Assessment of arsenic concentration in stream water using neuro fuzzy networks with factor analysis

Prediction of potentially toxic elements in water resources using MLP-NN, RBF-NN, and ANFIS: a comprehensive review

Water resources are constantly threatened by pollution of potentially toxic elements (PTEs). In efforts to monitor and mitigate PTEs pollution in water resources, machine learning (ML) algorithms have been utilized to predict them. However, review studies have not paid attention to the suitability of input variables utilized for PTE prediction. Therefore, the present review analyzed studies that employed three ML algorithms: MLP-NN (multilayer perceptron neural network), RBF-NN (radial basis function neural network), and ANFIS (adaptive neuro-fuzzy inference system) to predict PTEs in water. A total of 139 models were analyzed to ascertain the input variables utilized, the suitability of the input variables, the trends of the ML model applications, and the comparison of their performances. The present study identified seven groups of input variables commonly used to predict PTEs in water. Group 1 comprised of physical parameters (P), chemical parameters (C), and metals (M). Group 2 contains only P and C; Group 3 contains only P and M; Group 4 contains only C and M; Group 5 contains only P; Group 6 contains only C; and Group 7 contains only M. Studies that employed the three algorithms proved that Groups 1, 2, 3, 5, and 7 parameters are suitable input variables for forecasting PTEs in water. The parameters of Groups 4 and 6 also proved to be suitable for the MLP-NN algorithm. However, their suitability with respect to the RBF-NN and ANFIS algorithms could not be ascertained. The most commonly predicted PTEs using the MLP-NN algorithm were Fe, Zn, and As. For the RBF-NN algorithm, they were NO3, Zn, and Pb, and for the ANFIS, they were NO3, Fe, and Mn. Based on correlation and determination coefficients (R, R2), the overall order of performance of the three ML algorithms was ANFIS > RBF-NN > MLP-NN, even though MLP-NN was the most commonly used algorithm.

Viability of two adaptive fuzzy systems based on fuzzy c means and subtractive clustering methods for modeling Cadmium in groundwater resources

The Adaptive Neuro-Fuzzy Inference System (ANFIS) combines the strengths of both Artificial Neural Networks (ANNs) and Fuzzy Logic (FL) into a single framework. By doing so, it allows for quicker learning and adaptable interpretation capabilities, which are useful for modeling complex patterns and identifying nonlinear relationships. One significant challenge in assessing water quality is the difficulty and time-consuming nature of determining the various factors that impact it. Given this situation, predicting heavy metal levels in groundwater resources, both urban and rural, is essential. This paper investigates two methods, ANFIS-FCM and ANFIS-SUB, to determine their effectiveness in modeling Cadmium (Cd) in groundwater resources. ‏The parameters to be considered are: dissolved solids (TDS), electroconductivity (EC), turbidity (TU), and pH were assumed to be the independent variables. A total of 51 sampling location were used with in the groundwater resource were used to develop the fuzzy models. For evaluating the performance of ANFIS-FCM and ANFIS-SUB models, three different performance criteria including the correlation coefficient, root mean square error, and sum square error were used for comparing the model outputs with actual outputs‏.‏ Based on the obtained results from scatter plots of actual and predicted value by ANFIS-SUB and ANFIS- FCM models, the determination coefficient (R²) value for total data, test and train sets is equal to 0.978, 0.982, 0.993 and to 0.983, 0.999 and 0.998 respectively. This result proved the Cd predictions of the implemented ANFIS-FCM model was significantly close to the measured all experimental data with R² of 0.983. The performance of the implemented ANFIS-FCM model was compared with the ANFIS-SUB model and it is found that the ANFIS-FCM provided slightly higher accuracy than the ANFIS-SUB model. Also, the results obtained from the comparison between the predicted and the actual data indicated that the ANFIS-FCM and ANFIS-SUB have a strong potential in estimating the heavy metals in the groundwater with a high degree of accuracy.

