Dr. Philipp Denzel

Arbeit an der ZHAW

Tätigkeit

Machine Learning Researcher, Centre for Artificial Intelligence (CAI)

Arbeits- und Forschungsschwerpunkte

• Künstliche Intelligenz, Machine Learning, Deep Learning, Computer Vision
• Generatives Deep Learning, Computergestützte Astrophysik, Kosmologie
• Responsible & Trustworthy AI, Explainable AI

Lehrtätigkeit in der Weiterbildung

CAS Machine Intelligence

Berufserfahrung

Wissenschaftlicher Assistent
Institut für Computergestützte Wissenschaften (UZH)
2016 - 2021

Aus- und Weiterbildung

Ausbildung

• Dr. sc. nat. / Physik
  Universität Zürich
  2016 - 2021
• Msc / Computational Science
  Universität Zürich
  2014 - 2016
• Bsc / Physik (mit Nebenfach Informatik)
  Universität Zürich
  2010 - 2014

Netzwerk

ORCID digital identifier

ORCID ID: 0000-0003-0126-0659

Social Media

• Homepage
• LinkedIn

Projekte

• Erklärbare und handlungsorientierte KI für Intrusion-Detection-Systeme / Stellv. Projektleiter:in / laufend
• AI-Beschleunigte Radiative Transfer Simulationen für das SKAO / Stellv. Projektleiter:in / laufend
• GenAI4SKA: Simulierte astronomische Beobachtungen durch generative Deep Learning / Teammitglied / laufend
• Erklärbare KI für Intrusion-Detection-Systeme / Stellv. Projektleiter:in / abgeschlossen
• certAInty – A Certification Scheme for AI systems / Teammitglied / abgeschlossen
• Square Kilometre Array: Simulierte astronomische Beobachtungen durch generative Deep Learning / Teammitglied / abgeschlossen

Publikationen

Beiträge in wissenschaftlicher Zeitschrift, peer-reviewed

• Cerardi, N. et al. (2026) 'Implicit inference of the reionization history with higher-order statistics of the 21-cm signal', Monthly Notices of the Royal Astronomical Society, 549(1), p. stag779. doi: 10.1093/mnras/stag779.
• Bernardini, M. et al. (2026) 'Unveiling the dark Universe with HI and EMBER-2', Monthly Notices of the Royal Astronomical Society, 548(3), p. stag204. doi: 10.1093/mnras/stag204.
• Denzel, P. et al. (2026) 'Galactic alchemy : deep learning map-to-map translation in hydrodynamical simulations', Monthly Notices of the Royal Astronomical Society, 546(4), p. stag155. doi: 10.1093/mnras/stag155.
• Bonaldi, A. et al. (2025) 'Square Kilometre Array Science Data Challenge 3a : foreground removal for an EoR experiment', Monthly Notices of the Royal Astronomical Society, 543(2), pp. 1092–1119. doi: 10.1093/mnras/staf1466.
• Bianco, M. et al. (2025) 'Deep learning approach for identification of H II regions during reionization in 21-cm observations - III. Image recovery', Monthly Notices of the Royal Astronomical Society, 541(1), pp. 234–250. doi: 10.1093/mnras/staf973.

