Films based on crosslinked TEMPO-oxidized cellulose and predictive analysis via machine learning

Merve Özkan; Maryam Borghei; Alp Karakoç; Orlando J. Rojas; Jouni Paltakari

doi:10.1038/s41598-018-23114-x

Films based on crosslinked TEMPO-oxidized cellulose and predictive analysis via machine learning

Merve Özkan^*, Maryam Borghei, Alp Karakoç, Orlando J. Rojas, Jouni Paltakari

^*Corresponding author for this work

Research output: Contribution to journal › Article › Scientific › peer-review

27 Citations (Scopus)

230 Downloads (Pure)

Abstract

We systematically investigated the effect of film-forming polyvinyl alcohol and crosslinkers, glyoxal and ammonium zirconium carbonate, on the optical and surface properties of films produced from TEMPO-oxidized cellulose nanofibers (TOCNFs). In this regard, UV-light transmittance, surface roughness and wetting behavior of the films were assessed. Optimization was carried out as a function of film composition following the "random forest" machine learning algorithm for regression analysis. As a result, the design of tailor-made TOCNF-based films can be achieved with reduced experimental expenditure. We envision this approach to be useful in facilitating adoption of TOCNF for the design of emerging flexible electronics, and related platforms.

Original language	English
Article number	4748
Journal	Scientific Reports
Volume	8
Issue number	1
DOIs	https://doi.org/10.1038/s41598-018-23114-x
Publication status	Published - 1 Dec 2018
MoE publication type	A1 Journal article-refereed

Access to Document

10.1038/s41598-018-23114-x

CHEM-Ozkan-et al-Films based-Scientific Reports-2018Final published version, 3.16 MBLicence: CC BY

Cite this

@article{cd37fc95fe7e4b69a7fcb858b9feaf19,

title = "Films based on crosslinked TEMPO-oxidized cellulose and predictive analysis via machine learning",

abstract = "We systematically investigated the effect of film-forming polyvinyl alcohol and crosslinkers, glyoxal and ammonium zirconium carbonate, on the optical and surface properties of films produced from TEMPO-oxidized cellulose nanofibers (TOCNFs). In this regard, UV-light transmittance, surface roughness and wetting behavior of the films were assessed. Optimization was carried out as a function of film composition following the {"}random forest{"} machine learning algorithm for regression analysis. As a result, the design of tailor-made TOCNF-based films can be achieved with reduced experimental expenditure. We envision this approach to be useful in facilitating adoption of TOCNF for the design of emerging flexible electronics, and related platforms.",

author = "Merve {\"O}zkan and Maryam Borghei and Alp Karako{\c c} and Rojas, {Orlando J.} and Jouni Paltakari",

year = "2018",

month = dec,

day = "1",

doi = "10.1038/s41598-018-23114-x",

language = "English",

volume = "8",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Portfolio",

number = "1",

}

TY - JOUR

T1 - Films based on crosslinked TEMPO-oxidized cellulose and predictive analysis via machine learning

AU - Özkan, Merve

AU - Borghei, Maryam

AU - Karakoç, Alp

AU - Rojas, Orlando J.

AU - Paltakari, Jouni

PY - 2018/12/1

Y1 - 2018/12/1

N2 - We systematically investigated the effect of film-forming polyvinyl alcohol and crosslinkers, glyoxal and ammonium zirconium carbonate, on the optical and surface properties of films produced from TEMPO-oxidized cellulose nanofibers (TOCNFs). In this regard, UV-light transmittance, surface roughness and wetting behavior of the films were assessed. Optimization was carried out as a function of film composition following the "random forest" machine learning algorithm for regression analysis. As a result, the design of tailor-made TOCNF-based films can be achieved with reduced experimental expenditure. We envision this approach to be useful in facilitating adoption of TOCNF for the design of emerging flexible electronics, and related platforms.

AB - We systematically investigated the effect of film-forming polyvinyl alcohol and crosslinkers, glyoxal and ammonium zirconium carbonate, on the optical and surface properties of films produced from TEMPO-oxidized cellulose nanofibers (TOCNFs). In this regard, UV-light transmittance, surface roughness and wetting behavior of the films were assessed. Optimization was carried out as a function of film composition following the "random forest" machine learning algorithm for regression analysis. As a result, the design of tailor-made TOCNF-based films can be achieved with reduced experimental expenditure. We envision this approach to be useful in facilitating adoption of TOCNF for the design of emerging flexible electronics, and related platforms.

UR - http://www.scopus.com/inward/record.url?scp=85044281478&partnerID=8YFLogxK

U2 - 10.1038/s41598-018-23114-x

DO - 10.1038/s41598-018-23114-x

M3 - Article

AN - SCOPUS:85044281478

SN - 2045-2322

VL - 8

JO - Scientific Reports

JF - Scientific Reports

IS - 1

M1 - 4748

ER -

Films based on crosslinked TEMPO-oxidized cellulose and predictive analysis via machine learning

Abstract

Access to Document

Other files and links

Fingerprint

Bioeconomy Research Infrastructure

Cite this

Films based on crosslinked TEMPO-oxidized cellulose and predictive analysis via machine learning

Abstract

Access to Document

Other files and links

Fingerprint

Equipment

Bioeconomy Research Infrastructure

Cite this