Simultaneous and automated monitoring of the multimetal biosorption processes by potentiometric sensor array and artificial neural network

Prediction of lead (Pb) adsorption on attapulgite clay using the feasibility of data intelligence models

This study investigates the performance of support vector machine (SVM), multivariate adaptive regression spline (MARS), and random forest (RF) models for predicting the lead (Pb) adsorption by attapulgite clay. Models are constructed using batch stochastic data of heavy metal (HM) concentrations under different physicochemical conditions. Implementation of auto-hyper-parameter tuning using grid-search approach and comparative analysis is performed against the benchmark artificial intelligence (AI) models. Models are constructed based on Pb concentration (IC), the dosage of attapulgite clay (dose), contact time (CT), pH, and NaNO3 (SN). Principle component analysis (PCA) and correlation analysis (CA) methods are integrated to assess the importance of the applied predictors and their relationship with the target. Research findings approved the potential of the grid-RF model as a marginal superior predictive model against the grid-SVM in terms of MAE, i.e., 3.29 and 3.34, respectively; moreover, the md scored the same, i.e., 0.93, which reveals the potential predictability for both. Nonetheless, grid-MARS and standalone MARS models remained likewise in their predictability. IC parameter demonstrated the highest influential among all the predictors with the highest value of importance in the case of all three evaluators. The solution pH and dose stands together with marginal differences in case of PCA method; however, solution pH and CT appeared with similarity impact using the PCA method.

Mathematical Modelling of Biosensing Platforms Applied for Environmental Monitoring

In recent years, mathematical modelling has known an overwhelming integration in different scientific fields. In general, modelling is used to obtain new insights and achieve more quantitative and qualitative information about systems by programming language, manipulating matrices, creating algorithms and tracing functions and data. Researchers have been inspired by these techniques to explore several methods to solve many problems with high precision. In this direction, simulation and modelling have been employed for the development of sensitive and selective detection tools in different fields including environmental control. Emerging pollutants such as pesticides, heavy metals and pharmaceuticals are contaminating water resources, thus threatening wildlife. As a consequence, various biosensors using modelling have been reported in the literature for efficient environmental monitoring. In this review paper, the recent biosensors inspired by modelling and applied for environmental monitoring will be overviewed. Moreover, the level of success and the analytical performances of each modelling-biosensor will be discussed. Finally, current challenges in this field will be highlighted.

Heavy metal contamination prediction using ensemble model: Case study of Bay sedimentation, Australia

Lead (Pb) is a primary toxic heavy metal (HM) which present throughout the entire ecosystem. Some commonly observed challenges in HM (Pb) prediction using artificial intelligence (AI) models include overfitting, normalization, validation against classical AI models, and lack in learning/technology transfer. This study explores the extreme gradient boosting (XGBoost) model as a superior SuperLearning (SL) algorithms for Pb prediction. The proposed model was examined using historical data at the Bramble and Deception Bay (BB and DB) stations, Australia. The model was trained at one of the stations and transferred to a cross-station and vice versa. XGBoost showed higher reliability with less declination in (R²: coefficient of determination), i.e., 0.97 % over the testing phase, among others models at BB. At the cross-station (DB), the performance of the XGBoost model was decreased by 2.74 % (R²) against random forests (RF). The mean absolute error (MAE) observed 40 % (XGBoost) and 47 % (RF) less than artificial neural network (ANN). The XGBoost model performance declined by 3.44 % (R²) over testing (DB), which is minor among validated models. At the cross-station (BB), the XGBoost model showed the least decrement in terms of R², i.e., 7.99 % against the ANN (8.31 %), RF (10.26 %), and support vector machine (SVM, 36.19 %).

Heavy Metal/Toxins Detection Using Electronic Tongues

The growing concern for sustainability and environmental preservation has increased the demand for reliable, fast response, and low-cost devices to monitor the existence of heavy metals and toxins in water resources. An electronic tongue (e-tongue) is a multisensory array mostly based on electroanalytical methods and multivariate statistical techniques to facilitate information visualization in a qualitative and/or quantitative way. E-tongues are promising analytical devices having simple operation, fast response, low cost, easy integration with other systems (microfluidic, optical, etc) to enable miniaturization and provide a high sensitivity for measurements in complex liquid media, providing an interesting alternative to address many of the existing environmental monitoring challenges, specifically relevant emerging pollutants such as heavy metals and toxins.

Detection of copper, lead, cadmium and iron in wine using electronic tongue sensor system

An array of 10 potentiometric chemical sensors has been applied to the detection of total Fe, Cu, Pb and Cd content in digested wine. As digestion of organic matter of wine is necessary prior to the trace metal detection using potentiometric sensors, sample preparation procedures have been optimized. Different variants of wet and microwave digestion and dry ashing, 14 conditions in total, have been tested. Decomposition of organic matter was assessed using Fourier transform mid-infrared spectroscopy and total phenolic content. Dry ashing was found to be the most effective method of wine digestion. Measurements with sensors in individual solutions of Fe(III), Cu(II), Pb(II) and Cd(II) prepared on different backgrounds have shown that their detection limits were below typical concentration levels of these metals in wines and, in the case of Cu, Pb and Cd below maximum allowed concentrations. Detection of Fe in digested wine samples was possible using discrete iron-sensitive sensors with chalcogenide glass membranes with RMSEP of 0.05 mmol L(-1) in the concentration range from 0.0786 to 0.472 mmol L(-1). Low concentration levels of Cu, Pb and Cd in wine and cross-sensitivity of respective sensors resulted in the non-linearity of their responses, requiring back-propagation neural network for the calibration. Calibration models have been calculated using measurements in the model mixed solutions containing all three metals and a set of digested wine sample. RMSEP values for Cu, Pb and Cd were 3.9, 39 and 1.2 μmol L(-1) in model solutions and 2, 150 and 1 μmol L(-1) in digested wine samples.