<p>Predicting hard landings is crucial for aiding pilots’ decisions and ensuring flight safety. This paper addresses the limitations of current hard landing prediction models, specifically in terms of long-term forecasting accuracy and explainability. To overcome these challenges, it introduces the Informer hard landing prediction model, developed using QAR data, and performs an in-depth explainability analysis of the model’s output. Following the principles of learning assurance, the data processing and model training phases are standardized. This involves the application of forward–backward filtering and Granger causality testing to refine the QAR data, thus creating a dataset that aligns with essential prediction standards. The Informer model addresses the challenges of multivariate time series discontinuities by localizing its network to enhance data adaptability. During model training and testing, hyperparameters are finely tuned to maximize prediction accuracy and generalizability. To improve transparency, the model employs an attention weight matrix and a feature reset-based explainability method. Tests show that models trained on datasets developed through a defined data management process deliver favorable predictive performance. The localized enhanced network improved prediction accuracy by 23.5% and increased its capacity to learn from discontinuous multivariate time series. Compared to the LSTM network, the Informer network achieved an 18.83% improvement in prediction accuracy and demonstrated superior long-time series prediction capabilities.</p>