New Scientific Publication:
Revised WKI formula for predicting formaldehyde emissions from wood-based panels published

Braunschweig, August 13, 2026

In the article titled “Prediction of formaldehyde emissions from wood-based panels containing amino plastic resins using non-linear regression analysis and machine learning”, the authors Prof. Dr. Tunga Salthammer and Bettina Meyer present the results of the research project “WKI Equation – Revision 2” (Project No.: 11-37669), which was co-funded by the iVTH. The study has been published in the renowned journal *Chemosphere* and is freely available to the scientific community as an open-access publication.

The paper focuses on the further development of the established WKI formula for predicting formaldehyde emissions from wood-based panels with aminoplastic resins. Using nonlinear regression analysis and modern machine learning methods, the model was significantly improved and expanded.

Highlights:

• The methods allow for the conversion of formaldehyde emission rates to different test chamber conditions.
• An equation for particleboard has been successfully applied to MDF and plywood.
• The expanded training dataset enables broader application with regard to chamber testing.
• To this end, neural network regression is more functional than non-linear regression.
• Given four input parameters, four hidden layers, each with four neurons, were identified as optimal.

The project received financial support from the iVTH.

The publication is freely accessible under a CC BY-NC-ND license and can be viewed free of charge by anyone interested: https://www.sciencedirect.com/science/article/pii/S0045653526002195