Schriftliche Konferenzbeiträge, peer-reviewed

• Denzel, P. et al. (2026) 'Intrinsic and post-hoc explainability for anomaly detection in network intrusion detection systems', in 2026 IEEE Swiss Conference on Data Science and AI (SDS). IEEE, pp. 115–122. doi: 10.1109/sds70563.2026.00023.
• Salis, E. d. et al. (2025) 'Exploring the early universe with deep learning', in Valente de Oliveira, J. et al. (eds). Cham: Springer, pp. 426–438. doi: 10.1007/978-3-032-05176-9_33.
• Frischknecht-Gruber, C. et al. (2025) 'AI assessment in practice : implementing a certification scheme for AI trustworthiness', in Görge, R. et al. (eds) Symposium on Scaling AI Assessments (SAIA 2024). Schloss Dagstuhl – Leibniz-Zentrum für Informatik, pp. 15:1–15:18. doi: 10.4230/OASIcs.SAIA.2024.15.
• Billeter, Y. et al. (2024) 'MLOps as enabler of trustworthy AI', in 2024 11th IEEE Swiss Conference on Data Science (SDS). IEEE, pp. 37–40. doi: 10.1109/SDS60720.2024.00013.
• Denzel, P. et al. (2024) 'Towards the certification of AI-based systems', in 2024 11th IEEE Swiss Conference on Data Science (SDS). IEEE, pp. 84–91. doi: 10.1109/SDS60720.2024.00020.
• Weng, J. et al. (2024) 'Certification scheme for artificial intelligence based systems', in 34th European Safety and Reliability Conference (ESREL), Cracow, Poland, 23-27 June 2024. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. doi: 10.21256/zhaw-30549.

Weitere Publikationen

• Denzel, P. et al. (2026) Optimization of deep learning models for radio galaxy classification. arXiv. doi: 10.48550/arXiv.2601.04773.
• Bonaldi, A. et al. (2025) Square Kilometre Array Science Data Challenge 3a : foreground removal for an EoR experiment. arXiv. doi: 10.48550/arxiv.2503.11740.
• Frischknecht-Gruber, C. et al. (2025) 'Assessment tool for trustworthy AI systems : operational workflows for compliance assessment with regulatory requirements', in AI Days @ HES-SO, Geneva and Lausanne, Switzerland, 27–29 January 2025. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. doi: 10.21256/zhaw-32422.
• Bianco, M. et al. (2024) Deep learning approach for identification of HII regions during reionization in 21-cm observations : III. image recovery. arXiv. doi: 10.48550/arxiv.2408.16814.
• Denzel, P., Schilling, F.-P. and Gavagnin, E. (2023) 'Map-to-map translation for SKA mock observations and cosmological simulations', in Hammers & Nails 2023 - Swiss Edition, Ascona, Switzerland, 29 October - 3 November 2023. Winterthur: ZHAW Zürcher Hochschule für Angewandte Wissenschaften. doi: 10.21256/zhaw-29047.
• Denzel, P. B., Schilling, F.-P. and Gavagnin, E. (2023) 'Deep learning the SKA : the Square Kilometer Array project', in Datalab Symposium, Winterthur, Schweiz, 11. Januar 2023. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. doi: 10.21256/zhaw-27219.

Mündliche Konferenzbeiträge und Abstracts

Denzel, P. et al. (2023) 'A framework for assessing and certifying explainability of health-oriented AI systems', in Explainable AI in Medicine Workshop, Lugano, Switzerland, 2-3 November 2023.

Publikationen vor Tätigkeit an der ZHAW

• Bridging the gap between simply parametrized and free-form pixellated models of galaxy lenses: The case of WFI 2033-4723 quad. The Open Journal of Astrophysics, 4
• The lens SW05 J143454.4+522850: A fossil group at redshift 0.6? Monthly Notices of the Royal Astronomical Society, 506(2), 1715–1722
• A new strategy for matching observed and simulated lensing galaxies. Monthly Notices of the Royal Astronomical Society, 506(2), 1815–1831
• Time delay lens modelling challenge. Monthly Notices of the Royal Astronomical Society, 503(1), 1096–1123
• Denzel, P., Coles, J. P., Saha, P., & Williams, L. L. R. (2021). The Hubble constant from eight time-delay galaxy lenses. Monthly Notices of the Royal Astronomical Society, 501(1), 784–801
• Denzel, P., Mukherjee, S., Coles, J. P., & Saha, P. (2020). Lessons from a blind study of simulated lenses: Image reconstructions do not always reproduce true convergence. Monthly Notices of the Royal Astronomical Society, 492(3), 3885–3903
• Denzel, P., Diemand, J., & Angélil, R. (2016). Molecular dynamics simulations of bubble nucleation in dark matter detectors. Physical Review E, 93(1)

Zurück