The ephemeris accuracy parameters broadcast in the ephemeris messages are commonly utilized as an alarm threshold of the SISRE of GNSS. Accurately predicting the orbit and clock errors of broadcast ephemeris, and converting the prediction errors into broadcast ephemeris accuracy parameters using a robust model, is crucial for the integrity service of GNSS. The BDS-3 broadcasts four ephemeris accuracy parameters, which are 〖SISA〗_oe, 〖SISA〗_ocb, 〖SISA〗_oc1, and 〖SISA〗_oc2, to represent the STD of the satellite orbit and clock prediction errors in the broadcast ephemeris. The probability that the broadcast ephemeris SISRE exceeds 4.42 times the Signal-In-Space Accuracy (SISA) without triggering an alarm in time is expected to be less than 1 × 10-5. In addition to accurately enveloping the broadcast ephemeris SISRE, SISA should also reduce the over-envelopment margin over the SISRE to accurately express the system service accuracy. An orbit and clock error prediction method based on the Long Short-Term Memory neural network is proposed. This method utilizes historical satellite orbit and clock errors, derived from the difference between precise and broadcast ephemeris, to train the LSTM neural network. The trained LSTM model is then used to predict orbit and clock errors for the next 24 hours. The predicted errors are used to calculate the corresponding SISA for the broadcast ephemeris. The results indicate that the 24-hour accuracies of predicted orbit and clock errors are less than 0.06 meters and 0.25 meters, respectively. The calculated SISA can completely envelop the actual broadcast ephemeris SISRE, achieving 100% coverage, while also reducing the over-envelopment margin by 80%. Furthermore, the horizontal protection level and vertical protection level calculated using the corresponding SISA are reduced by approximately 14%, meeting the integrity requirements set by the ICAO for Approach with APV I. This significantly improves the integrity and availability of the BDS-3 service.
