English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/218382
Share/Impact:
Statistics
logo share SHARE logo core CORE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:

Title

From chemical structure to quantitative polymer properties prediction through convolutional neural networks

AuthorsMiccio, Luis A.; Schwartz, G. A.
KeywordsQSPR
Properties prediction
Deep learning
Neural network
Issue Date2020
PublisherElsevier
CitationPolymer 193: 122341 (2020)
AbstractIn this work convolutional-fully connected neural networks were designed and trained to predict the glass transition temperature of polymers based only on their chemical structure. This approach has shown to successfully predict the Tg of unknown polymers with average relative errors as low as 6%. Several networks with different architecture or hiperparameters were successfully trained using a previously studied glass transition temperatures dataset for validation, and then the same method was employed for an extended dataset, with larger Tg dispersion and polymer's structure variability. This approach has shown to be accurate and reliable, and does not require any time consuming or expensive measurements and calculations as inputs. Furthermore, it is expected that this method can be easily extended to predict other properties. The possibility of predicting the properties of polymers not even synthesized will save time and resources for industrial development as well as accelerate the scientific understanding of structure-properties relationships in polymer science.
Publisher version (URL)https://doi.org/10.1016/j.polymer.2020.122341
URIhttp://hdl.handle.net/10261/218382
DOIhttp://dx.doi.org/10.1016/j.polymer.2020.122341
ISSN0032-3861
Appears in Collections:(CFM) Artículos
Files in This Item:
File Description SizeFormat 
accesoRestringido.pdf59,24 kBAdobe PDFThumbnail
View/Open
Show full item record
Review this work
 


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.