The synthesis of nanoscale particles and particle aggregates from liquid or gaseous precursors is affected by a variety of trade-off relations, for example, in terms of product composition, yield, or energy efficiency. Machine-supported process evaluation and learning (ML) of these relations enables optimization strategies for advanced material processing. Such a workflow is demonstrated on the example of plasma-assisted aerosol deposition (PAAD) of alumina powders. Depending on processing conditions, these powders comprise of hetero-aggregate mixtures of crystalline and amorphous polymorphs. Process optimization toward a specific target composition calls for ML approaches. For this, a sufficiently large and consistent dataset of PAAD input (processing) and output (product)parameters is initially generated by real-world processing, and subsequently extrapolated into a cloud of≈106input-output parameter matrices using Gaussian process regression with multivariate output and input-output feature analysis. It is subsequently demonstrated how not only the phase composition of the obtained alumina powders, but also product resilience to variations in specific processing parameters, or – as a perspective – the energy efficiency of material processing can be predicted.