Self-Supervised Temporal Analysis of Spatiotemporal Data

*=Equal Contributors
There exists a correlation between geospatial activity temporal patterns and type of land use. A novel self-supervised approach is proposed to survey landscape based on activity time series, where time series signal is transformed to frequency domain and compressed into embeddings by a contractive autoencoder, which preserve cyclic temporal patterns observed in time series. The embeddings are input to segmentation neural network for binary classification. Experiments show that the temporal embeddings are effective in classifying residential area and commercial area.