Publications

You can also find my articles on my Google Scholar profile.

ETH Zurich

Ancestor regression in structural vector autoregressive models

Christoph Schultheiss, Markus Ulmer, and Peter Bühlmann. 2025. "Ancestor regression in structural vector autoregressive models." Journal of Causal Inference 13(1), doi:10.1515/jci-2024-0011

Spectrally Deconfounded Random Forests

Markus Ulmer, Cyrill Scheidegger, and Peter Bühlmann. 2025. "Spectrally Deconfounded Random Forests." arXiv e-prints, arXiv:2502.03969

Machine Health / Predictive Maintenance

A Generic Machine Learning Framework for Fully-Unsupervised Anomaly Detection with Contaminated Data

Markus Ulmer, Jannik Zgraggen, and Lilach Goren Huber. 2024. "A Generic Machine Learning Framework for Fully-Unsupervised Anomaly Detection with Contaminated Data." International Journal of Prognostics and Health Management 15(1), doi:10.36001/ijphm.2024.v15i1.3589

Scaling Up Deep Learning Based Predictive Maintenance for Commercial Machine Fleets: a Case Study

Markus Ulmer, Jannik Zgraggen, Gianmarco Pizza, and Lilach Goren Huber. 2022. "Scaling up deep learning based predictive maintenance for commercial machine fleets: A case study." 9th Swiss Conference on Data Science (SDS), Lucerne, Switzerland pp. 40-46, doi:10.1109/SDS54800.2022.00014

Transfer learning approaches for wind turbine fault detection using deep learning

Jannik Zgraggen, Markus Ulmer, Eskil Jarlskog, Gianmarco Pizza, and Lilach Goren Huber. 2021. "Early fault detection based on wind turbine scada data using convolutional neural networks." PHM Society European Conference 6(1), 12, doi:10.36001/phme.2021.v6i1.2835

Cross-Turbine Training of Convolutional Neural Networks for SCADA-Based Fault Detection in Wind Turbines

Markus Ulmer, Eskil Jarlskog, Gianmarco Pizza, and Lilach Goren Huber. 2020. "Early fault detection based on wind turbine scada data using convolutional neural networks." Annual Conference of the PHM Society 12(1), 10, doi:10.36001/phmconf.2020.v12i1.1205

Early fault detection based on wind turbine scada data using convolutional neural networks

Markus Ulmer, Eskil Jarlskog, Gianmarco Pizza, Jaakko Manninen, and Lilach Goren Huber. 2020. "Early fault detection based on wind turbine scada data using convolutional neural networks." PHM Society European Conference 5(1), 9, doi:10.36001/phme.2020.v5i1.1217

Other

The impact of misclassifications and outliers on imputation methods

Matthias Templ and Markus Ulmer. 2024. "The impact of misclassifications and outliers on imputation methods." Journal of Applied Statistics 51(14), doi:10.1080/02664763.2024.2325969