Re-Engineering InSAR Kinematics via Local Markov Memory: A Scalable Machine Learning Framework for Corridor Slope Displacement Forecasting

Slope instabilities pose a significant threat to transportation infrastructure, creating the need for reliable data-driven approaches for displacement forecasting. This study proposes a scalable machine learning framework that integrates Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) displacement time series with a structured sliding-window transformation to predict short-term vertical slope displacements under multi-cadence satellite acquisition schedules. The transformation reformats raw InSAR observations into fixed-length input windows, where the four most recent displacement measurements and their corresponding elapsed time intervals are used to predict the subsequent displacement based on a local Markov-type assumption. An iterative modelling strategy, progressing from baseline to multi-interval configurations on balanced and unbalanced datasets, was implemented using Artificial Neural Networks (ANN) and Multiple Linear Regression (MR). Under a uniform 12-day satellite revisit schedule, ANN and MR achieved comparable predictive performance (RMSE = 2.85, R2 = 0.93). When evaluated on the more realistic multi-cadence datasets (12–144 days), ANN showed a modest performance advantage over MR, with lower RMSE (2.86 vs. 2.98) and slightly higher R2 (0.92 vs. 0.91). These results indicate that the relative performance of the two approaches is influenced by the temporal sampling structure, with ANN providing a modest improvement under heterogeneous temporal cadences. Sensitivity analysis further identified the most recent displacement stages as the dominant predictors, confirming the importance of short-term deformation history. The proposed framework provides an efficient, scalable, and data-driven solution for regional InSAR-based slope displacement forecasting, supporting early detection of deformation trends and risk-informed management of transportation infrastructure, particularly in data-scarce environments.