ML-surrogate modeling for the estimation of random system performance parameter progress by the Chained Gaussian Process Regression method

The ability to accurately forecast productivity parameters is of great importance in various fields, such as engineering designs and structures, workforce management, and economic analysis. However, forecasting such parameters is challenging due to their inherent stochastic nature and time dependence, as well as the presence of heteroscedasticity in data. In this study, we aim to address these challenges by developing a surrogate model that can effectively predict the productivity parameter, taking into account its random process over time and heteroscedastic characteristics.