GitHub - JuliusFx131/GEO-AI-Challenge-for-Cropland-Mapping-Challenge: Current available solutions eg #WorldCover apply inconsistent "cropland" definitions from #FAOSATA’s and are rarely up to date. This work focused on building cost effective classification for cropland mapping for #Sudan, #Iran & #Afghanistan regions. For Afghanistan we focused on temporal classification while for the rest year-long classification

JuliusFx131 / GEO-AI-Challenge-for-Cropland-Mapping-Challenge Public

forked from ITU-GeoAI-Challenge/GEO-AI-Challenge-for-Cropland-Mapping-Challenge

Notifications You must be signed in to change notification settings
Fork 0
Star 1

Current available solutions eg #WorldCover apply inconsistent "cropland" definitions from #FAOSATA’s and are rarely up to date. This work focused on building cost effective classification for cropland mapping for #Sudan, #Iran & #Afghanistan regions. For Afghanistan we focused on temporal classification while for the rest year-long classification

zindi.africa/competitions/geo-ai-challenge-for-cropland-mapping-with-satellite-imagery

1 star 1 fork Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 13 Commits
1.a) Data Extraction Prep -Split Into Countries.ipynb		1.a) Data Extraction Prep -Split Into Countries.ipynb
1.b) Data Extraction - Final Step_(NOT COLAB).ipynb		1.b) Data Extraction - Final Step_(NOT COLAB).ipynb
1.c) VISUALIZATION.ipynb		1.c) VISUALIZATION.ipynb
2.e) GRIDSEARCHED - 0.913.ipynb		2.e) GRIDSEARCHED - 0.913.ipynb
Code for Accessing GEE Console.txt		Code for Accessing GEE Console.txt
Presentation Slides.pptx		Presentation Slides.pptx
README.txt		README.txt
Test.csv		Test.csv
Train.csv		Train.csv
requirements.txt		requirements.txt
technical report.pdf		technical report.pdf

Repository files navigation

Order of Executing the .ipynb Files:

1.Ensure you are working in the Anaconda environment on your PC. All files provided for this work should be in same location


2.Begin by running the "1.a) Data Extraction Prep -Split Into Countries.ipynb" file first.


-This step is necessary to generate the each country's train and test csv files, which are used in the subsequent "1.b) Data Extraction - Final Step_(NOT COLAB).ipynb" file.

3. Proceed to run the "1.b) Data Extraction - Final Step_(NOT COLAB).ipynb" file.

-This step is necessary to pull sentinel bands for each country for both train and test files 


4. Proceed to run the "2.e) GRIDSEARCHED - 0.913.ipynb" file.


5. For the final submission on Zindi, use the output from the last step, specifically the "1.lgbm.csv".