On November 7-9, Prof. Marco Scavino will participate in KAUST recruiting activities developed by the Office of International Programs with visits to Tecnológico de Monterrey and Universidad Nacional Autónoma de México (UNAM).

On November 9 he will give a seminar at the Departamento de Probabilidad y Estadística, Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas (IIMAS), UNAM in Mexico City.


Title
Bayesian techniques for fatigue life prediction in metallic materials and for inference in linear PDEs with random boundary conditions.

Abstract
In this talk, we present, first, a statistical treatment of the data extracted from a set of records of fatigue experiments performed on aluminum alloys 75S-T6. Our primary goal is to predict the fatigue life of metallic materials, providing a systematic Bayesian approach for calibration and classification of the proposed models. Second, we introduce a method of hierarchical Bayesian inference to estimate the thermal properties of a wall. 
We apply our methodology to a case of an experimental study conducted in an environmental chamber. The results show that our technique reduces the bias error of the estimates of the parameters of the wall, compared to other approaches where the boundary conditions are assumed not random. The estimate of the information gain allows guiding the user in the efficient determination of the variables characterizing the experiment.