10.26204/10.26204/DATA/13 Wagner, Dennis Dennis Wagner Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Hartung, Fabian Fabian Hartung Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau BASF (Germany) Arweiler, Justus Justus Arweiler Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Muraleedharan, Aparna Aparna Muraleedharan TUM Straubing Jungjohann, Indra Indra Jungjohann Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Nair, Arjun Arjun Nair Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Reithermann, Steffen Steffen Reithermann Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Schulz, Ralf Ralf Schulz Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Bortz, Michael Michael Bortz Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Neider, Daniel Daniel Neider TU Dortmund University Leitte, Heike Heike Leitte Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Pfeffinger, Joachim Joachim Pfeffinger BASF (Germany) Mandt, Stephan Stephan Mandt Irvine University Fellenz, Sophie Sophie Fellenz Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Katz, Torsten Torsten Katz BASF (Germany) Jirasek, Fabian Fabian Jirasek Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Burger, Jakob Jakob Burger TUM Straubing Hasse, Hans Hans Hasse Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Kloft, Marius Marius Kloft https://orcid.org/0000-0001-6829-3725 Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau 2025 time series anomaly detection chemical process 2025 Creative Commons Attribution 4.0 International MIT License Monitoring chemical processes is necessary to prevent catastrophic failures, optimize costs and profits, and ensure the safety of employees and the environment. A key component of modern monitoring systems is the automated detection of anomalies in sensor data over time, called time series, enabling partial automation of plant operation and adding additional layers of supervision to crucial components. The development of anomaly detection methods in this domain is challenging, since real chemical process data is usually proprietary, and simulated data is generally not a sufficient replacement. In this paper, we present NoBOOM, the first collection of datasets for anomaly detection in real-life chemical process data, including labeled data from a running process at a leading industry partner, and several chemical processes run in a laboratory‑scale plant and a pilot‑scale plant. While we are not able to share every detail about the industrial process, for the laboratory‑ and pilot‑scale plants, we provide comprehensive information on plant configuration, processes run, operation, and, in particular, anomaly events, enabling a differentiated analysis of anomaly detection methods. To demonstrate the complexity of the benchmark, we analyze the data with regard to common issues of time-series anomaly detection (TSAD) benchmarks, including triviality and biases. Deutsche Forschungsgemeinschaft https://doi.org/10.13039/501100001659 459419731 DFG Research Unit FOR 5359 on Deep Learning on Sparse Chemical Process Data Carl-Zeiss-Stiftung https://doi.org/10.13039/100007569 Process Engineering 4.0