Prediction of stream nitrogen and phosphorus concentrations from high-frequency sensors using Random Forests Regression

Stream nutrient concentrations exhibit marked temporal variation due to hydrology and other factors such as the seasonality of biological processes. Many water quality monitoring programs sample too infrequently (i.e., weekly or monthly) to fully characterize lotic nutrient conditions and to accurately estimate nutrient loadings. A popular solution to this problem is the surrogate-regression approach, a method by which nutrient concentrations are estimated from related parameters (e.g., conductivity or turbidity) that can easily be measured in situ at high frequency using sensors. However, stream water quality data often exhibit skewed distributions, nonlinear relationships, and multicollinearity, all of which can be problematic for linear-regression models. Here, we use a flexible and robust machine learning technique, Random Forests Regression (RFR), to estimate stream nitrogen (N) and phosphorus (P) concentrations from sensor data within a forested, mountainous drainage area in upstate New York. When compared to actual nutrient data from samples tested in the laboratory, this approach explained much of the variation in nitrate (89%), total N (85%), particulate P (76%), and total P (74%). The models were less accurate for total soluble P (47%) and soluble reactive P (32%), though concentrations of these latter parameters were in a relatively low range. Although soil moisture and fluorescent dissolved organic matter are not commonly used as surrogates in nutrient-regression models, they were important predictors in this study. We conclude that RFR shows great promise as a tool for modeling instantaneous stream nutrient concentrations from high-frequency sensor data, and encourage others to evaluate this approach for supplementing traditional (laboratory-determined) nutrient datasets.

Explore a Multivariate Bayesian Uncertainty Processor driven by artificial neural networks for probabilistic PM2.5 forecasting

Quantifying predictive uncertainty inherent in the nonlinear multivariate dependence structure of multi-step-ahead PM_2.5 forecasts is challenging. This study integrates a Multivariate Bayesian Uncertainty Processor (MBUP) and an artificial neural network (ANN) to make accurate probabilistic PM_2.5 forecasts. The contributions of the proposed approach are two-fold. First, the MBUP can capture the nonlinear multivariate dependence structure between observed and forecasted data. Second, the MBUP can alleviate predictive uncertainty encountered in PM_2.5 forecast models that are configured by ANNs. The reliability of the proposed approach was assessed by a case study on air quality in Taipei City of Taiwan. We consider forecasts of PM_2.5 concentrations as a function of meteorological and air quality factors based on long-term (2010-2018) hourly observational datasets. Firstly, the Back Propagation Neural Network (BPNN) and the Adaptive Neural Fuzzy Inference System (ANFIS) were investigated to produce deterministic forecasts. Results revealed that the ANFIS model could learn different air pollutant emission mechanisms (i.e. primary, secondary and natural processes) from the clustering-based fuzzy inference system and produce more accurate deterministic forecasts than the BPNN. The ANFIS model then provided inputs (i.e. point estimates) to probabilistic forecast models. Next, two post-processing techniques (MBUP and the Univariate Bayesian Uncertainty Processor (UBUP)) were separately employed to produce probabilistic forecasts. The Bayesian Uncertainty Processors (BUPs) can model the dependence structure (i.e. posterior density function) between observed and forecasted data using a prior density function and a likelihood density function. Here in BUPs, the Monte Carlo simulation was introduced to create a probabilistic predictive interval of PM_2.5 concentrations. The results demonstrated that the MBUP not only outperformed the UBUP but also suitably characterized the complex nonlinear multivariate dependence structure between observations and forecasts. Consequently, the proposed approach could reduce predictive uncertainty while significantly improving model reliability and PM_2.5 forecast accuracy for future horizons.

Tackling environmental challenges in pollution controls using artificial intelligence: A review

This review presents the developments in artificial intelligence technologies for environmental pollution controls. A number of AI approaches, which start with the reliable mapping of nonlinear behavior between inputs and outputs in chemical and biological processes in terms of prediction models to the emerging optimization and control algorithms that study the pollutants removal processes and intelligent control systems, have been developed for environmental clean-ups. The characteristics, advantages and limitations of AI methods, including single and hybrid AI methods, were overviewed. Hybrid AI methods exhibited synergistic effects, but with computational heaviness. The up-to-date review summarizes i) Various artificial neural networks employed in wastewater degradation process for the prediction of removal efficiency of pollutants and the search of optimizing experimental conditions; ii) Evaluation of fuzzy logic used for intelligent control of aerobic stage of wastewater treatment process; iii) AI-aided soft-sensors for precisely on-line/off-line estimation of hard-to-measure parameters in wastewater treatment plants; iv) Single and hybrid AI methods applied to estimate pollutants concentrations and design monitoring and early-warning systems for both aquatic and atmospheric environments; v) AI modelings of short-term, mid-term and long-term solid waste generations, and various ANNs for solid waste recycling and reduction. Finally, the future challenges of AI-based models employed in the environmental fields are discussed and proposed.

