Open ivanzvonkov opened 1 year ago
Low cropland amount, low metrics: https://github.com/nasaharvest/crop-mask/blob/0b9c305ae71994b8d938ee34a77a295565ff7435/data/models.json#L19
Could be improved by NDVI stratification
Next step adding WFP data
@MsPixels now that you have some corrective points, the next step is to add them to the code base! Here's an example of me adding the the Namibia WFP data https://github.com/nasaharvest/crop-mask/pull/227 The main change is to datasets.py which you will have to update too! More info here: https://github.com/nasaharvest/crop-mask#adding-new-labeled-data
What changed:
Test metrics:
"accuracy": 0.9685,
"f1_score": 0.125,
"precision_score": 0.0909,
"recall_score": 0.2,
"roc_auc_score": 0.8155
Compute Cost: Cloud Run: $109.84 Cloud Functions: $5.69 Total: $115.13
The compute cost above actually also accounts for Zambia v2 so it is actually lower
Yeah, @ivanzvonkov, major improvement indeed. Just wondering why the f1 score is this low despite this result.
Additional data has been added in #243, now new model can be trained
Model being trained https://github.com/nasaharvest/crop-mask/pull/250
From Christina in meeting 1/19:
Yes, @hannah-rae, I can create the in-season cropland map and hopefully the WFP map
Model being trained #250
Namibia_North_2020_v2
"test_metrics":
"accuracy": 0.9324,
"f1_score": 0.0625,
"precision_score": 0.037,
"recall_score": 0.2,
"roc_auc_score": 0.8661
Comparing V1 and V2 - Namibia_North
Although this model predicts more crop fields than normal, it is able to correctly predict crop fields in the big yellow squares
@MsPixels @ivanzvonkov I was looking at the last comments on this issue but we don't have the "next steps" recorded for when it got picked back up. Are these the potential next steps?
Other things to try:
Thanks Hannah for your feedback. Yes, these are potential next steps.
Next steps:
Metrics for the model:
"Namibia_North_V3": {
"params": "https://wandb.ai/nasa-harvest/crop-mask/runs/qzfflhy8",
"test_metrics": {
"accuracy": 0.9635,
"f1_score": 0.1429,
"precision_score": 0.0833,
"recall_score": 0.5,
"roc_auc_score": 0.8404},
"val_metrics": {
"accuracy": 0.9744,
"f1_score": 0.1053,
"precision_score": 0.0556,
"recall_score": 1.0,
"roc_auc_score": 0.9834}
I also adjusted the threshold (greater than 0.8) here. I think it removes some noise
@MsPixels initial evaluation: "I think the model does a good job at the west but over-predicts at the east, especially in the flood plains. Some built-up areas were captured as cropland. I'm not super confident about the South. Waiting for confirmation from Christina."
@MsPixels will try the post-classification filtering to see if that reduces some false positive areas (e.g. water/lake shorelines) and we will work with Christina to make final decision.
Post-classification filtering @hannah-rae.
Start year: 2020 Start month: September