Overview of Datasets
===================

This section provides an overview of the datasets available in LimeSoDa. The datasets vary in size, features, and sensor types used for data collection.

Dataset Characteristics
----------------------

The following characteristics are documented for each dataset:

- **Dataset_ID**: Unique identifier/name of the dataset
- **Number_of_samples**: Number of analyzed soil samples (rows) in the dataset
- **Number_of_features**: Number of features (columns) in the dataset
- **Sensors**: Types of sensors used to create the features
- **Coordinates**: Availability of coordinates or dummy covariates
- **Location**: Geographic location where data was collected
- **Study_area_in_ha**: Size of the study area in hectares
- **Sampling_Design**: Brief description of the sampling methodology

Sensor Types
-----------

The datasets incorporate data from various sensor types:

- **CSMoisture**: Capacitive soil moisture
- **DEM**: Digital elevation model and terrain parameters
- **ERa**: Apparent electrical resistivity
- **Gamma**: Gamma-ray activity
- **MIR**: Mid infrared spectroscopy
- **NIR**: Near infrared spectroscopy
- **pH-ISE**: Ion selective electrodes for pH determination
- **RSS**: Remote sensing derived spectral data
- **VI**: Vegetation indices
- **vis-NIR**: Visible and near infrared spectroscopy
- **XRF**: X-ray fluorescence derived elemental concentrations

Dataset Details
--------------

For detailed information about specific datasets, please refer to their individual documentation pages:

- :doc:`B_204`
- :doc:`BB_250`
- :doc:`BB_30_1`
- :doc:`BB_30_2`
- :doc:`BB_51`
- :doc:`BB_72`
- :doc:`CV_98`
- :doc:`G_104`
- :doc:`G_150`
- :doc:`H_138`
- :doc:`MG_112`
- :doc:`MG_44`
- :doc:`MGS_101`
- :doc:`MWP_36`
- :doc:`NRW_115`
- :doc:`NRW_42`
- :doc:`NRW_62`
- :doc:`NSW_52`
- :doc:`O_32`
- :doc:`PC_45`
- :doc:`RP_62`
- :doc:`SA_112`
- :doc:`SC_50`
- :doc:`SC_93`
- :doc:`SL_125`
- :doc:`SM_40`
- :doc:`SP_231`
- :doc:`SSP_460`
- :doc:`SSP_58`
- :doc:`UL_120`
- :doc:`W_50`

The complete dataset contains 31 distinct soil sample collections with varying characteristics and purposes.