Closed ivanzvonkov closed 1 year ago
Data being added to repo: https://github.com/nasaharvest/crop-mask/pull/230
Sudan_Blue_Nile_CEO_2019 (Timesteps: 24)
----------------------------------------------------------------------------
disagreement: 0.0%
eo_data_complete 1500
✔ training amount: 311, positive class: 31.5%
✔ validation amount: 581, positive class: 37.9%
✔ testing amount: 608, positive class: 37.5%
"accuracy": 0.9408,
"f1_score": 0.9227,
"precision_score": 0.9034,
"recall_score": 0.943,
"roc_auc_score": 0.9723
https://code.earthengine.google.com/382a613f09d8d435ee0ccd9313bde813
Initial prediction merging led to some missing tiles, after investigating and remerging same predictions v2 had not missing tiles. Attributing to some intermittent merging issue.
Related #244
Reviewed-- as with others like Tanzania, we seem to have issues around wetlands; otherwise, the mask looks decent. I suggest we look into sourcing non-crop examples of wetlands in CropHarvest possibly from a recent wetland product-- hopefully, one that does well at separating crops like rice.
Potential source of global wetland map that we could use, but should cross-check with the "problem areas" where wetlands are misclassified in our map: https://www2.cifor.org/global-wetlands/
Another potential wetlands dataset for sampling non-crop points from: https://www.worldwildlife.org/pages/global-lakes-and-wetlands-database
Next step corrective labeling with GEE script, relevant #222
Options in Earth Engine: https://developers.google.com/s/results/earth-engine/datasets?q=wetlands&text=wetlands
Short term -> corrective labeling Long term -> Issue about wetland data + analysis
@cnakalembe, please find the link to the Corrective labeling App for Sudan Blue Nile https://aasareansah.users.earthengine.app/view/sudanbluenilecorrectivelabelapp
Second version of map: https://code.earthengine.google.com/1026aec46650a3578d3672b04e34c4d2 Looks about the same
It is better in some places. I can do another round of corrective labeling, this time denser than before. The first time I was being conservative, looking for larger patterns.
Let's discuss on Monday in the meeting!
Start year: 2019 Start month: February