In this study, a type of artificial intelligence called Long Short-Term Memory (LSTM) networks is used to predict how far saltwater moves into estuaries. Different data types (such as salinity, water levels, wind, and river flow) are combined with computer model outputs to train LSTM networks. Once the network is trained, it is applied to the same data to predict saltwater movements quickly and accurately. The approach is tested on two tidal estuaries and shows that the network works even when some data is missing. However, predicting further into the future is more challenging because short-term events affect saltwater movement. This study shows that LSTM networks can make fast and accurate predictions of saltwater entering estuaries, helping with real-time monitoring and decision-making for coastal protection and water management.