross-validation confirms the RF model's robustness with an average R2 value of 0.959. This research underscores the RF model's reliability and effectiveness in forecasting pozzolanic concrete compressive strength, with practical applications for concrete optimization and construction practices, establishing it as the preferred choice compared to other machine learning models. IUBAT Review—A Multidisciplinary Academic Journal, 7(1): 90-122

Real-time pavement temperature prediction through ensemble machine learning

Pavement temperature is crucial for assessing asphalt pavement's performance and structural integrity due to its viscoelastic behavior. Currently, asphalt temperature prediction includes analytical, numerical, and statistical methods and relies on field investigation with intensive labor and time to hinder routine practice. Machine learning (ML) offers a promising solution for reliable and accurate real-time predictions by considering various dynamic environmental factors. This research employs four ensemble ML algorithms: eXtreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGBM), Random Forest (RF), and Adaptive Boosting (AdaBoost) to predict pavement temperature at different depths. XGB consistently outperformed other ensemble models, boasting the highest average R2 value (97.92%) and lower MAE and RMSE than LGBM, RF, and AdaBoost. XGB also significantly outperformed other commonly used models (linear regression, SVR, ANN, LSTM, and GRU) with an average reduction in errors of 35.29%, 63.75%, 42.75%, and an increase in R2 by 4.39% for MAE, MSE, RMSE, and R2, respectively. The Shapley additive explanation (SHAP) was applied to interpret the underlying influencing factors and their interactions, and revealed atmospheric temperature as the most impactful feature, contributing over 40.58% among the significant features.Furthermore, the predictive performance of XGB was enhanced by incorporating Principal Component Analysis to reduce computational consumption with average reductions of 8.98%, 16.59%, 9.01%, and 7.89% in MAE, MSE, MAPE, and RMSE. XGB with PCA emerges as the most effective and efficient model for predicting pavement temperatures at various depths to facilitate timely decision-making for preventive maintenance and rehabilitation and prevent future catastrophic failures.

Machine learning-based thermal performance study of microchannel heat sink under non-uniform heat load conditions

The parallel microchannel heat sink stands as a pivotal solution in managing high heat flux electronics due to its efficient heat transfer characteristics and ease of manufacturing. While numerous studies have explored the thermal performance and flow characteristics of microchannel heat sinks, most have focused on uniform heat loads or relied heavily on numerical methods. This study presents an experimental system tailored to generate data for analyzing the thermal performance of microchannel heat sinks under various conditions. Leveraging this dataset, four distinct machine learning models Artificial Neural Network (ANN), XGBoost, LightGBM, and K-nearest neighbor (KNN) were trained using 22 input features, totalling 560 data points categorised into geometry parameters, heating patterns, and boundary conditions details. The models were tasked with predicting six response variables: the average base temperature of the heat sink, temperature change (ΔT), hotspot temperature, heat transfer coefficient (h), Nusselt number (Nu), and thermal resistance (Rth). Among the four machine learning models, XGBoost exhibited a good predictive accuracy of an average R2 value of 0.98 and MAE values of 2.1 across all responses. Furthermore, the study delved into the impact of varying input features on prediction accuracy, revealing a consistent enhancement in accuracy with the inclusion of more features across all models.

Advancing nodal leakage estimation in decentralized water networks: Integrating Bayesian optimization, realistic hydraulic modeling, and data-driven approaches

The expansion of cities escalates the demand on water utilities amid global water scarcity, making leakage management a critical challenge for water sector sustainability. On this subject, the study introduces an advanced practical approach for estimating nodal leakage through the calibration of decentralized networks using available data. The approach includes conducting a pressure step-test for data collection, employing the DBSCAN algorithm for outlier detection, and employing Bayesian optimization for effective calibration. Hydraulic leakage models, particularly the power and modified orifice equations, are innovatively applied to model and identify existing leaks at each network node through deep comparison. The computational analysis demonstrated efficiency and accuracy in overcoming vast computational complexity and time constraints, with the calibration of a real-life network resulting in a cumulative MSE of 0.892 and an average R² and NSE values near 0.98. Additionally, realistic leakage modeling revealed inaccuracies in the acknowledged connection between the modified orifice equation and the leakage power equation. This study also provides key insights for enhancing water loss management and conducting on-site inspections in an environmentally conscious manner, especially crucial for budget-constrained water utilities and authorities experiencing revenue declines.

