Comment on Predicting Aqueous Adsorption of Organic Compounds onto Biochars, Carbon Nanotubes, Granular Activated Carbons, And Resins with Machine Learning

Gabriel Sigmund, Mehdi Gharasoo, Thorsten Hüffer, Thilo Hofmann (Corresponding author)

Publications: Contribution to journalCorrectionPeer Reviewed

Abstract

Zhang et al.1 published a paper on machine learning basedpredictions of organic contaminant sorption ontocarbonaceous materials and resins. The authors provide anovel approach to predict concentration-dependent sorptiondistribution coefficients (KD) to these materials, without theneed to link it to any specific isotherm model. This study is avaluable contribution to the field that can stimulate thescientific discussion in the adsorption-modeling communityregarding (i) mechanistic assumptions prior to model building,(ii) the parametrization of the model based on theseassumptions, (iii) the grouping of data to train the algorithm,and (iv) data filtering strategies. We recently published a paperon a similar topic2 and are confident that this discussion isvaluable to improve the future applicability of machine learningtechniques to sorption phenomena.
Original languageEnglish
Pages (from-to)11636-11637
Number of pages2
JournalEnvironmental Science & Technology
Volume54
Issue number18
DOIs
Publication statusPublished - 15 Sept 2020

Austrian Fields of Science 2012

  • 105906 Environmental geosciences

Keywords

  • sorption
  • Organic compounds
  • Sorbents
  • Machine Learning
  • Materials

Fingerprint

Dive into the research topics of 'Comment on Predicting Aqueous Adsorption of Organic Compounds onto Biochars, Carbon Nanotubes, Granular Activated Carbons, And Resins with Machine Learning'. Together they form a unique fingerprint.

Cite this