Companies specialising in coatings, adhesives and sealants, together with their suppliers, are facing a combination of long-standing and new challenges. They must react quickly to changing customer demands while balancing cost and performance. At the same time, ambitious sustainability goals and new regulatory frameworks require the replacement of restricted substances and the redesign of existing formulations. Adding to this complexity, a generational shift in laboratories is making the transfer of expert knowledge to new employees increasingly urgent.
Against this backdrop, there is a growing need to accelerate research and development processes. New digital tools are emerging to help identify substitute ingredients, optimise multiple objectives at once, and ensure structured knowledge sharing within R&D teams. AI platforms tailored to chemistry-driven industries are already proving effective in this context.
Optimising complex systems faster
One global construction chemicals company used an AI platform to optimise a multi-layer coating system. The goal was to improve stability without compromising essential mechanical and functional properties. By combining domain expertise with machine learning, the team modelled each layer and the system as a whole. As a result, the development timeline was cut by more than 50 %, showing how AI can significantly accelerate innovation cycles.
Another case comes from the adhesives and sealants sector: a global manufacturer needed to reformulate a pressure-sensitive adhesive to eliminate PFAS while maintaining high performance. Initially planned as a five-year project, the company applied AI to screen millions of small molecules and identify promising candidates. Within four months a viable option was found, reducing the development time from five years to just two.
Event tip: Digitalisation
Digital tools are revolutionising coatings development – from formulation and testing to data analysis and quality assurance. TheEC Conference “Digitalisation in Coatings Formulation – Automation and Data Tools in R&D Labs and Quality Control”, taking place on 5–6 November in Cologne, will showcase how automation and digital systems can boost efficiency, accuracy and innovation speed. The event is aimed at laboratory managers, R&D teams, production specialists and anyone looking to specialise in digitally supported processes. In addition to expert presentations on current trends and developments, the conference offers valuable opportunities to exchange ideas directly with industry professionals.
Improving efficiency and market responsiveness
Raw material suppliers are also using AI to strengthen competitiveness. An industrial minerals company optimised its production line settings through AI models, cutting overall manufacturing costs by 20 % while reducing energy use and carbon footprint. At the same time, the company shortened the formulation development cycle for new coatings from six months to one month. This agility enabled faster adaptation to regional market needs without compromising quality.
Sequential learning is another approach showing strong results. In collaboration with California Polytechnic State University, researchers replaced alkylphenol ethoxylate (APEO) surfactants with more environmentally benign alternatives. By combining existing experimental data with AI models and running three sequential learning rounds (twelve experiments in total), they achieved the required stability, rheology and gloss with completely new surfactants.
Data quality as a key factor
Successful AI deployment in coatings development depends on the quality and structure of available data. Contrary to common belief, large datasets are not always required: projects can often start with as few as 20 well-documented data points. Precise material and process histories, accurate property measurements and inclusion of both successful and failed experiments help models identify meaningful cause-and-effect relationships.
Unlike general “big data” systems, these specialised AI platforms are designed to work with smaller, chemistry-aware datasets. They can incorporate expert input to build predictive models for formulation and process optimisation, even where experiments are costly and data volume is limited.
Strategic role of AI in the coatings industry
The coatings, adhesives and sealants sector is at a crossroads, facing traditional performance and cost challenges alongside sustainability targets and stricter regulations. AI platforms provide a strategic tool to shorten development cycles, support regulatory compliance, and preserve critical know-how. For many companies, adopting AI is becoming an essential step to remain competitive in a rapidly changing market.
link