Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Esters flash point prediction using artificial neural networks.

Gonzalo Astray1, Juan F Gálvez, Juan C Mejuto

  • 1Department of Physical Chemistry, Faculty of Sciences, University of Vigo, 32004 Ourense, Spain.

Journal of Computational Chemistry
|September 29, 2012
PubMed
Summary

An artificial neural network accurately predicts ester flash points using four variables. This model shows high accuracy for both training and testing datasets, aiding chemical safety assessments.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Food Authenticity Models for <i>Mytilus galloprovincialis</i> (Mediterranean Mussel): Exploratory Study.

Foods (Basel, Switzerland)·2025
Same author

Exploring the mechanism of flavonoids modification by dimerization strategies and their potential to enhance biological activity.

Food chemistry·2024
Same author

Machine Learning Models to Classify Shiitake Mushrooms (<i>Lentinula edodes</i>) According to Their Geographical Origin Labeling.

Foods (Basel, Switzerland)·2024
Same author

Modelling Polyphenol Extraction through Ultrasound-Assisted Extraction by Machine Learning in <i>Olea europaea</i> Leaves.

Foods (Basel, Switzerland)·2023
Same author

Oxidation of Aldehydes Used as Food Additives by Peroxynitrite.

Antioxidants (Basel, Switzerland)·2023
Same author

Machine Learning to Predict the Adsorption Capacity of Microplastics.

Nanomaterials (Basel, Switzerland)·2023

Area of Science:

  • Chemical Engineering
  • Computational Chemistry
  • Machine Learning Applications

Background:

  • Flash point is a critical safety parameter for esters.
  • Accurate prediction of flash point is essential for safe handling and storage.
  • Existing methods for flash point determination can be time-consuming or require specific equipment.

Purpose of the Study:

  • To develop and implement an artificial neural network (ANN) for predicting the flash point of esters.
  • To identify key variables influencing ester flash points.
  • To validate the predictive accuracy of the developed ANN model.

Main Methods:

  • An artificial neural network (ANN) model was designed and implemented.
  • The ANN utilized a 4-5-8-5-1 topology.

Related Experiment Videos

  • Four distinct variables were employed as inputs for the model development.

    • Main Results:

    • The developed ANN achieved a high square correlation coefficient (R(2)) of 0.99 during training.
    • The root mean square error (RMSE) was 5.46 K for the training set.
    • For the testing set, the ANN demonstrated strong performance with R(2) of 0.96 and RMSE of 13.02 K.

    Conclusions:

    • The artificial neural network model effectively predicts ester flash points.
    • The model's high accuracy suggests its utility in chemical safety assessments.
    • The developed ANN offers a reliable computational tool for ester flash point prediction.