Application of hybrid improved temporal convolution network model in time series prediction of river water quality

Smoothing and denoising the original time series data can effectively improve the accuracy of prediction²³. Therefore, in this study, we used the SG filter to remove the noise in the original water quality time series. The SG filter is a filtering method based on the local polynomial least squares fitting in the time domain. The biggest feature of this filter is that it can ensure the shape and width of the signal are unchanged while filtering out the noise.

A subsequence \(x\) with window size \(w=2m+1\) can be expressed as: