# Self-Supervised Temporal Analysis of Spatiotemporal Data

arXiv: https://arxiv.org/abs/2304.13143 · HTML: https://mlsanity.com/paper/2304.13143/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 8 references that are in the map.
- First posted on arXiv 25 Apr 2023.

## Builds on (most cited first, 3 of 3)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Trinity: A No-Code AI platform for complex spatial datasets](https://mlsanity.com/paper/2106.11756/) (2021)
- [Reachability Embeddings: Scalable Self-Supervised Representation Learning from Mobility Trajectories for Multimodal Geospatial Computer Vision](https://mlsanity.com/paper/2110.12521/) (2021)

## Built on by (most cited first, 2 of 2)

- [SeMAnD: Self-Supervised Anomaly Detection in Multimodal Geospatial Datasets](https://mlsanity.com/paper/2309.15245/) (2023)
- [Temporal Embeddings: Scalable Self-Supervised Temporal Representation Learning from Spatiotemporal Data for Multimodal Computer Vision](https://mlsanity.com/paper/2401.08581/) (2023)

## Abstract (arXiv)

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, multimodal modeling of downstream geospatial tasks using deep semantic segmentation. Experiments show that temporal embeddings are semantically meaningful representations of time series data and are effective across different tasks such as classifying residential area and commercial areas.