Spatio-temporal fusion for daily Sentinel-2 images

• Published in: Remote sensing of environment Vol. 204; pp. 31 - 42
• Main Authors: Wang, Qunming, Atkinson, Peter M.
• Format: Journal Article
• Language: English
• Published: New York Elsevier Inc 01.01.2018; Elsevier BV
• Subjects: color; data collection; Downscaling; Ecological monitoring; Environmental monitoring; Fusion; image analysis; Image fusion; monitoring; prediction; regression analysis; Regression models; remote sensing; Satellites; Sensors; Sentinel-2; Sentinel-3; Spatial discrimination; Spatial filtering; Spatial resolution; Temporal resolution; temporal variation; time series analysis; Downscaling; Sentinel-3; Image fusion; Sentinel-2
• ISSN: 0034-4257; 1879-0704
• DOI: 10.1016/j.rse.2017.10.046

Sentinel-2 and Sentinel-3 are two newly launched satellites for global monitoring. The Sentinel-2 Multispectral Imager (MSI) and Sentinel-3 Ocean and Land Colour Instrument (OLCI) sensors have very different spatial and temporal resolutions (Sentinel-2 MSI sensor 10m, 20m and 60m, 10days, albeit 5days with 2 sensors, conditional upon clear skies; Sentinel-3 OLCI sensor 300m, <1.4days with 2 sensors). For local monitoring (e.g., the growing cycle of plants) one either has the desired spatial or temporal resolution, but not both. In this paper, spatio-temporal fusion is considered to fuse Sentinel-2 with Sentinel-3 images to create nearly daily Sentinel-2 images. A challenging issue in spatio-temporal fusion is that there can be very few cloud-free fine spatial resolution images temporally close to the prediction time, or even available, strong temporal (i.e., seasonal) changes may exist. To this end, a three-step method consisting of regression model fitting (RM fitting), spatial filtering (SF) and residual compensation (RC) is proposed, which is abbreviated as Fit-FC. The Fit-FC method can be performed using only one Sentinel-3–Sentinel-2 pair and is advantageous for cases involving strong temporal changes (i.e., mathematically, the correlation between the two Sentinel-3 images is small). The effectiveness of the method was validated using two datasets. The created nearly daily Sentinel-2 time-series images have great potential for timely monitoring of highly dynamic environmental, agricultural or ecological phenomena. •Sentinel-2 and Sentinel-3 data are fused to create daily Sentinel-2 images.•Fit-FC is proposed for spatio-temporal fusion.•Fit-FC is advantageous for cases involving strong temporal changes.•The fused products have great potential for timely monitoring of rapid changes.