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 Video

Updated: Feb 24, 2026

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

2.9K

Rapid Life-Cycle Impact Screening Using Artificial Neural Networks.

Runsheng Song1, Arturo A Keller1, Sangwon Suh1

  • 1Bren School of Environmental Science and Management, University of California , Santa Barbara, California 93106, United States.

Environmental Science & Technology
|August 16, 2017
PubMed
Summary

Artificial neural network (ANN) models estimate chemical life-cycle impacts using molecular structures. These models show promise for screening environmental and health impacts, especially when data is limited.

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

Countering the Faltering Ability of Warming Oceans to Absorb CO<sub>2</sub> by Adding Silica and Other Nanoparticles.

Environmental science & technology·2026
Same author

Metabolomic profiling of diatoms reveals distinct impacts of silver nanoparticles and ions.

Environmental science. Nano·2026
Same author

Biochar Reduces Nanoplastics Uptake by Lettuce and Alleviates Its Toxicity to the Plant.

Journal of agricultural and food chemistry·2026
Same author

The importance of multiregional accounting for corporate carbon emissions.

Nature communications·2025
Same author

Correction: Sustainable valorization of fish head wastes into nitrogen-based nutrients: a comparative life cycle assessment.

Journal of biological engineering·2025
Same author

CuO@SiO<sub>2</sub> Seed Priming Enhances Drought Tolerance and Phosphorus Acquisition Efficiency of Maize.

Environmental science & technology·2025

Area of Science:

  • Environmental Science
  • Computational Chemistry
  • Chemical Engineering

Background:

  • The rapid increase in chemical production outpaces the understanding of their life-cycle impacts.
  • Accurate assessment of chemical impacts is crucial for sustainable development and risk management.

Purpose of the Study:

  • To develop and validate deep artificial neural network (ANN) models for estimating the life-cycle impacts of chemicals.
  • To identify the most effective methods for selecting molecular descriptors for ANN models.
  • To define the application domain (AD) for reliable model predictions.

Main Methods:

  • Utilized multilayer artificial neural networks (ANNs) trained on molecular structure data.
  • Evaluated six key life-cycle impact categories: cumulative energy demand, global warming, acidification, human health, ecosystem quality, and eco-indicator 99.

Related Experiment Videos

Last Updated: Feb 24, 2026

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

2.9K
  • Compared three molecular descriptor selection approaches, identifying principal component analysis (PCA) as optimal.
  • Estimated the application domain (AD) for each impact category to ensure model reliability.

    • Main Results:

    • ANN models demonstrated good predictive performance for acidification (R²=0.73), human health (R²=0.71), and eco-indicator 99 (R²=0.87).
    • The global warming model showed lower performance (R²=0.48).
    • Principal component analysis (PCA) proved to be the most effective method for selecting molecular descriptors.

    Conclusions:

    • ANN models can serve as valuable initial screening tools for chemical life-cycle impacts, particularly in data-scarce situations.
    • The reliability of ANN predictions is dependent on the specific impact category and the defined application domain (AD).
    • Understanding and defining the AD is critical for accurate interpretation of ANN model outputs in chemical impact assessments.