A Deep Learning Approach for Spatio-Temporal Forecasting of InSAR Ground Deformation in Eastern Ireland
This addresses the problem of predicting ground displacement for urban infrastructure and geological hazard mitigation, representing a novel methodological shift rather than an incremental improvement.
The paper tackled forecasting ground deformation from sparse InSAR data by introducing a deep learning framework that transforms measurements into a dense tensor, enabling the use of a hybrid CNN-LSTM model. Results showed significantly more accurate and spatially coherent forecasts compared to baselines like LightGBM and LASSO regression, establishing a new performance benchmark for this task.
Monitoring ground displacement is crucial for urban infrastructure stability and mitigating geological hazards. However, forecasting future deformation from sparse Interferometric Synthetic Aperture Radar (InSAR) time-series data remains a significant challenge. This paper introduces a novel deep learning framework that transforms these sparse point measurements into a dense spatio-temporal tensor. This methodological shift allows, for the first time, the direct application of advanced computer vision architectures to this forecasting problem. We design and implement a hybrid Convolutional Neural Network and Long-Short Term Memory (CNN-LSTM) model, specifically engineered to simultaneously learn spatial patterns and temporal dependencies from the generated data tensor. The model's performance is benchmarked against powerful machine learning baselines, Light Gradient Boosting Machine and LASSO regression, using Sentinel-1 data from eastern Ireland. Results demonstrate that the proposed architecture provides significantly more accurate and spatially coherent forecasts, establishing a new performance benchmark for this task. Furthermore, an interpretability analysis reveals that baseline models often default to simplistic persistence patterns, highlighting the necessity of our integrated spatio-temporal approach to capture the complex dynamics of ground deformation. Our findings confirm the efficacy and potential of spatio-temporal deep learning for high-resolution deformation forecasting.