Dr. Melanie Schaller completed her PhD at the university of Würzburg in 2023 focusing on the application of Cyber-Physical Systems for non-invasive monitoring of intracranial pressure via a pressure derivative. On the software side, her work focuses on sensor networks, state space models, neural operator learning, anomaly detection, and cyber‑physical systems, with a strong emphasis on graph‑based and physics‑informed machine learning methods.On the hardware side, her focus lies on sensor network applications.

She has completed several research projects in the field of machine learning for real‑world sensing systems. Her research includes methods for identifying normal and abnormal structural behavior in dynamic environments, where sensor data is used to characterize system responses and detect deviations indicative of potential damage or failure. 

In another line of work, she develops machine‑learning techniques for monitoring and diagnosing anomalies in distributed networks, including the detection and localization of critical events such as leakages. Beyond networked systems, her research also explores fluid‑dynamic modeling and high‑speed imaging, where she investigates the behavior of laminar and transitional water jets using physics‑informed learning approaches but also the erosion effects on different materials. These methods leverage physics‑guided neural networks to bridge the gap between experimental observations and underlying flow physics.