The ionospheric delays degrade the position accuracy of GPS measurements, leading to challenges in precise navigation and positioning services. Leveraging emerging artificial intelligence mathematical tools to forecast ionospheric disturbances using GPS-estimated Total Electron Content (TEC) observations is of utmost importance. In this study, a multi-input LSTM forecasting technique is investigated and tested to evaluate its capability in predicting ionospheric delays over Bengaluru station (16.26° N, 80.44° E). The research utilizes eight years (2009–2016) of GPS measured vertical TEC (VTEC) time-series data for training and validation. The successful implementation of the LSTM-based model demonstrates the potential of deep learning techniques in addressing ionospheric challenges, paving the way for further advancements in space weather prediction and its impact on satellite communication systems.