Self-memory model for predicting groundwater depth series with periodical fluctuation

The change process of groundwater table with time is a complex nonlinear process, so it is difficult using the present various methods to predict the change to be applied commonly in practice. A sort of new prediction method was proposed for the groundwater table series with periodical fluctuation. First, the differences of the mean values and amplitudes of groundwater table series in different periods should be eliminated and a new time series was established. Subsequently it was considered as a particular solution of groundwater system and the differential equation was retrieved based on the principle of system self-memorization. Finally, a self-memorization model of predicted groundwater table was established using the differential equation. The results show that this proposed method is convenient and practical and the predicted values are close to the real values, so it can be popularized and applied to the analysis of other time series with periodical fluctuation.