# Dark Matter signal search. Episode 2.1 — Data

来源：https://www.kaggle.com/competitions/dmse-2-1/data

采集时间：2026-10-24T15:51:02Z

OPERA detector consists of several huge layers of special sensitive blocks *).
![OPERA overall](https://storage.googleapis.com/kaggle-media/competitions/inclass/6986/media/opera_2d.png)
Each layer is constructed as a wall of a special sandwich-like detection modules, called bricks *):
![](https://storage.googleapis.com/kaggle-media/competitions/inclass/6986/media/opera_ecc_scanning.png)
Such bricks interleave lead with photo emulsion. So as neutrino goes through the brick, it may interact with the lead and produce shower-like patterns, that are described by coordinates and angles of the initial particle and the collection of tracks that belong to the shower. The signal sample consists of simulated events. To obtain background sample the emulsion plates has been exposed to cosmic rays during creation, transportation, etc. Such traces which are mostly random is the main source of the background.
File descriptions
DS_2_train.csv
- the training set
DS_2_test.csv
- the test set
Data fields in training/test sets
training/test samples
Id
- ID of a track
X
- X coordinate of the track start
Y
- Y coordinate of the track start
Z
- Z coordinate of the track start
TX
- angle of the track in XZ plane
TY
- angle of the track in YZ plane
chi2
- goodness of fit of the track line to the track hits
there is
signal
field in the training set, which equals to
1.0
for signal event and to
0.0
otherwise.
Training set also has field
event_id
either equals to -999, which means this track is a background or equals to shower ID (like in Episode 1) in case it is signal.
Unlike Episode 1, there are no starting points of the showers. This makes the problem much more challenging, but much closer to the proposed SHIP detector setting.
*) images are courtesy of OPERA collaboration.