Comprehensive Eutrophication Assessment Based on Fuzzy Matter Element Model and Monte Carlo-Triangular Fuzzy Numbers Approach

Evaluating the eutrophication level of lakes with a single method alone is challenging since uncertain, fuzzy, and complex processes exist in eutrophication evaluations. The parameters selected for assessing eutrophication include chlorophyII-a, chemical oxygen demand, total phosphorus, total nitrogen, and clarity. Firstly, to deal with the uncertainties and fuzziness of data, triangular fuzzy numbers (TFN) were applied to describe the fuzziness of parameters. Secondly, to assess the eutrophication grade of lakes comprehensively, an improved fuzzy matter element (FME) approach was incorporated with TFNs with weights determined by combination of entropy method and analytic hierarchy process (AHP). In addition, the Monte Carlo (MC) approach was applied to easily simulate the arithmetic operations of eutrophication evaluation. The hybrid model of TFN, FME, and MC method is termed as the TFN⁻MC⁻FME model, which can provide more valuable information for decision makers. The developed model was applied to assess the eutrophication levels of 24 typical lakes in China. The evaluation indicators were expressed by TFNs input into the FME model to evaluate eutrophication grade. The results of MC simulation supplied quantitative information of possible intervals, the corresponding probabilities, as well as the comprehensive eutrophication levels. The eutrophication grades obtained for most lakes were identical to the results of the other three methods, which proved the correctness of the model. The presented methodology can be employed to process the data uncertainties and fuzziness by stochastically simulating their distribution characteristics, and obtain a better understanding of eutrophication levels. Moreover, the proposed model can also describe the trend of eutrophication development in lakes, and provide more valuable information for lake management authorities.

Estimating spatio-temporal dynamics of stream total phosphate concentration by soft computing techniques

This study attempts to model the spatio-temporal dynamics of total phosphate (TP) concentrations along a river for effective hydro-environmental management. We propose a systematical modeling scheme (SMS), which is an ingenious modeling process equipped with a dynamic neural network and three refined statistical methods, for reliably predicting the TP concentrations along a river simultaneously. Two different types of artificial neural network (BPNN-static neural network; NARX network-dynamic neural network) are constructed in modeling the dynamic system. The Dahan River in Taiwan is used as a study case, where ten-year seasonal water quality data collected at seven monitoring stations along the river are used for model training and validation. Results demonstrate that the NARX network can suitably capture the important dynamic features and remarkably outperforms the BPNN model, and the SMS can effectively identify key input factors, suitably overcome data scarcity, significantly increase model reliability, satisfactorily estimate site-specific TP concentration at seven monitoring stations simultaneously, and adequately reconstruct seasonal TP data into a monthly scale. The proposed SMS can reliably model the dynamic spatio-temporal water pollution variation in a river system for missing, hazardous or costly data of interest.

A cloud model-based approach for water quality assessment

Water quality assessment entails essentially a multi-criteria decision-making process accounting for qualitative and quantitative uncertainties and their transformation. Considering uncertainties of randomness and fuzziness in water quality evaluation, a cloud model-based assessment approach is proposed. The cognitive cloud model, derived from information science, can realize the transformation between qualitative concept and quantitative data, based on probability and statistics and fuzzy set theory. When applying the cloud model to practical assessment, three technical issues are considered before the development of a complete cloud model-based approach: (1) bilateral boundary formula with nonlinear boundary regression for parameter estimation, (2) hybrid entropy-analytic hierarchy process technique for calculation of weights, and (3) mean of repeated simulations for determining the degree of final certainty. The cloud model-based approach is tested by evaluating the eutrophication status of 12 typical lakes and reservoirs in China and comparing with other four methods, which are Scoring Index method, Variable Fuzzy Sets method, Hybrid Fuzzy and Optimal model, and Neural Networks method. The proposed approach yields information concerning membership for each water quality status which leads to the final status. The approach is found to be representative of other alternative methods and accurate.