Improving predictive modeling of polymeric materials using a hybrid approach of machine learning and expert intervention (9 pag.)

CRAVERO, FIORELLA; PONZONI, IGNACIO; DIAZ, MONICA FATIMA

Buenos Aires

Conferencia; 21th LACCEI International Multi-Conference for Engineering, Education and Technology (LACCEI 2023); 2023

The OAS Summit of Engineering for the Americas

This work describes a hybrid methodology that combines machine learning and the intervention of experts to improve the predictive modeling of properties of high interest of polymeric materials. Although these materials have many advantages, developing a new material with specific properties from a new molecular structure is very challenging and time-consuming and expensive. The demand for materials with very specific properties continues to grow, so machine learning techniques have been applied to predict these properties. The hybrid methodology was developed in an evolutionary way from an expert intervention at the end of the machine learning process, to a more decisive intervention throughout the cycle. This allows obtaining more robust and reliable models for the design of new materials, which can help designers obtain property profiles for prototypes prior to the synthesis stage, saving time and resources.