To enhance development efficiency for hot-melt adhesives, adaptive design of experiments based on Bayesian optimization was applied to formulation design, and its effectiveness was evaluated. The results demonstrated the successful identification of a formulation capable of meeting the conflicting target properties of low viscosity and high adhesive strength, which are considered difficult to achieve simultaneously, within just four experimental cycles. This outcome is likely attributable to the construction of a highly accurate machine learning model using Gaussian process regression, which may have effectively captured the objective function within the formulation space. As a result, the exploration of the formulation space through Bayesian optimization was highly efficient, and the target values were achieved with an exceptionally small number of experiments. These findings suggest that experimental design using Bayesian optimization is a highly effective approach for the development of hot-melt adhesives.

The deadline for achieving the Sustainable Development Goals（SDGs）is approaching, and realistic and immediate responses are required. In particular, concrete measures to address environmental issues such as microplastics and marine plastics are one of the most urgent issues. In the cutting-edge research field of polymer synthesis, attention is focused on how to impart degradability to conventionally used non-degradable synthetic polymers, and competitive efforts are underway around the world to design molecules and develop reactions to incorporate decomposition functions into molecules at the polymer synthesis stage. In this review, we focus on imparting degradability to vinyl polymers synthesized by radical polymerization. After explaining the basic matters related to the decomposition of vinyl polymers, we introduce degradable polymers using radical ring-opening polymerization and radical copolymerization. Research trends in controlled polymerization and depolymerization are also explained.