Machine learning guided formulation design of digital light processing printable elastomers beyond viscosity stretchability tradeoff

The development of high-performance resins for vat photopolymerization-based three-dimensional printing is constrained by coupled trade-offs among viscosity, curing kinetics, and mechanical properties. Material discovery is often limited because conventional printing-based screening cannot evaluate formulations that are highly viscous or slow-curing. This study introduces a data-efficient workflow linking small-volume formulation screening, machine-learning optimization, and functional validation for constraint-aware design. By using a systematic library of formulations spanning printable and non-printable regimes, small-volume mold curing decouples material characterization from printing limitations to expand the training domain. Regression models trained on viscosity, curing time, elongation at break and tensile modulus identify an optimized formulation with suitable processability and high stretchability. Thermomechanical analyses reveal a homogeneous network and improved stability, while printed components exhibit robust durability. In this work, we show that a generalizable blueprint for rapid photopolymer formulation enables the constraint-aware design of functional materials for soft robotics and programmable three-dimensional devices. 3D printing is promising method for material design, though optimizing properties is challenging to evaluate formulations Here the authors use a machine learning method for formulation screening in a printing method.