Are Time-Series Foundation Models Ready for E-Nose Data? An Empirical Assessment of Their Embeddings
For researchers in gas sensing, this paper provides an empirical assessment of TSFMs on E-Nose data, highlighting the need for fine-tuning and fusion, but the findings are incremental as they confirm known limitations of foundation models on niche domains.
The paper evaluates time-series foundation models (TSFMs) on electronic nose (E-Nose) data, finding that fine-tuning is necessary for satisfactory performance and that fusing TSFM embeddings with specialized model representations improves results, indicating both potential and limitations.
Inspired by advances in natural language processing and computer vision, "time-series foundation models" (TSFMs) have recently been introduced with the promise of strong generalization across diverse time-series tasks, including forecasting, classification, and anomaly detection, as well as across domains such as healthcare, climate science, and manufacturing. However, their utility for gas-sensing data remains largely unexplored. To address this gap, this paper systematically evaluates recent TSFMs on electronic nose (E-Nose) data. In particular, we investigate whether embeddings produced by representative TSFMs, including Chronos-2 and MOMENT, provide effective representations for gas identification and concentration prediction. Specifically, we show that fine-tuning is necessary to achieve satisfactory performance on E-Nose data, and fusing TSFM embeddings with representations learned by specialized predictive models can further improve the performance, suggesting both the potential and limitations of current TSFMs for gas-sensing applications.