# EO Summer School 2025 Hackathon - NDVI time-series — Data

来源：https://www.kaggle.com/competitions/eo-summer-school-2025-hackathon-ndvi-reconstruct/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## Files

*   **train.csv** - The time series that need to be reconstructed, the rows are samples IDs, while columns the corresponding timeframe. Each element of the .csv can eather have and NDVI values or a not a value, in case the data is a gap.
*   **test.csv** - This specifies where the reconstruction will be evaluated (based on sample ID and timefreame) 
*   **sample_submission.csv** - a sample submission file in the correct format, corresponding to the NDVI values in the combinations of indices specified by test.csv.

## Additional data from neighbor tiles

Additional data from complete time-series (excluding gaps already present) from neighbor tiles will be released on Zenodo at https://zenodo.org/records/17017626.

As you will notice each image associated to a timframe contain several gaps. This is be due to missing Landsat scenes, cloud presence, and other sources of contaminants.
![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F28558337%2F234579aa3adda64fef939699a1b545f2%2FScreenshot%20from%202025-09-01%2013-52-42.png?generation=1756727714377673&alt=media)

## *In discussion you will find more info and some code on how to access the data!*