Long-term daily prediction of saltwater intrusion based on the long memory-double autoregressive model

View Full Paper

Ask AI

Bookmark

Authors

Discussion

The long memory-double autoregressive model improves long-term prediction of chloride threshold breaches in estuaries, indicating better accuracy.

The LMDAR model achieved a Nash–Sutcliffe efficiency above 0.51 for long-term predictions across all stations.
In short-term predictions, the LMDAR, LSTM, and GRU models showed comparable accuracies with values exceeding 0.7.
Analysis was conducted using data from four salinity monitoring stations in the Pearl River Estuary.
The LMDAR model demonstrates consistent performance, indicating its effectiveness as a predictive tool for saltwater intrusion.

Lin et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

The long memory-double autoregressive model improves long-term prediction of chloride threshold breaches in estuaries, indicating better accuracy.