Skip to content

GEE code for pixel-based land cover classification with Random Forest (RF) algorithm, and for NDVI time series visualization.

License

Notifications You must be signed in to change notification settings

MrBourriz/Land-Cover-mapping-using-GEE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Land cover mapping using GEE

About

This repository contains scripts developed for a project that aims to explore the spatio-temporal monitoring of land cover in the province of Berkane. The study employs various classification approaches including pixel-based and object-based image analysis (OBIA),with the objective of comparing their effectivness. Multiple classifiers, such as Random Forest (RF), Artificial Neural Network (ANN), and Decision Tree (DT), have been selected for the classification process. Classification_RF specifically focuses on implementing (RF) within Google Earth Engine (GEE). On the other hand, NDVI_Timeseries_Visualization is designed for visualizing time series data, with a specific emphasis on the Normalized Difference Vegetation Index (NDVI).

Dataset

  • Landsat 7 Collection 2 Tier 1 TOA Reflectance
  • MOD13A2.061 Terra Vegetation Indices 16-Day Global 1km (MODIS)
  • Shapefile of the Province of Berkane

General Workflow

image

Results

1. Classification using RF

image

2. NDVI time series visualization

74f87e9cfef8a698fe108972f9efdeca-2a800343cae1854a62a6c791b6c0506f_getPixels

Contributing

Pull requests are always welcome! For significant changes or bug reports, please initiate the process by opening an issue, this allows us to collaboratively address the proposed modifications to improve this project.

To Do

  • Implementing RF Algorithm in GEE.
  • Visualization of the NDVI time series.
  • Enhancement of the classification accuracy.
  • Convert GEE JavaScript to Python.

Acknowledgments

This project would not have been possible without the collaborative efforts and contributions from:

References

[1] Google Earth Engine guides. Website. https://developers.google.com/earth-engine/guides

Contact

For further details, please reach out to me via E-mail: mbouriz2000@gmail.com

About

GEE code for pixel-based land cover classification with Random Forest (RF) algorithm, and for NDVI time series visualization.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published