Artificial neural networks (ANN) coupled with ppLFERs (poly-parameter linear free energy relationships) provided an easy and powerful method for predicting aqueous adsorption on four most widely used adsorbents: biochar, CNTs, GAC, and resin. During the modeling process, two different data splitting approaches were compared and group-selection (rather than point-selection) was decided for the adsorption data splitting, which provided better consistency between the validation and test sets. Also, a cosine similarity approach, based on which only the data that shared high similarity with the test set were selected as the training set, was employed to further improve the accuracy of the prediction. Compared with the published results, ANN-ppLFERs could predict aqueous adsorption more accurately with the RMSE (root mean square error) values between 0.23 to 0.31 log unit, and the developed easy-to-use integrated GUI tool is user-friendly and can greatly enable non-modelers to conduct adsorption prediction. Overall, the well-improved results suggested a promising future of ANN-ppLFERs in aqueous adsorption prediction.

Predicting adsorption of organic contaminants on biochar, CNTs, GAC, and resins by artificial neural networks

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.