This work is motivated by the Ob\'epine French system for SARS-CoV-2 viral load monitoring in wastewater. The objective of this work is to identify, from time-series of noisy measurements, the underlying auto-regressive signals, in a context where the measurements present numerous missing data, censoring and outliers. We propose a method based on an auto-regressive model adapted to censored data with outliers. Inference and prediction are produced via a discretised smoother. This method is both validated on simulations and on real data from Ob\'epine. The proposed method is used to denoise measurements from the quantification of the SARS-CoV-2 E gene in wastewater by RT-qPCR. The resulting smoothed signal shows a good correlation with other epidemiological indicators and an estimate of the whole system noise is produced.

翻译：这项工作的动机是法国SARS-COV-2病毒载荷监测系统,目的是从噪音测量的时序中,在测量显示大量缺失数据、检查和离线的情况下,确定基本的自动递减信号,我们建议采用一种方法,即基于自动递减模型,适应有外部线的检查数据,通过离散的光滑器作出推断和预测,该方法通过模拟和Ob\'epine的真数据加以验证,拟议方法用于通过RT-qPCR对废水中的SARS-COV-2 E基因进行量化,从而形成软化测量,由此产生的光滑信号与其他流行病学指标有良好关联,并生成了整个系统噪音的估计数。