No abstract

Computational data science , especially the machine learning approach has been a major contribution to the field of engineering. In this study, data mining and machine learning were practiced estimating the partitioning of Per- and Poly-fluoroalkyl Substances (PFAS) compounds during aqueous adsorption on various adsorbent materials with a vision to potentially replace the time-consuming and labor-intensive adsorption experiments. Regression models, such as linear, tree, support vector machine (SVM), ensemble of trees, and gaussian process regression (GPR) models were trained and tested using previously published data. 290 data points and 170 data points for activated carbon and mineral adsorbents, respectively, were mined for training the models and 10 data points were used to test the trained models. Statistical parameters, such as Root-Mean-Square Error (RSME), R-Squared, Mean Average Error (MAE), Mean Squared Error (MSE), etc., were used to compare the regression models. It was found that rational quadratic GPR (R-squared = 0.9966) and fine regression tree (R-Squared = 0.9427) models had the highest estimation accuracy for carbon-based and mineral-based adsorbents, respectively. These models were then validated for prediction accuracy using 10 data points from previous studies as an outer test set. Rational quadratic GPR was able to achieve 99% prediction accuracy for carbon-based adsorbent, while fine tree regression model was able to achieve 94% prediction accuracy. Despite such high estimation accuracy, the data mining process revealed the data shortage and the need for more research on PFAS adsorption to present real-world models. This study, as one of the first, shed a light on the determination of key parameters in aquatic chemistry with data mining and machine learning approaches.

No abstract

No abstract

Per and Poly-fluoroalkyl Substances (PFAS) has been a major subject of research in environmental sector ever since it was found in the environment and blood serums at toxic levels. As landfills are the final disposal method for majority of the waste, PFAS concentration in landfill leachate have been found in the range of few µg/L to mg/L. Only few conventional treatments such as Activated Carbon, Reverse Osmosis, and Ion-Exchange has been proven effective in removing PFAS. However, these treatment methods are proving to be very expensive and generate secondary contamination that needs to be disposed-off or treated. Since the phase out of C8-PFAS compounds, more short chain PFAS compounds are detected in landfill leachate. Hence, an effective treatment strategy is needed to keep up with the rising concentration levels and variety of PFAS compounds. The purpose of this study was to develop a sustainable and cost-effective process using modified Coal Fly-Ash (CFA) that can treat both short chain and long chain PFAS compounds. Previous studies have shown application of CFA in removal of dye and metals from different types of wastewaters. In previous studies CFA was modified to enhance its surface properties, that can improve the adsorption of organic and anionic contaminants. In this study, thermo-chemical modification was used on CFA to remove organic matter and PFAS compounds. Preliminary results showed that, CFA can remove more than 90% UV absorbance, more than 80% TOC and approximately 40% of total PFAS compounds. The maximum adsorption capacity for total PFAS was found to be 84 ng PFAS per g CFA, out of which 70 ng was for short chain PFAS and 14 ng for long chain PFAS compounds. An effective removal of organic matter and PFAS compounds, show a promising application of CFA in leachate treatment. However, further research is needed to analyze the adsorption dynamics, kinetics, post-treatment disposal method, and any possible contamination when mixing CFA with landfill leachate.