This document describes a multi-stage stochastic programming approach for production planning under uncertainty in raw material quality and demand. It models demand uncertainty as a scenario tree where each stage represents a cluster of time periods with stationary demand behavior. Yield uncertainty is modeled as scenarios with stationary probability distributions. The yield scenarios are then integrated into the demand scenario tree to form a hybrid tree. The proposed multi-stage stochastic programming model allows full recourse for demand scenarios and simple recourse for yield scenarios to reflect differences in available information over time. The model aims to minimize inventory and production costs while meeting demand, capacity, and inventory constraints under the uncertainty.