SiaPy data used in examples

The hyperspectral images were acquired using Hyspex push-broom cameras from Norsk Elektro Optikk (Oslo, Norway). Two spectral regions were covered:

- VNIR-1600: Visible to near-infrared (400–988 nm) with 160 bands and a bandwidth of 3.6 nm.- SWIR-384: Short-wave infrared (950–2500 nm) with 288 bands and a bandwidth of 5.4 nm.

The acquired hyperspectral data, expressed as reflectance values, were already radiometrically calibrated to ensure accuracy and reliability for subsequent analysis.

An experiment:

Greenhouse experiment under controlled environmental conditions.

Conducted at the Agricultural Institute of Slovenia (Ljubljana, Slovenia). 

From April to August 2021.

A night/day temperature of 21 °C/15 °C; relative humidity of 60%, and photoperiod of 14h.

KIS Krka and 18 KIS Savinja cultivars grown from tubers in 5-litre pots.

5 weeks after planting, half plants of both cultivars were randomly assigned to either water-deficient or well-watered groups. 

The water-deficient group was exposed to a limited water irrigation regime, i.e., up to 50% of substrate saturation field capacity. 

The soil moisture was surveilled using tensiometers (14.04.04 Jett Fill tensiometers, Eijkelkamp, Giesbeek Netherlands).

Throughout the duration of the experiment, the matric potential of the soil was maintained within the range -0,01 MPa to -0,025 MPa for well-watered plants, and -0,05 MPa to -0,07 MPa for water-deficient plants. 

Description of file names:

The file naming convention for the dataset is structured to provide detailed information about the contents and context of each file. The files include L1_L2_L3__test__ID_CAM.img, which represents an image file, and L1_L2_L3__test__ID_CAM.hdr, which is the corresponding header file for the image.

The naming components are as follows:

L: Denotes the labels of plants in the image.

ID: A random identifier assigned at the time the image is acquired.

CAM: Indicates the camera type used, where corr refers to VNIR and corr2 refers to SWIR.

Additionally, the label format is defined as V-T-N, such as KK-K-04. Each component within the label has a specific meaning:

V (Variety): Specifies the plant variety, with examples including KK for KIS Krka and KS for KIS Savinja.

T (Treatment): Refers to the type of treatment applied to the plant, such as K for Control or S for Drought.

N (Index): Represents the index number of a particular plant in the dataset.