##Training Dataset (train_soc.csv):
- Dataset Name: KSSL dataset
- As a part of the SS4GG project, this dataset comprises 5165 unique locations with a total of 23898 laboratory measurements of SOC density.
##Validation Dataset (test_soc.csv)
The dataset contains both public and private test points. Public points are available for internal validation of your models. It will help you fine-tune and assess the accuracy of your predictions during the development phase. Private dataset represents the final test of your model's effectiveness in real-world scenarios. Your goal is to predict these hidden values accurately. 

## Columns
Explanation of columns (variables) in the training dataset can be found [here](https://docs.google.com/document/d/1IbzrJuyOBRFNTzXzcvw_y0O25fVfj2osJFs1TukHflw/edit?usp=sharing).

##Important columns are:
* `sample_id`: unique ID
* `logoc_d.f`: target variable in log-scale
* `X`, `Y`: easting and northing in EPSG 5070
* `observation_year`: observation year
* `olc_id`: Open Location ID (https://en.wikipedia.org/wiki/Open_Location_Code) this allows you to check unique locations of points
* `UUID`: Universally Unique Identifier (https://en.wikipedia.org/wiki/Universally_unique_identifier) this allows you to point to exact sample / unique row; 


Note that columns `hzn_top` and `hzn_bot` indicate upper and lower boundary of the soil layer (for example 0–30 cm depth interval has upper depth of 0 and lower depth of 30).