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 stratify landscape based on mobility activity time series. First, the time series signal is transformed to the frequency domain and then compressed into task-agnostic temporal embeddings by a contractive autoencoder, which preserves cyclic temporal patterns observed in time series. The pixel-wise embeddings are converted to image-like channels that can be used for task-based, multi-modal modeling of downstream geospatial tasks using… Read More Apple Machine Learning Research 







Leave a Reply

Your email address will not be published. Required fields are marked *