Informer-Based Real-Time Correction Method for Chromatographic Backgrounds

Baseline drift is a common interference factor in spectral data acquisition, and background deduction serves as a critical step for enhancing data quality. Although numerous baseline correction methods exist, most are confined to static data processing and fail to meet real-time analysis requirements. To address this, we propose a real-time baseline estimation method based on the Informer time-series prediction model, with focused research on three key aspects: chromatographic dataset construction, model training, and baseline prediction. Simulation experiments demonstrate that the proposed method achieves comparable accuracy to conventional static processing approaches while exhibiting significant real-time advantages. In processing real chromatographic data, the model achieves a 98.3\% chromatographic peak retention rate, with a single computation time of approximately 35ms - substantially shorter than typical chromatographic sampling cycles (600-900 ms), thus fully satisfying the quantitative analysis requirements for real-time background deduction. Our real-time baseline correction code and data are publicly available at: https://github.com/users/hustcjl37/