Multistep-ahead Forecasting of Chlorophyll a Using a Wavelet Nonlinear Autoregressive Network

Multistep-ahead forecasting is essential to many practical problems, such as weather forecast, the early warning of disasters. However, existing studies mainly focus on current-time or one-step-ahead prediction since forecasting multiple steps continuously presents difficulties, such as accumulated errors and long-term time series modeling.

This study proposed an effective multistep-ahead forecasting model wavelet nonlinear autoregressive network (WNARNet), which integrates the wavelet transform and a nonlinear autoregressive neural network (NAR), for the forecast of chlorophyll a concentration. As 1 shows, the wavelet transform decreases the accumulative errors by dividing complicated time series into simpler ones. Simultaneously, the NAR maintains the dependencies between the time series.

Fig. 1 The specific procedure of WNARNet.

The buoy monitoring data of the Wenzhou coastal area obtained in 2014-2015 is used to verify the feasibility and effectiveness of WNARNet. The model performs well in predicting the dynamics of chlorophyll a and it is able to predict different horizons flexibly and accurately without training new models. Furthermore, experimental results demonstrate that WNARNet significantly outperforms other benchmark methods of multistep-ahead forecasting, as shown in 2.

Fig. 2. Comparison of the predictive performance of the different models with different horizons.

References:

Du,Z.,Qin,M., Zhang,F.,Liu,R.(2018). Multistep-ahead forecasting of chlorophyll a using a wavelet nonlinear autoregressive network. Knowledge-Based Systems.160,61-70.