From Intelligence to Sustainability: AI-Optimized Adhesives and Sealants for Next-Generation Green Buildings
Kartikeya Avinash Narkhede Avinash Narkhede
Paper Contents
Abstract
Adhesives and sealants, while frequently underestimated, are crucial for the effectiveness, longevity, and environmental friendliness of high-performance green buildings. This review thoroughly analyses their diverse contributions to energy efficiency, structural stability, indoor air quality, and lifecycle circularity. Conventional formulations, mainly derived from petroleum, present challenges due to the emission of volatile organic compounds (VOCs), restricted recyclability, and negative environmental impacts. New bio-based alternatives provide sustainability advantages but often fall short in terms of durability and performance.Artificial Intelligence (AI) and Machine Learning (ML) are revolutionizing the fields of formulation design, performance forecasting, and lifecycle assessment. Models driven by AI facilitate the optimization of adhesive systems across multiple objectives, ensuring a balance between mechanical strength, environmental compliance, and cost efficiency. The use of physics-informed ML frameworks and digital twins (DTs) significantly improves predictive maintenance and real-time monitoring of sealant joints, thereby prolonging service life and minimizing energy losses during operations. This review compiles recent developments in material chemistry, adhesion mechanics, durability modelling, and regulatory adherence, while also addressing techno-economic and ethical considerations. It promotes a systems-thinking perspective, emphasizing that adhesives and sealants should be regarded as vital elements in sustainable construction rather than mere peripheral components. Upcoming developments may include open-access datasets, reversible bonding chemistries, and AI-enhanced lifecycle design, which aim to close the divide between innovation and practical application.
Copyright
Copyright © 2025 Kartikeya Avinash Narkhede. This is an open access article distributed under the Creative Commons Attribution License.