Skip to main content
Journal cover image

Predicting emerging chemical content in consumer products using machine learning.

Publication ,  Journal Article
Thornton, LL; Carlson, DE; Wiesner, MR
Published in: The Science of the total environment
August 2022

Chemical ingredients in consumer products are continually changing. To understand our exposure to chemicals and their consequent risk, we need to know their concentrations in products, or chemical weight fractions. Unfortunately, manufacturers rarely report comprehensive weight fraction data on product labels. The goal of this study was to evaluate the utility of machine learning strategies for predicting weight fractions when chemical constituent data are limited. A "data-poor" framework was developed and tested using a small dataset on consumer products containing engineered nanomaterials to represent emerging substances. A second, more traditional framework was applied to a "data-rich" product dataset comprised of bulk-scale organic chemicals for comparison purposes. Feature variables included chemical properties, functional use categories (e.g., antimicrobial), product categories (e.g., makeup), product matrix categories, and whether weight fractions were manufacturer-reported or experimentally obtained. Classification into three weight fraction bins was done using a random forest or nonlinear support vector classifier. An ablation study revealed that functional use data improved predictive performance when included alongside chemical property data, suggesting the utility of functional use categories in evaluating the safety and sustainability of emerging chemicals. Models could roughly stratify material-product observations into order of magnitude weight fractions with moderate success; the best of these achieved an average balanced accuracy of 73% on the nanomaterials product data. Framework comparisons also revealed a positive trend in sample size versus average balanced accuracy, suggesting great promise for machine learning approaches with continued investment in chemical data collection.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

The Science of the total environment

DOI

EISSN

1879-1026

ISSN

0048-9697

Publication Date

August 2022

Volume

834

Start / End Page

154849

Related Subject Headings

  • Organic Chemicals
  • Machine Learning
  • Environmental Sciences
  • Environmental Exposure
  • Consumer Product Safety
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Thornton, L. L., Carlson, D. E., & Wiesner, M. R. (2022). Predicting emerging chemical content in consumer products using machine learning. The Science of the Total Environment, 834, 154849. https://doi.org/10.1016/j.scitotenv.2022.154849
Thornton, Luka Lila, David E. Carlson, and Mark R. Wiesner. “Predicting emerging chemical content in consumer products using machine learning.The Science of the Total Environment 834 (August 2022): 154849. https://doi.org/10.1016/j.scitotenv.2022.154849.
Thornton LL, Carlson DE, Wiesner MR. Predicting emerging chemical content in consumer products using machine learning. The Science of the total environment. 2022 Aug;834:154849.
Thornton, Luka Lila, et al. “Predicting emerging chemical content in consumer products using machine learning.The Science of the Total Environment, vol. 834, Aug. 2022, p. 154849. Epmc, doi:10.1016/j.scitotenv.2022.154849.
Thornton LL, Carlson DE, Wiesner MR. Predicting emerging chemical content in consumer products using machine learning. The Science of the total environment. 2022 Aug;834:154849.
Journal cover image

Published In

The Science of the total environment

DOI

EISSN

1879-1026

ISSN

0048-9697

Publication Date

August 2022

Volume

834

Start / End Page

154849

Related Subject Headings

  • Organic Chemicals
  • Machine Learning
  • Environmental Sciences
  • Environmental Exposure
  • Consumer Product Safety