Monthly Bigeye Tuna Catches Forecasting Using Wavelet Functional Autoregression

In this paper, the aim is to apply a functional autoregressive (FAR) model combined with multiscale wavelet analysis for monthly bigeye tuna catches forecasting in the ocean ecosystem of the equatorial Indian ocean. Wavelet technique performs a time-frequency analysis of a time series, which permits to decompose the raw time series into trend and residual components. In wavelet domain, the trend component and residual component are forecasted with a linear autoregressive model and a FAR model; respectively. Hence, the proposed forecast is the co-addition of two predicted components. We find that the proposed forecasting strategy achieves 98% of the explained variance with reduced parsimony and high accuracy.