AI-Driven Design and Green Preparation of Bio-Based Fire-Safe Polymeric Materials

This work introduces, for the first time, an innovative bio-based flame retardant (FR) system forbiocomposites, leveraging experimental insights and machine learning (ML) to optimize both compositionand performance. By integrating a computationally guided, cost-efficient experimentationstrategy, we systematically combine design of experiments for space exploration, ML-driven propertyprediction, and optimization techniques to rapidly identify high-performance formulations. Ourapproach enhances mechanical strength while significantly improving fire safety, minimizing relianceon resource-intensive trial-and-error processes. The optimal formulation achieved an 18.4% increasein tensile strength (TS) and a 53.1% reduction in the peak heat release rate (pHRR) comparedto the pure polymer. Bayesian optimization validated the individually optimal solutions, achievingup to a 22.3% improvement in TS and a 73.7% reduction in pHRR. This research establishes adigitally integrated workflow that harnesses AI-driven predictive analytics and iterative optimizationto accelerate the development of sustainable, high-performance biocomposites and bio-based flameretardants, offering eco-friendly alternatives to conventional fire-safe polymeric materials.