# GprMax Deep Learning Challenge 1 (GDLC-1) — Data

来源：https://www.kaggle.com/competitions/gpr-max-deep-learning-challenge-1-gdlc-1/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## Description of the Data - Overview

The data consists of 4400 synthetically generated B-Scans and their corresponding 4400 ground truth models, which are the 2D permittivity distributions for each model. The data are saved in numpy arrays (.npy) in the folders Input_Data and Ground_Truth. 

The B-Scans of the training data consist of 230 equidistant traces every 20 cm from the transmitter. The discretisation step of the time domain is 3.0434 ns and the total steps are 230 i.e. a total of 700 ns collected. The only processing applied to the data is a time varying gain i.e. every trace A(t) was multiplied by $$A(n\cdot dt) = A(n\cdot dt)*n^{3}$$, where *n* is the time index of the FDTD simulation i.e. n = t/dt, where dt = 0.0467 ns (the discretisation step of the FDTD based on the Courant limit).

Conclusively, the B-Scans are 2D gray images with 230x230 dimensions. These images will be the inputs in the machine learning model. The B-Scans are not scaled!

The ground truth data consist of 2D gray images 224x224 dimensions. The discretisation step of the x-axis is 22.32 cm, and the discretisation step of the y-axis is 9.82 cm i.e. the whole domain is 50x22 meters. The values of the permittivities vary from 1 (permittivity of free space) to 10, which is an approximation of the upper permittivity value we expect to find in Lunar and Martian environments. 

**To simplify the problem and express it in an abstract manner, we need to develop an image-to-image translation that will take a B-Scan (230x230 gray image) as input and give the ground truth (224x224 gray image) as output. **

!! Notice that the BScans in the training data are complete, while the BScans in the evaluation set have many missing traces !!

## Description of the data - FDTD Details 

Below are the FDTD parameters used to synthetically generate the models (more info in the Notebook *gprMax_Simulations.ipynb*)
- Spatial step: dx = dy = dz = 0.02 cm 
- Domain: 2D   50.02 x 24 meters  
- Time step: 0.99 Courant limit
- PML layers: 60 
- Source characteristics: randomly selected pulses with central frequency that varies from 60 - 100 MHz and different types of pulses.

## Description of the data - Geometry

The models consist of randomly generated layers with different permittivities, different stochastic distributions of permittivities, different sampling rates between min and max permittivity, and different stochastic surface. The number of layers and their parameters are chosen randomly in each execution resulting to a wide range of models with complex geometries and stochastic formations. More information can be found in the Notebook *gprMax_Simulations* and in the notebook *Open and Explore Data*.

## Files - Training Data

*   **Training_Bscan** - Folder that contains the .npy files for the processed (time-varying gain) B-Scan.
*   **Bscan_{n}.npy** - Input data. The nth Bscan saved in a numpy array,  np.shape(B_Scan{n}.npy) = (230,230).
*   **Training_Labels** - Folder that contains the .npy files for the ground truth i.e. relative permittivity structure.
*   **Model_{n}.npy** -  Labels. The nth ground truth model saved in a numpy array,  np.shape(Model_{n}.npy) = (224,224).

## Files - Testing Data
*   **Evaluation_Dataset** - Folder that contains the .npy files for the processed (time-varying gain) B-Scan from the testing set.
*   **Testing_Bscan_{n}.npy** - Input data. The nth testing Bscan saved in a numpy array,  np.shape(B_Scan{n}.npy) = (230,230).

These Bscans have missing traces. This is to add an extra challenge to the competition resemblance missing data or bad quality data that need to be interpolated. The participants need to find a way to train their model for missing data or develop a way to fill the missing data prior to inversion.

## Notebook
Check the notebook *Open and Explore Training Data* and *Open and Explore Evaluation Data* for more information on how to open and visualise the data.

## Paper 

More information can be found in the paper 

**Giannakis, I., Warren, C., Giannopoulos, A., Leontidis, G., Su, Y., Zhou, F., Martin-Torres, J., Diamanti, N.,
"Investigating the Capabilities of Deep Learning for Processing and Interpreting One-Shot Multi-offset GPR Data: A Numerical Case Study for Lunar and Martian Environments", arXiv:2410.14386, 2024**

https://doi.org/10.48550/arXiv.2410.14386