## Evaluation

Participants will be evaluated based on the **Root Mean Squared Error (RMSE)** between the predicted and actual maize yield values.

The RMSE is defined as:

$$
\text{RMSE} = \sqrt{ \frac{1}{n} \sum_{i=1}^{n} \left( y\_i - \hat{y}\_i \right)^2 }
$$

Where:

* $y\_i$ is the true (observed) yield for the $i^{th}$ field
* $\hat{y}\_i$ is the predicted yield for the $i^{th}$ field
* $n$ is the total number of test samples

### Notes:

* Lower RMSE values indicate better model performance.
* The final leaderboard will be based on a hidden portion of the test set to ensure fair evaluation.
* In case of tied RMSE values, the participant who submitted first will be ranked higher.

This metric penalizes larger errors more heavily than smaller ones, encouraging models that are not only accurate on average but also robust across all predictions.