| dc.description.abstract |
Among all natural disasters, earthquakes cause the most severe devastation to both infrastructure as well as human lives. The pattern of surface deformation from satellite-based measures, such as interferometric synthetic aperture radar (InSAR), helps understand crustal dynamics and associated seismic hazards in tectonically active areas. In the last few years, the exponentially rising volume of InSAR data has led to the formulation of automatic crustal deformation algorithms through data-intensive machine learning models. In this study, we propose the long-short-term memory (LSTM) architecture of deep neural networks to forecast InSAR-based line-of-sight displacement. The model suitably captures the inherent temporal variations of SAR interferograms. The method implementation on a region near Central and East Java, Indonesia shows satisfactory performance (mean absolute percentage error around 2%) of the proposed LSTM model comprising four layers, each consisting of 100 nodes. We therefore conclude that deep neural network is a promising avenue for InSAR time series analysis. |
en_US |