Forecasting Source Stability in Scientific Experiments using Temporal Learning Models: A Case Study from Tritium Monitoring

TL;DR

This paper explores the use of advanced deep learning time-series models to predict the stability duration of the tritium source in the KATRIN experiment, aiming to improve experimental scheduling and maintenance.

Contribution

It applies and compares multiple forecasting models to real experimental data, identifying N-BEATS as the most effective for predicting source stability in a complex physics setting.

Findings

N-BEATS outperforms other models in accuracy and consistency.

Forecasting long-term stability remains a challenging open problem.

Deep learning models can enhance experimental planning in physics research.

Abstract

The Karlsruhe Tritium Neutrino Experiment (KATRIN) aims to measure the absolute neutrino mass with unprecedented sensitivity, requiring precise monitoring of the windowless gaseous tritium source, where tritium beta decay occurs. To track variations of the source activity, beta-induced X-ray spectroscopy provides real-time diagnostics. However, traditional drift detection methods struggle with the infrequent and transient nature of instability events in gaseous tritium. This study bridges the gap between state-of-the-art time-series forecasting models and real-world experimental applications by leveraging deep learning to predict the time to stability after instabilities. Unlike standard benchmarking approaches that emphasize algorithmic performance on fixed datasets, we apply forecasting models -- including LSTM, N-BEATS, TFT, NHITS, DLinear, NLinear, TSMixer, and Chronos-LLM -- to complex, large-scale experimental data. Our findings highlight two challenges: learning from sparse instability events and forecasting long time horizons (i.e., predicting hundreds of future points), both of which are ongoing challenges in time-series forecasting and remain active areas of research. This prediction task has direct experimental value by enabling better scheduling and maintenance planning. A reliable forecast of stability time allows for more efficient measurement and task management during stabilization periods. Through model selection, we identified N-BEATS as the top performer, excelling in accuracy and repeatability, demonstrating that deep learning can optimize large-scale physics experiments.