LandTrendr-CCDC Comparison Tool
This tool can be used to visualize and compare the outputs of the LandTrendr and CCDC algorithms for a single Landsat pixel
The scripts in this repository facilitate interactively running the LandTrendr (Landsat-based detection of Trends in Disturbance and Recovery) and CCDC (Continuous Change Detection and Classification) algorithms concurrently for clicked pixels, and resulting charts enable comparison of both time series inputs and temporal segmentation results. This repository includes a modified copy of LandTrendr utilities and relies on functionality from the CCDC algorithm API.
Getting started:
The tool packaged as an Earth Engine App can be found here.
Alternatively, if you want to access the tool's source code, you can add the repository to your Earth Engine scripts by clicking here, it will be displayed in the Reader section. The visualization tool is accessible by running LandTrendr-CCDC.js.
For this script to work correctly, users must also enable access to CCDC visualization utilities by clicking here to connect to the GEE-CCDC Tools repository, also described here.
Key parameters for the LandTrendr and CCDC algorithms can be adjusted in the left-hand panel, and clicking the map will interactively display both LandTrendr and CCDC Landsat inputs and segmentation results for the selected pixel in a set of charts in the right-hand panel. Note: CCDC is a more computationally intensive algorithm and results may be slow to load and display.
Additional LandTrendr utilities are included in LandTrendr.js and a description of the original LandTrendr utilities can be found here.
Manuscript
This tool was designed to accompany an in-prep manuscript intended to provide high-level comparison current limitations, ongoing challenges, and opportunities for future integration and comparison of LandTrendr and CCDC approaches and map products.
Example CSVs and PNGs generated using the comparison tool are available in the examples directory, and an iPython notebook for recreating key figures from the manuscript is available here.
Citations
LandTrendr implementation in GEE: Kennedy, R.E., Yang, Z., Gorelick, N., Braaten, J., Cavalcante, L., Cohen, W.B., Healey, S. (2018). Implementation of the LandTrendr Algorithm on Google Earth Engine. Remote Sensing. 10, 691.
CCDC implementation in GEE: Coming soon!
Third-party CCDC utilities used in this tool: Arévalo, P., Bullock, E.L., Woodcock, C.E., Olofsson, P., 2020. A Suite of Tools for Continuous Land Change Monitoring in Google Earth Engine. Front. Clim. 2. https://doi.org/10.3389/fclim.2020.576740