Drying kinetics and quality characteristics of exocarpium citreic grandis slices with hot air, vacuum, and microwave vacuum dryers

The study investigates the impact of different drying methods on the selection of thin-layer drying kinetic models, parameters, and quality for Exocarpium Citreic Grandis. This study investigates the drying characteristics, index constituents content, and microscopic structures of Exocarpium Citreic Grandis slices, subjected to three drying techniques: HAD (at 50, 60, 70∘C), VD (at 50, 60, 70∘C), and MVD (at 1000, 1500, 2000W). A thin-layer drying kinetic model was established. The findings demonstrated that the drying process was primarily dominated by the falling rate phase. When the drying temperature was 70∘C and the microwave power was 2000W, the HAD VD, and MVD took 120, 360, and 20 minutes respectively. By fitting six commonly used thin-layer drying models, it was discovered that the optimal mathematical models for HAD, VD, and MVD were the Page model, the Logarithmic model, and the Page model, respectively. The highest average R2 values were 0.9963, 0.9965, and 0.9964, and the lowest average RMSE values were 0.01782, 0.01704, and 0.0174 respectively. The effective diffusion coefficient increased with the drying temperature and microwave power, with MVD having the maximum coefficient. As the temperature and microwave power increased, the contents of naringin and rhoifolin decreased. However, the naringin content in MVD was 23.05% and 45.71% higher compared to hot air and VD respectively. The cross-section of Exocarpium Citreic Grandis dried via microwave vacuum exhibited a porous honeycomb structure with uniformly distributed spaces and larger pores, reflecting an expansion effect. The HAD process also resulted in a honeycomb-like structure, but with smaller pores. The VD process resulted in a layered structure with significant cell collapse. Microwave vacuum drying demonstrates superior energy efficiency and product quality compared to hot air and vacuum drying methods. The study finds that microwave drying does not have a destructive impact on the active compounds of Exocarpium Citreic Grandis. To facilitate large-scale, continuous production, microwave drying can be practically applied in industrial processing.

Accelerated urban river water quality assessment in Southern India using visible and near-infrared spectroradiometry

Optical indicators of water quality offer resource managers a swift and cost-effective means of monitoring water bodies. Remote sensing presents a promising avenue to overcome limitations, enabling comprehensive evaluation across geographical and temporal scales. This study presents initial findings utilizing hyperspectral sensing to analyze the water quality of the urban river Cooum in Chennai, Tamil Nadu. Lab analysis of 40 water samples included examination for key ions such as chloride, calcium, fluoride, sulphate, nitrate, and bicarbonates, as well as assessment of solids and colloidal components. Spectral analysis using a handheld Visible Near-Infrared (VNIR) spectroradiometer yielded reflectance curves, depicting the response of various water types and pollutants at different wavelengths. Integration of spectroradiometer data with water quality parameters facilitated the identification of empirical models tailored to the parameters of interest. The developed models exhibited an average R2 value of 0.7, underscoring the efficacy of hyperspectral remote sensing in rapidly assessing water quality in polluted rivers.

Peach seed shell and Aspergillus oryzae as adsorbents for the uptake of acid violet 90 dye from wastewater

In this study, Aspergillus oryzae (A. Oryzae) biomass and waste peach seed shells (PPSS) were used to create alternative and effective adsorbents. Acid Violet 90 (AVD) dye was removed from wastewater using the as-prepared adsorbents. Different process variables like pH (2–11), contact period (0–180 min), and adsorbent mass (0.2–2.0 g/L) were examined. The solution pH had a synergistic effect on the improved removal of AVD and the optimal adsorption removal for the PPSS and the A. Oryzae adsorbent occurred at pH 2.0 and pH 5.0, respectively. The findings demonstrated that, in comparison to A. Oryzae, PPSS reported a greater AVD adsorption (mg/g). The equilibrium time for the adsorption process was attained within 180 min for both adsorbents. The adsorption kinetics modelling results showed a good fit with pseudo-second-order kinetics, for both adsorbents, with average R2 values of 0.999 (for PPSS) and 0.997 (for A. Oryzae). Similarly, the isotherm modelling results confirmed the good fitting of the Langmuir isotherm model for A. Oryzae (R2 = 0.999) and the Freundlich model for PPSS (R2 = 0.997). The maximum adsorption capacity (qmax) of 55.0 and 94.92 mg/g was recorded for A. Oryzae and PPSS, respectively. Mechanistic investigation of the present system suggests that both intraparticle diffusion and surface sorption mechanisms control the adsorption rate. As agro materials, both adsorbents are composed of mostly oxygen-based surface functional groups like the –OH, –C = O, -C-O-C, and multiple carbon-carbon bonds, all contributed to the synergistic mechanism interaction between the adsorbent and AVD dye in this study. This study, therefore, revealed that the PPSS and A. Oryzae may be very helpful for removing anionic dye from contaminated wastewater, indicating its potential for useful application in the removal of other major pollutants.