Machine learning-based prediction of surface checks and bending properties in weathered thermally modified timber

Machine learning (ML)-based models, decision tree and ANFIS, were used to predict the degree of surface checking bending properties 30-month weathered thermally modified timber. The results showed that investigated initial board did not allow accurate predictions checks. ML regression clustering analysis confirmed important variables for dynamic stiffness, acoustic velocity, density lowest local modulus. models performed better than conventional timber grading, a prediction accuracy 80–90% stiffness 50–70% strength could be achieved.