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

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 created using Sentinel-2 satellite imagery (with 10m spatial and 1 month temporal resolution). 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. The CaiRoad dataset has a total of 28015 change events with 2259 road construction events from the city of Cairo and the CalFire dataset has 2172 change events with 204 labeled fire events in California. 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. For example the best performing model has a retrieval precision@25 of 0.46 on CaiRoad benchmark.