Skip to content

evan-greenbrg/LavakaMapping-v1

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LavakaMapping-v1

This is part of a project where I was attempting to first classify erosional gullies in the Madagascar highlands, and then measure phase correlation over gully features using Differential Interferometric Synthetic Aperature Radar (DInSAR).


File breakdown:
PreProcess.py: Takes individual input features, converts them to the same EPSG, clips them to the same extent, resamples them to the same size, and stacks them to a single meta-file.
Trainer.py: Performs the model trainig. Uses a Random Forest Classifier from SK-Learn. Performs test-train split, cross-validation, and model analysis. Saves best fit model.
Classifier.py: Uses input model to classify points over stack of regional input features.
Analysis.py: Samples phase correlation values from correlation interferogram for each land-cover type. Gathers general statistics and has a few plots it can produce.
RasterHelper.py: General library that contains most of the worker functions for the broad workflows.

I've called this v1 as the classifier could be significantly improved. There may be a v2 at some point that focuses on lavaka identification rather than correlation analysis.
Right now, this contains both workflows.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages