Researchers are unlocking a lot of new knowledge about these versatile materials. They are leveraging the power of artificial intelligence (AI) to drive their work in civil and environmental engineering. A recent study published by Winston Lindqwister and colleagues, titled “Chemical Homogenization for Nonmixing Reactive Interfaces in Porous Media,” appears in ACS Omega. The remainder of this paper will focus on the expansive potential for AI to supplement human analysis of the intricate labyrinths formed by porous media. It further forecasts their conduct in different applications, from building to battery design.
Research in the physics and chemistry of porous media have wide-ranging implications given their ubiquitous nature in both natural and engineered systems. These materials have arbitrary internal architectures that look like Swiss cheese. Their special microstructures are highly hierarchical and multiscale, featuring four prominent characteristics that could be easily understood and characterized. The research team, consisting of Laura Dalton, Manolis Veveakis, and Ken Gall, stress the importance of these features. They find these aspects to be incredibly important for synthesizing a comprehensive understanding of contents material characteristics.
Research Collaboration and AI Integration
Dalton, Veveakis and Gall have collaborated to create a series of highly influential papers. These models have all led to publications in high impact journals like Communications Engineering, ACS Omega, and the Philosophical Transactions of the Royal Society A. Dalton, who is assistant director of CEE’s Julie Ann Wrigley Global Institute of Sustainability, couldn’t be more excited about the research.
“The results of these papers make me hopeful and excited!” – Laura Dalton
One particularly cool thing about their work is how they’re using AI. In particular, they want to understand how well the internal architectures of these porous materials direct certain chemical reactions to occur. The team seized on a particularly mighty recent mathematical theorem. Familiarity with these four microstructural features drastically improves the material optimization process.
The collaborative research effort has produced multiple papers, with Lindqwister’s study focusing on chemical homogenization and another significant paper titled “Predicting compressive stress-strain behavior of elasto-plastic porous media via morphology-informed neural networks” published in Communications Engineering. The DOI for the ACS Omega paper DOI 10.1021/acsomega.5c00641, DOI for the other paper DOI 10.1038/s44172-025-00410-9.
Implications for Engineering and Design
Alongside these increases in efficiency and effectiveness, the research findings present a powerful opportunity to level up material design processes across disciplines. Dalton emphasized the opportunity to use their results to make complicated design problems very simple.
“So the fact our results suggest that we can simplify a complicated design challenge to four features is remarkable.” – Laura Dalton
QinYi (Emma) Tian, one of the study’s authors, emphasized the great promise but the risk that AI models present. Most importantly, she highlighted their unique capacity for foreshadowing fundamental material qualities prerequisite for any structural durability.
“The AI model showed strong potential in reliably predicting the four features needed for a given strength,” – QinYi (Emma) Tian
The implications go beyond the ivory tower – they have serious impacts on practical engineering applications. As Dalton clarified, the old ways of weighting safety factors used to drive a lot of ineffectively applied resources. Using better predictive tools based on their research, engineers would be able to optimize designs and use less material without sacrificing safety.
“However, these safety factors also lead to inefficient use of materials, time, labor and money. With these predictive tools, engineers can optimize a structurally sound design with fewer materials and in a fraction of the time.” – Laura Dalton
Future Directions and Applications
Looking toward the future, the research team is hoping that their discoveries will inform other industries where porous materials are key players. For example, deep geothermal energy projects require consistent accurate data from the samples found deep underground, making the need for high-quality supply chain data crucial.
“When you’re working on a geothermal energy project, you often only get one sample from, say, 2,000 feet beneath the earth, and you have to extract as much information about it as you can,” – Manolis Veveakis
With AI integration, it speeds up the analysis process up to 100 times. It further improves the precision of predictions regarding the performance of materials based on their properties. Lindqwister highlighted how these developments have the potential to be truly transformative.
“If we can reliably predict a majority of a material’s response based on just a few structural features, we can dramatically streamline the design process,” – Winston Lindqwister
He noted that this research, paired with other emerging technologies such as 3D printing, creates new potential opportunities. It provides an opportunity for unprecedented control over customizing structures to address uniquely defined engineering objectives.