12. Jan 2026

Huntsman using AI to accelerate SPF fire-performance testing

Huntsman using AI to accelerate SPF fire-performance testing

Huntsman Building Solutions has used the Citrine Platform to reduce reliance on full-scale fire testing, shortened development time and deliver a high-performing, sprayable, and regulation-compliant foam.

Huntsman Building Solutions is using artificial intelligence to transform how fire performance is modelled and developed for spray polyurethane foam (SPF) insulation, reducing reliance on costly and time-consuming large-scale fire tests while improving formulation efficiency. The work is being carried out with the Citrine Platform, an AI-driven materials informatics system designed to integrate experimental data with predictive analytics.

Meeting fire safety standards such as ASTM E-84—which evaluates flame spread and smoke development—is a critical step in certifying spray polyurethane foams for building insulation applications. Traditional development workflows rely on sequential small-scale tests followed by independent full-scale fire tests, a process that can take months and incur significant expense. Huntsman’s goal was to establish a data-driven framework that married deep chemical understanding with rapid iterative modelling to accelerate this cycle.

By training AI models on a combination of small-scale fire test data, formulation inputs and material descriptors such as ingredient ratios and molecular fingerprints, the Citrine Platform can predict performance outcomes including flame spread, smoke development and thermal insulation (R-value). Engineers then use sequential learning—an iterative workflow where model suggestions guide laboratory experiments—and re-ingest new results into the system to refine predictions and prioritise the most promising formulation paths.

One output of this AI-assisted development was the R1.3-FR formulation, an adapted version of a starting formulation (AI002) that showed significantly improved fire resistance in independent large-scale testing while maintaining sprayability and physical performance targets. Huntsman reports that the AI workflow has reduced wasted effort, improved materials understanding, and shortened development lead times.

“This makes AI/ML partners in innovation, not just a recommender,” said Rogerio Drummond De Souza, technical director of Specialties and Roofing Products at Huntsman, underscoring the role of machine learning as an active contributor to formulation strategy.

Photo by Max Kukurudziak on Unsplash

Citrine Informatics 

Privacy settings

We use cookies on this website that are necessary for the operation of the website and therefore cannot be deselected. If you would like to know which cookies these are, you will find them listed individually in the privacy policy. Our website also uses external components that may set cookies. By loading external components, data about your behaviour can be collected by third parties, which is why we need your consent. Without your permission, there may be restrictions on content and operation. Detailed information can be found in our privacy policy.

Necessary cookies are always loaded