Reference dataset for comparison of cloud detection algorithms for Sentinel-2 imagery
| Main Authors: | Tang, Xiaojing, Tarrio, Katelyn, Masek, Jeffrey, Claverie, Martin, Ju, Junchang, Qiu, Shi, Zhu, Zhe, Chen, Shijuan, Fu, Qiyuan, Liu, Yihao, Shen, Xianfei, Wang, Yetianjian, Zhang, Yingtong, Zhu, Chongyang, Woodcock, Curtis |
|---|---|
| Format: | info dataset Journal |
| Bahasa: | eng |
| Terbitan: |
, 2021
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/5721781 |
Daftar Isi:
- Sentinel-2 cloud mask reference dataset generated and analyzed as part of Tarrio, K., Tang, X., Masek, J.G., Claverie, M., Ju, J., Qiu, S., Zhu, Z. and Woodcock, C.E., 2020. Comparison of cloud detection algorithms for Sentinel-2 imagery. Science of Remote Sensing, 2, p.100010. [https://www.sciencedirect.com/science/article/pii/S2666017220300092](https://www.sciencedirect.com/science/article/pii/S2666017220300092) 1. Reference masks Algorithms: Fmask 1.x Fmask 2.x Fmask 4.x Tmask Sen2Cor MAJA LaSRC Locations: South Africa (35JPM) Senegal (28PDC) Switzerland (32TLT) France (31TCJ, 31TFJ) Morocco (29RNQ) Standardized legend: Original algorithm outputs were standardized to the same categorical legend. 0 = clear land 1 = clear water 2 = cloud shadow 3 = snow/ice 4 = cloud All reference masks processed to both 10m and 30m resolution, with the exception of Tmask, which is available only at a 30m resolution. Mask naming convention: All processed masks are named according to the following convention: M<*resolution*><*S2 MGRS tile ID*><*YYYY*><*DOY*><*algorithm*> e.g. **M30T28PDC2016351TMASK** 2. Interpreted sample points Sample points were selected based on agreement among different map products. This record includes a shapefile with the final interpretations for each of the sampled sites. (See publication for additional information.)
- This research was funded by NASA through both the Harmonized Landsat Sentinel effort and the Making Earth System Data Records for Use in Research Environments (MEaSUREs) Program, as well as the USGS through the Landsat Science Team.