The participants can either use the provided training data to develop their models, or use gprMax to generate additional synthetic data to complement the existing dataset. The participants can also apply any pre-processing they think is necessary prior to training; and they can combine (or use exclusively) non-machine learning interpretation methods such as migration and full waveform inversion.

Submissions are evaluated on [mean absolute error](https://en.wikipedia.org/wiki/Mean_absolute_error) between the predicted models and the ground truth. The evaluation set consists of 100 models (Evaluation_Dataset), the average mean absolute error of these models will be the final score. 

**!! The evaluation models have missing traces. The participants will have to find a way to fill these missing values or train their model including "corrupted" data with missing values. More info in the Notebook *Filling_Missing_Values* !!**


## Submission File
You need to submit a .csv file with the following format

- Every row will be the flatten prediction (an image 224x224 flatten)
- The first column should be named 'Id' and have the index of the prediction (e.g. 1,2,3,4...).


If your predictions are saved in a numpy array called "predictions" with shape (100, 224, 224) i.e. 100 samples with dimensions 224x224, then you can use the following code to transform the numpy array to an eligible .csv format

`import pandas as pd`
`array_2d = predictions.reshape(100, -1)`
`df = pd.DataFrame(array_2d)`
`df["Id"] = range(len(df))`
`df.set_index('Id', inplace=True)`
`df.to_csv('name_of_the_file.csv')`