Seminar: Thomas Wutzler

Parameter learning is a special case of hybrid models, where a machine learning model uses known site covariates, to predict a subset of the unknown parameters of the process based model. The analyst is interested in both, the uncertainty of hybrid model predictions, and the uncertainty of process-model parameters, including their correlations (posterior). For example consider a soil organic matter process-model that predicts carbon stocks for different sites. We need to parameterize the unknown carbon use efficiency (CUE) of the soil microbial community that differs by site, but is hypothesized to correlate with climate variables and pedogenic factors, such as clay content.We apply a machine learning model to estimate CUE and fit it end-to-end with other parameters of the process-model to observed carbon stocks. In addtion to the predicted CUE, we are interested in the uncertainty of CUE and its correlation with other parameters.This talk introduces the HybridVariationalInference method to quantify uncertainty of such cases.