Change Event Dataset for Discovery from Spatio-temporal Remote Sensing Imagery

Utkarsh MallBharath HariharanKavita Bala

Cornell University

In NeurIPS 2022 (Featured)

CaiRoad Events

Other Events

CalFire Events


Satellite imagery is increasingly available, high resolution, and temporally detailed. Changes in spatio-temporal datasets such as satellite images are particularly interesting as they reveal the many events and forces that shape our world. However, finding such interesting and meaningful change events from the vast data is challenging. In this paper, we present new datasets for such change events that include semantically meaningful events like road construction. Instead of manually annotating the very large corpus of satellite images, we introduce a novel unsupervised approach that takes a large spatio-temporal dataset from satellite images and finds interesting change events. To evaluate the meaningfulness on these datasets we create 2 benchmarks namely CaiRoad and CalFire which capture the events of road construction and forest fires. These new benchmarks can be used to evaluate semantic retrieval/classification performance. We explore these benchmarks qualitatively and quantitatively by using several methods and show that these new datasets are indeed challenging for many existing methods.


[pdf]   [supplementary pdf]

Utkarsh Mall, Bharath Hariharan and Kavita Bala. "Change Event Dataset for Discovery from Spatio-temporal Remote Sensing Imagery". In NeurIPS Datasets and Benchmarks Track, 2022.

 title={Change Event Dataset for Discovery from Spatio-temporal Remote Sensing Imagery},
 author={Mall, Utkarsh and Hariharan, Bharath and Bala, Kavita},
 booktitle={NeurIPS Datasets and Benchmarks Track},



[txt] Readme.txt

[zip] [10.7 GB]: Contains change events, satellite image stack, human annotated road labels and train-test splits from Cairo.

[zip] [7.2 GB]: Contains change events, satellite image stack, annotated fire labels and train-test splits from California fire location.

[csv] all_forest_fires.csv: Contains list of forest from California Fire website. and


Our Code can be found at the GitHub Repo.

Pretrained models for unsupervised change detection can be found here.


[08-12-2022] The data now contains a small subset of CaiRoad and CalFire namely TinyCaiRoad and TinyCalFire that can be downloaded for visualization and understanding purposes.

[08-10-2022] Pre-trained self-supervised change detection models are not present on the page.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.