Aeration, while fundamental for the widely used activated sludge (AS) process, is a particularly energy-intensive operation in the typical wastewater treatment plant. Consequently, the development of predictive models is highly desirable for the improvement of the mechanistic understanding of the overall AS process as well as for the optimization of said operation. This is, in turn, critical for the reduction of the environmental impact and general operational costs of wastewater treatment. Unfortunately, the traditional engineering practice has relied on the usage of global oxygen transfer coefficients (K L a) corrected by empirical factors, which disregards the spatial heterogeneity induced by an evolving bubble size distribution (BSD) and often fails at capturing the impact of the sludge's viscosity. The result is that predictive power is often lacking. Accordingly, this work presents a modeling methodology based on the population balance framework aimed at efficiently predicting the K L a under realistic combinations of process conditions and considering the mentioned spatial effects. The model was calibrated and validated with experimental data measured in a bubble column reactor, and its main numerical characteristics were evaluated. The proposed methodology was found to be capable of producing accurate predictions of the changes in the BSD along the analyzed column and of the emergent oxygen transfer coefficients. Since this approach is computationally cheap and able to incorporate underlying physicochemical driving forces, it can be a valuable complement to traditional aeration models, and it potentially opens the door to more robust predictions of the performance of the AS process.