A key component of disaster management and infrastructure organization is predicting cumulative deformations caused by landslides. One of the critical points in predicting deformation is to consider the spatio-temporal relationships and interdependencies between the features, such as geological, geomorphological, and geospatial factors (predisposing factors). Using algorithms that create temporal and spatial connections is suggested in this study to address this important point. This study proposes a modified graph convolutional network (GCN) that incorporates a long and short-term memory (LSTM) network (GCN-LSTM) and applies it to the Moio della Civitella landslides (southern Italy) for predicting cumulative deformation. In our proposed deep learning algorithms (DLAs), two types of data are considered, the first is geological, geomorphological, and geospatial information, and the second is cumulative deformations obtained by permanent scatterer interferometry (PSI), with the first investigated as features and the second as labels and goals. This approach is divided into two processing strategies where: (a) Firstly, extracting the spatial interdependency between paired data points using the GCN regression model applied to velocity obtained by PSI and data depicting controlling predisposing factors; (b) secondly, the application of the GCN-LSTM model to predict cumulative landslide deformation (labels of DLAs) based on the correlation distance obtained through the first strategy and determination of spatio-temporal dependency. A comparative assessment of model performance illustrates that GCN-LSTM is superior and outperforms four different DLAs, including recurrent neural networks (RNNs), gated recurrent units (GRU), LSTM, and GCN-GRU. The absolute error between the real and predicted deformation is applied for validation, and in 92% of the data points, this error is lower than 4 mm.

Different interferometric approaches have been developed over the past few decades to process SAR data and recover surface deformation, and each approach has advantages and limitations. Finding an accurate and reliable interval for preparing mean deformation rate maps (MDRMs) remains challenging. The primary purpose of this paper is to implement an application consisting of three unsupervised clustering algorithms (UCAs) for determining the best interval from SAR-derived deformation data, which can be used to interpret long-term deformation processes, such as subsidence, and identify displacement patterns. Considering Port Harcourt (in the Niger Delta) as the study area, it was essential to remove the sources of error in extracting deformation signals from SAR data, spatially ionospheric and tropospheric delays, before using UCAs to obtain its characteristics and real deformation data. Moreover, another purpose of this paper is to implement the advanced integration method (AIM) for atmospheric phase screen (APS) correction to enhance deformation signals obtained through different SAR processing approaches, including interferometric SARs (two-pass interferometry, InSAR) and multitemporal interferometry SARs (n-pass interferometry, DInSAR; permanent scatterer interferometry (PSI); and small baseline subset (SBAS)). Two methods were chosen to evaluate and find the best technique with which to create an MDRM: The first one was to compare the signals corrected by the AIM and the vertical component of the GPS station, which showed the AIM providing 58%, 42%, and 28% of the matching with GNSS station outputs for InSAR, PSI, and SBAS, respectively. Secondly, similarity measures and Davies–Bouldin index scores were implemented to find an accurate and reliable interval in which the SBAS technique with the unsupervised K-medians method has been chosen. Based on GNSS vertical deformation in a 500 m radius around the station, the SBAS K-medians technique expressed up to 5.5% better deformation patterns than the map of SAR processing techniques.

Around the world, the occurrence of landslides has become one of the greatest threats to human life, property, infrastructure, and natural environments. Despite extensive research and discussions on the spatiotemporal dependence of landslide displacements, there is still a lack of understanding concerning the factors that appear to control displacement distribution in landslides because of their significant variations. This paper implements a Graph Convolutional Network (GCN) to predict displacement following the Moio della Civitella landslide in southern Italy and identify factors that may affect the distribution of movement following the landslide. An interferometric technique, known as permanent scatter interferometry (PSI), has been developed based on Synthetic Aperture Radar (SAR) satellite imagery to derive permanent scatter points that can be used to represent the deformation of landslides. This study utilized the GCN regression model applied to PSs points and data reflecting geological and geomorphological factors to extract the interdependency between paired data points, resulting in an adjacency matrix of the interval [0, 0,8). The proposed model outperforms conventional machine learning and deep learning algorithms such as linear regression (LR), K-nearest neighbors (KNN), Support vector regression (SVR), Decision tree, lasso, and artificial neural network (ANN). The absolute error between the actual and predicted deformation is used to evaluate the proposed model, which is less than 2 millimeters for most test set points.