FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304014290> ?p ?o ?g. }

• W4304014290 endingPage "159348" @default.
• W4304014290 startingPage "159348" @default.
• W4304014290 abstract "Efficiency improvement in contaminant removal by nanofiltration (NF) and reverse osmosis (RO) membranes is a multidimensional process involving membrane material selection and experimental condition optimization. It is unrealistic to explore the contributions of diverse influencing factors to the removal rate by trial-and-error experimentation. However, the advanced machine learning (ML) method is a powerful tool to simulate this complex decision-making process. Here, 4 traditional learning algorithms (MLR, SVM, ANN, kNN) and 4 ensemble learning algorithms (RF, GBDT, XGBoost, LightGBM) were applied to predict the removal efficiency of contaminants. Results reported here demonstrate that ensemble models showed significantly better predictive performance than traditional models. More importantly, this study achieved a compelling tradeoff between accuracy and interpretability for ensemble models with an effective model interpretation approach, which revealed the mutual interaction mechanism between the membrane material, contaminants and experimental conditions in membrane separation. Additionally, feature selection was for the first time achieved based on the aforementioned model interpretation method to determine the most important variable influencing the contaminant removal rate. Ultimately, the four ensemble models retrained by the selected variables achieved distinguished prediction performance (R2adj = 92.4 %–99.5 %). MWCO (membrane molecular weight cut-off), McGowan volume of solute (V) and molecular weight (MW) of the compound were demonstrated to be the most important influencing factors in contaminant removal by the NF and RO processes. Overall, the proposed methods in this study can facilitate versatile complex decision-making processes in the environmental field, particularly in contaminant removal by advanced physicochemical separation processes." @default.
• W4304014290 created "2022-10-10" @default.
• W4304014290 creator A5011469016 @default.
• W4304014290 creator A5042305497 @default.
• W4304014290 creator A5059336561 @default.
• W4304014290 creator A5067046617 @default.
• W4304014290 creator A5071773009 @default.
• W4304014290 date "2023-01-01" @default.
• W4304014290 modified "2023-10-16" @default.
• W4304014290 title "Prediction of organic contaminant rejection by nanofiltration and reverse osmosis membranes using interpretable machine learning models" @default.
• W4304014290 cites W1489463871 @default.
• W4304014290 cites W1929018038 @default.
• W4304014290 cites W2004847971 @default.
• W4304014290 cites W2005020926 @default.
• W4304014290 cites W2019657322 @default.
• W4304014290 cites W2030949899 @default.
• W4304014290 cites W2034026260 @default.
• W4304014290 cites W2036599029 @default.
• W4304014290 cites W2037578666 @default.
• W4304014290 cites W2044617754 @default.
• W4304014290 cites W2062319810 @default.
• W4304014290 cites W2072274571 @default.
• W4304014290 cites W2073124248 @default.
• W4304014290 cites W2346821280 @default.
• W4304014290 cites W2501195055 @default.
• W4304014290 cites W2518757374 @default.
• W4304014290 cites W2526773060 @default.
• W4304014290 cites W2612927211 @default.
• W4304014290 cites W2751145381 @default.
• W4304014290 cites W2782357189 @default.
• W4304014290 cites W2793408059 @default.
• W4304014290 cites W2906922093 @default.
• W4304014290 cites W2909082795 @default.
• W4304014290 cites W2913323966 @default.
• W4304014290 cites W2917249005 @default.
• W4304014290 cites W2919841204 @default.
• W4304014290 cites W2973049920 @default.
• W4304014290 cites W2990405315 @default.
• W4304014290 cites W2998681661 @default.
• W4304014290 cites W2999615587 @default.
• W4304014290 cites W3013623430 @default.
• W4304014290 cites W3014900511 @default.
• W4304014290 cites W3015364947 @default.
• W4304014290 cites W3019326297 @default.
• W4304014290 cites W3031797850 @default.
• W4304014290 cites W3042493983 @default.
• W4304014290 cites W3047425455 @default.
• W4304014290 cites W3049235151 @default.
• W4304014290 cites W3085992613 @default.
• W4304014290 cites W3087070249 @default.
• W4304014290 cites W3093997868 @default.
• W4304014290 cites W3098733244 @default.
• W4304014290 cites W3100249628 @default.
• W4304014290 cites W3117144466 @default.
• W4304014290 cites W3118786697 @default.
• W4304014290 cites W3122993262 @default.
• W4304014290 cites W3129173798 @default.
• W4304014290 cites W3130219998 @default.
• W4304014290 cites W3131184440 @default.
• W4304014290 cites W3134637036 @default.
• W4304014290 cites W3139236016 @default.
• W4304014290 cites W3149531770 @default.
• W4304014290 cites W3153462804 @default.
• W4304014290 cites W3164963289 @default.
• W4304014290 cites W3170788003 @default.
• W4304014290 cites W3188971811 @default.
• W4304014290 cites W3197484245 @default.
• W4304014290 cites W3200542697 @default.
• W4304014290 cites W3200628952 @default.
• W4304014290 cites W3213699326 @default.
• W4304014290 cites W4200027750 @default.
• W4304014290 cites W4200450866 @default.
• W4304014290 cites W4205149203 @default.
• W4304014290 cites W4205684881 @default.
• W4304014290 cites W4210420816 @default.
• W4304014290 cites W4214951874 @default.
• W4304014290 cites W4280557848 @default.
• W4304014290 cites W4280610773 @default.
• W4304014290 doi "https://doi.org/10.1016/j.scitotenv.2022.159348" @default.
• W4304014290 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36228787" @default.
• W4304014290 hasPublicationYear "2023" @default.
• W4304014290 type Work @default.
• W4304014290 citedByCount "8" @default.
• W4304014290 countsByYear W43040142902023 @default.
• W4304014290 crossrefType "journal-article" @default.
• W4304014290 hasAuthorship W4304014290A5011469016 @default.
• W4304014290 hasAuthorship W4304014290A5042305497 @default.
• W4304014290 hasAuthorship W4304014290A5059336561 @default.
• W4304014290 hasAuthorship W4304014290A5067046617 @default.
• W4304014290 hasAuthorship W4304014290A5071773009 @default.
• W4304014290 hasConcept C111919701 @default.
• W4304014290 hasConcept C119857082 @default.
• W4304014290 hasConcept C119898033 @default.
• W4304014290 hasConcept C12267149 @default.
• W4304014290 hasConcept C127413603 @default.
• W4304014290 hasConcept C130797344 @default.
• W4304014290 hasConcept C146763847 @default.
• W4304014290 hasConcept C148483581 @default.

• next