The submissions will be evaluated using **weighted F1-score**, to select models that achieve both high precision in correctly identifying erosion events and high recall in detecting as many true erosion instances as possible.

## Submission File
For each `sample_id` in the test set, the participants must predict the erosion class `Code` (string/factor or integer). The file should contain a header and have the following format:
```
sample_id,Code
1012,0
5006,1
9999,2
 ```