<p>Variational quantum algorithms (VQAs) are hybrid algorithms that combine quantum computing capabilities with classical machine learning (ML) tasks, utilizing classical optimizers to train parametrized quantum circuits. This work demonstrates their practical utility by addressing regression tasks in an industrially relevant context: modelling dendritic solidification in metals, a process crucial for determining mechanical properties in additive manufacturing. By comparing a classical surrogate model based on extreme gradient boosting with a hybrid classical-quantum VQA model, this work shows that VQAs can serve as a viable alternative for computationally expensive surrogate modelling. These findings highlight the potential of VQAs to tackle complex physical phenomena in high-cost computational scenarios, advancing their application in real-world industrial ML challenges.</p>