Deep Learning Neural Network Approach for Predicting the Sorption of Ionizable and Polar Organic Pollutants to a Wide Range of Carbonaceous Materials

Sigmund, Gabriel; Gharasoo, Mehdi; Hüffer, Thorsten; Hofmann, Thilo

doi:10.1021/acs.est.9b06287

Cited by 124 publications

(69 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jhin and Hwang 21 , applied ANFIS to predict radical scavenging activities of carotenoids, while Kebria et al 22 used ANFIS to model landfill leachate transport in underlying soil. Namely on adsorption, Sigmund et al 23 predicted the sorption of ionizable and polar organic pollutants by a wide range of carbonaceous materials using ANN. Ghaedi et al 24 modelled the removal of sunset yellow by activated carbon using ANN.…”

mentioning

confidence: 99%

Modelling of the adsorption of urea herbicides by tropical soils with an Adaptive‐Neural‐based Fuzzy Inference System

Agbaogun

Alonso

Buddenbaum

et al. 2021

Journal of Chemometrics

View full text Add to dashboard Cite

Sorption of pesticides by soils holds a major consequence for their fate in the environment. As such, sorption coefficient (K d /K oc), which is derived from laboratory or field experiments is a fundamental parameter used in almost all screening tools to evaluate the fate or mobility of these compounds. The value of this coefficient is controlled by many soil and solute specific properties, as well as environmental variables. Soft computing techniques such as Adaptive Neuro-Fuzzy Inference System (ANFIS) have been successfully used to predict the equilibrium partitioning of many compounds in various engineered systems. Application of these techniques to natural systems such as soils is however lacking. Here, we present the use of ANFIS in predicting the sorption per unit mass of soil, Q e , used in the calculation of K d /K oc of compounds in soils. In a previous study, we collected data associated to the adsorption of five phenylurea herbicides in 18 tropical soils. Here, we analysed such data and based on established correlations, nine variables were selected as potential input vectors (i.e., six soil properties, two herbicides molecular descriptors and initial solute concentrations). A total of 255 ANFIS models of one to eight input vectors were elaborated under 10-fold cross-validation. Multiple linear regression (MLR) models were similarly developed, and compared with the ANFIS in terms of mean absolute error (MAE), root-mean-square error (RMSE) and coefficient of determination (R 2). The best ANFIS model (M94) has an MAE test , RMSE test and R 2 test of 3.43 ± 0.43, 4.94 ± 0.80 and 0.95 ± 0.01, respectively, whereas the best MLR model (M13) returned an

show abstract

mentioning

confidence: 99%

Modelling of the adsorption of urea herbicides by tropical soils with an Adaptive‐Neural‐based Fuzzy Inference System

Agbaogun

Alonso

Buddenbaum

et al. 2021

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…In this manuscript, glyphosate–monomers interactions were evaluated using a relatively simple statistical method. However, a more sophisticated statistical method, e.g., the neural network approach [ 48 ], can be used later for the precise evaluation of more complex interactions between a desired target and the large numbers of functional monomers.…”

Section: Resultsmentioning

confidence: 99%

Rational Design of Molecularly Imprinted Polymers Using Quaternary Ammonium Cations for Glyphosate Detection

Zarejousheghani

Jaafar

Wollmerstaedt

et al. 2021

Sensors

View full text Add to dashboard Cite

Molecularly imprinted polymers have emerged as cost-effective and rugged artificial selective sorbents for combination with different sensors. In this study, quaternary ammonium cations, as functional monomers, were systematically evaluated to design imprinted polymers for glyphosate as an important model compound for electrically charged and highly water-soluble chemical compounds. To this aim, a small pool of monomers were used including (3-acrylamidopropyl)trimethylammonium chloride, [2-(acryloyloxy)ethyl]trimethylammonium chloride, and diallyldimethylammonium chloride. The simultaneous interactions between three positively charged monomers and glyphosate were preliminary evaluated using statistical design of the experiment method. Afterwards, different polymers were synthesized at the gold surface of the quartz crystal microbalance sensor using optimized and not optimized glyphosate-monomers ratios. All synthesized polymers were characterized using atomic force microscopy, contact angle, Fourier-transform infrared, and X-ray photoelectron spectroscopy. Evaluated functional monomers showed promise as highly efficient functional monomers, when they are used together and at the optimized ratio, as predicted by the statistical method. Obtained results from the modified sensors were used to develop a simple model describing the binding characteristics at the surface of the different synthesized polymers. This model helps to develop new synthesis strategies for rational design of the highly selective imprinted polymers and to use as a sensing platform for water soluble and polar targets.

show abstract

“…We determined the Morris and Sobol indices (Morris, 1991;Campolongo et al, 2007;Saltelli et al, 2008;Pianosi et al, 2015) for the two core model variants (M and T), using the SAFE toolbox of MATLAB (Pianosi et al, 2015;Sigmund et al, 2020). We calculated the mean of the elementary effects (μ*) and the standard deviation of the elementary effects (σ) for the Morris Method, as well as main and total effects for Sobol indices with a total of 15,000 sample inputs in both cases.…”

Section: Global Sensitivity Analysismentioning

confidence: 99%

Modeling Bioavailability Limitations of Atrazine Degradation in Soils

Rodriguez

Ingalls

Meierdierks

et al. 2021

Front. Environ. Sci.

View full text Add to dashboard Cite

Pesticide persistence in soils is a widespread environmental concern in agro-ecosystems. One particularly persistent pesticide is atrazine, which continues to be found in soils and groundwater in the EU despite having been banned since 2004. A range of physical and biological barriers, such as sorption and mass-transfer into bacterial cells, might limit atrazine degradation in soils. These effects have been observed in experiments and models working with simplified systems. We build on that work by developing a biogeochemical model of the degradation process. We extended existing engineered system models by including refined representations of mass-transfer processes across the cell membrane as well as thermodynamic growth constraints. We estimated model parameters by calibration with data on atrazine degradation, metabolite (hydroxyatrazine) formation, biomass, and isotope fractionation from a set of controlled retentostat/chemostat experiments. We then produced site-specific model predictions for arable topsoil and compared them with field observations of residual atrazine concentrations. We found that the model overestimated long-term atrazine biodegradation in soils, indicating that this process is likely not limited by bioavailability or energetic constraints of microbial growth. However, sorption-limited bioavailability, could explain the long-term fate and persistence of the main degradation metabolite hydroxyatrazine. Future studies should seek alternative controls that drive the observed atrazine persistence in soil. This work helps to bridge the gap between engineered and natural systems, allowing us to use laboratory setups to gain insight into real environmental systems.

show abstract

Deep Learning Neural Network Approach for Predicting the Sorption of Ionizable and Polar Organic Pollutants to a Wide Range of Carbonaceous Materials

Cited by 124 publications

References 67 publications

Modelling of the adsorption of urea herbicides by tropical soils with an Adaptive‐Neural‐based Fuzzy Inference System

Modelling of the adsorption of urea herbicides by tropical soils with an Adaptive‐Neural‐based Fuzzy Inference System

Rational Design of Molecularly Imprinted Polymers Using Quaternary Ammonium Cations for Glyphosate Detection

Modeling Bioavailability Limitations of Atrazine Degradation in Soils

Contact Info

Product

Resources

About