Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

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

Sort by

Same author

Evaluation of Functionalized Birch Bark Extracts in Epoxy Thermosets.

Biomacromolecules·2026

Same author

Prehospital Resuscitation with Type O Whole Blood for Trauma and Hemorrhage.

The New England journal of medicine·2026

Same author

Designing cost-effective supply chains for plastics at the end-of-life.

Journal of cleaner production·2026

Same author

Transfusion in transit: A decade of prehospital blood transfusion in pediatric trauma.

The journal of trauma and acute care surgery·2026

Same author

Covert-attention shifting superseded: Simple visual search explained by a computational cognitive architecture with early vision limitations, eye movements, and task strategies.

Psychonomic bulletin & review·2026

Same author

Adding spatially-resolved characterization factors for ozone formation potential in the United States Environmental Protection Agency's tool for the reduction of chemical and other impacts.

The Science of the total environment·2026

Search research articles

Related Experiment Video

Updated: Jun 2, 2025

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

Regression tools for chemical release modeling: An additive manufacturing case study.

David E Meyer¹, Raymond L Smith¹, Elizabeth Lanphear²

¹Center for Environmental Solutions and Emergency Response, United States Environmental Protection Agency, Cincinnati, Ohio.

Journal of Occupational and Environmental Hygiene

|January 13, 2025

Summary

Estimating chemical releases using regression models is crucial for risk assessments. Various methods, including machine learning, accurately predicted volatile organic compound releases from 3D printing, informing exposure assessments.

Keywords:

Decision tree extrusion neural network process read-across process releases synthetic data

More Related Videos

Negative Additive Manufacturing of Complex Shaped Boron Carbides

Negative Additive Manufacturing of Complex Shaped Boron Carbides

Published on: September 18, 2018

A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars

A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars

Published on: August 4, 2018

Related Experiment Videos

Last Updated: Jun 2, 2025

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

Negative Additive Manufacturing of Complex Shaped Boron Carbides

Negative Additive Manufacturing of Complex Shaped Boron Carbides

Published on: September 18, 2018

A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars

A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars

Published on: August 4, 2018

Area of Science:

Environmental Science
Chemical Engineering
Data Science

Background:

Chemical release data are vital for industrial risk assessments but often unavailable.
Estimating these releases is necessary to understand potential exposures.

Purpose of the Study:

To explore the effectiveness of various regression methods for predicting chemical releases.
To inform chemical risk assessments using data from extrusion-based additive manufacturing.

Main Methods:

Assessed linear Least Squares, LASSO, Ridge regression, classification and regression tree, random forest, and neural network analysis.
Utilized secondary data on polymeric extrusion and evaluated synthetic data generation.
Tested model performance on a common dataset with varying features.

Main Results:

All assessed methods achieved predictions within 10% error for up to 98% of the test population.
Linear methods and neural networks performed well with fewer features; tree-based methods handled more features.
Including related process data improved predictions, while synthetic data showed minor gains.

Conclusions:

Regression modeling, including machine learning, shows promise for predicting chemical releases.
Model performance varies with feature selection, highlighting the need for careful feature engineering.
Future research should focus on primary data acquisition and model optimization for environmental release prediction.