Measuring Sand Dune Migration Rates with COSI-Corr and Landsat: Opportunities and Challenges

It has been over a decade since COSI-Corr, the Co-Registration of Optically Sensed Images and Correlation, was first used to produce a raster map of sand dune movement, however, no studies have yet applied it to the full Landsat archive. The orthorectified and geolocated Landsat Level-1 Precision Terrain (L1TP) products offer the opportunity to simplify the COSI-Corr pre-processing steps, allowing an automated workflow to be devised. In the Bodele Depression, Chad, this automated workflow has calculated average dune speeds of 15.83 m/year and an increase in dune movement of 2.56 m/year +/- 12.58 m/year from 1987 to 2009. However, this increase does not stem from a systematic increase in dune mobility. The fastest 25% of dunes from 1987 to 1998 reduced their speed by 18.16%. The overall increase stems from the acceleration of features previously moving under 13.30 m/year. While successfully applied to the Bodele Depression, the automated workflow produces highly variable outputs when applied to the Grand Erg Oriental, Algeria. Variations within path/row scene pairings are caused by the use of mobile features, such as dune crests, as ground control points (GCPs). This has the potential to warp Landsat scenes during the L1TP processing, potentially obfuscating dune migration. Two factors appear to be crucial in determining whether a Landsat scene is suitable for COSI-Corr analysis. Firstly, dune mobility must exceed the misregistration criteria. Secondly, GPCs should be located on static features such as bedrock outcrops.