Qinghe Gao and Lukas Schulze Balhorn complete their PhD research; defences on 20 November 2026

PhD students Qinghe Gao and Lukas Schulze Balhorn have completed their PhD research. Both will defend their dissertations publicly on Friday, 20 November 2026, in the TU Delft Aula.

Qinghe Gao worked at the interface of deep learning and chemical process design. His PhD research covered graph neural networks for molecular property prediction, reinforcement learning for process design, and self-supervised learning. Recent publications include transfer learning for reinforcement learning-based process synthesis, environmental impact prediction with graph neural networks on molecular graphs, Bayesian uncertainty quantification of graph neural networks, and the review Multi-agent systems for chemical engineering.

Lukas Schulze Balhorn worked on knowledge extraction, optimization and machine learning in chemical engineering, with a focus on generative AI for engineering diagrams. His work includes Graph-to-SFILES for control structure prediction, rule-based and generative autocorrection of P&IDs, and the open-source package pyDEXPI. He was a co-recipient of the 2024 IChemE Senior Moulton Medal and the 2025 Faculty Open Science Award of the Faculty of Applied Sciences.

Public defences

Both defences take place on Friday, 20 November 2026 in the TU Delft Aula, Delft, and are open to the public.

• 10:00–11:00: Qinghe Gao, "Graph Machine learning for Molecular Property Prediction and Process Design"
• 12:30–13:30: Lukas Schulze Balhorn, "Autocorrection of Piping and Instrumentation Diagrams using Artificial Intelligence"

We thank Qinghe and Lukas for their contributions to the group and wish them all the best for their defences and their next steps.