SP.231 Dataset
=============

Description
-----------
* Target Soil Properties: SOM, pH, Clay
* Groups of Features: vis-NIR 
* Sample size: 231
* Number of Features: 271
* Coordinates: With coordinates (EPSG: 32654)
* Location: Saitama Prefecture, Japan
* Sampling Design: Two sampling designs over multiple fields depending on the soil conditions: (1) systematic sampling, in which samples are taken in the corners and middle of the field and (2) simple random sampling
* Study Area Size: 3.1 ha
* Geological Setting: Volcanic ash (Andosols)
* Previous Data Publication: None
* Contact Information:
    * Masakazu Kodaira (kodaira@cc.tuat.ac.jp), Tokyo University of Agriculture and Technology
* License: CC BY-SA 4.0
* Publication/Modification Date (d/m/y): 28.02.25, version 1.0
* Changelog:
    * Version 1.0 (28.02.25): Initial release

Details
-------

Dataset
^^^^^^^
The dataset contains the following target soil properties and features:

Target Soil Properties:
""""""""""""""""""""""

SOM - Soil Organic Matter
    * Code: ``SOM_target``
    * Unit: %
    * Protocol: Measured through the weight difference before and after ignition
    * Sampling Date: February 2017, December 2017 and February 2018
    * Sampling Depth: 0 - 15 cm

pH
    * Code: ``pH_target``
    * Unit: Unitless
    * Protocol: Measured in water suspension with a glass electrode with a 2.5:1 liquid:soil gravimetric ratio
    * Sampling Date: February 2017, December 2017 and February 2018
    * Sampling Depth: 0 - 15 cm

Clay
    * Code: ``Clay_target``
    * Unit: %
    * Protocol: Sieve-Pipette method, measured through fractioning the soil into the sand fractions by sieving, and the silt and clay fractions by sedimentation in water (Gee and Bauder 1986)
    * Sampling Date: February 2017, December 2017 and February 2018
    * Sampling Depth: 0 - 15 cm

Groups of Features:
"""""""""""""""""

vis-NIR – Visible and Near Infrared Spectroscopy
    * Number of Features: 271
    * Code(s): ``wl_350``, ``wl_355``, ``wl_360`` ... ``wl_1700``
    * Unit: % (Reflectance)
    * Sensing: Mounted vis-NIR spectrometer (SAS3000, Shibuya Seiki Co. Ltd., Ehime Prefecture, Japan), in-situ, spectral range was 320 – 1,700 nm at 1 - 7 nm intervals
    * Processing: Discarding noisy edges of the spectrum (320 - 350 nm), resampling to 5 nm intervals
    * Sampling Date: February 2017, December 2017 and February 2018
    * Spectral Information (After Data Processing):
        * Data Representation: Wavelength (in nm)
        * Spectral Resolution: 1 nm
        * Spectral Range: 350 - 1,700 nm

Examples
--------

.. code-block:: python

    from LimeSoDa import load_dataset, split_dataset
    from sklearn.linear_model import LinearRegression
    from sklearn.metrics import r2_score, mean_squared_error
    import numpy as np

    # Load and explore the dataset
    data = load_dataset("SP.231")
    dataset = data["Dataset"]
    folds = data["Folds"]
    coords = data["Coordinates"]

    # Split into train/test using fold 1
    X_train, X_test, y_train, y_test = split_dataset(
        data=data,
        fold=1,
        targets=["pH_target", "SOM_target", "Clay_target"]
    )

    # Fit model and get predictions
    model = LinearRegression()
    model.fit(X_train, y_train)
    predictions = model.predict(X_test)

    # Calculate performance metrics
    r2 = r2_score(y_test, predictions)
    rmse = np.sqrt(mean_squared_error(y_test, predictions))
    print(f"R-squared: {r2:.7f}")
    print(f"RMSE: {rmse:.7f}")

References
----------

Gee, G.W. & Bauder, J.W. (1986) Particle-Size Analysis. In: Klute, A., Ed., Methods of Soil Analysis, Part 1. Physical and Mineralogical Methods, Agronomy Monograph No. 9, 2nd Edition, American Society of Agronomy/Soil Science Society of America, Madison, WI, 383-411.