Simultaneous classification and location of deformation in SAR interferograms using deep learning

With the evolution of InSAR into a tool for active hazard monitoring, new methods are sought to quickly and automatically interpret the large number of interferograms that are created. We present a convolutional neural network (CNN) that is able to both classify the type of deformation, and to locate the deformation within an interferogram in a single step. We achieve this through building a “two headed model", which returns both outputs after one forward pass of an interferogram though the network. We train our model by first creating a dataset of synthetic interferograms, but find that our model’s performance is improved through the inclusion of real Sentinel-1 data. When building models of this type, it is common for some of the weights within the model to be transferred from other models designed for different problems. Consequently, we also investigate how to best organise interferograms such that the filters learned in other domains are sensitive to the signals in interferograms, but find that using different data in each of the three input channels degrades performance when compared to the simple case of repeating wrapped or unwrapped phase across each channel. We also release our labelled Sentinel-1 interferograms as a database named VolcNet, which consists of ∼500,000 labelled interferograms. VolcNet comprises of time series of unwrapped phase and labels of the magnitude, location, and duration of deformation, which allows for the automatic creation of interferograms between any two acquisitions, and greatly increases the amount of data available compared to other labelling strategies.