Hyperspectral imaging dataset of potato plants exposed to water-deficit condition

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.
• 28 cultivars of KIS Krka and 18 of KIS Savinja 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. 

Hyperspectral imaging: 

• Every week after the deficit was introduced.
• Total of 5 imaging sessions were performed.
• The imaging sessions took place in a dark room, where cameras were positioned at a 3 m distance from the potato plants, together with calibrated halogen lamps.
• Hyperspectral images were acquired in the VNIR (visible to near infrared) and SWIR (short-wave infrared) spectral regions. 
• Hyspex (Norsk Elektro Optikk, Oslo Norway) push-broom cameras VNIR-1600 (400–988 nm, 160 bands, bandwidth 3.6 nm) and SWIR-384 (950–2500 nm, 288 bands, bandwidth 5.4 nm) were used.

Files:

• File structure:

        📂 imagings
        ├── 📁 imaging-1
        │   ├── 📄 0_1_0__KK-K-04_KS-K-05_KK-S-03__imaging-1__1-22_20000_us_2x_HSNR02_ 2022-05-11T104633_corr_rad_f32.hdr
        │   ├── 📄 0_1_0__KK-K-04_KS-K-05_KK-S-03__imaging-1__1-22_20000_us_2x_HSNR02_2022-05-11T104633_corr_rad_f32.img
        │   └── 📄 ...
        ├── 📁 imaging-2
        │   └── 📄 ...
        ├── 📁 imaging-3
        │   └── 📄 ...
        ├── 📁 imaging-4
        │   └── 📄 ...
        └── 📁 imaging-5
            └── 📄 ...

• Description of a name:

A_B_C__L1_L2_L3__imaging-X__ID.img -> image file

A_B_C__L1_L2_L3__imaging-X__ID.hdr -> header file belonging to an image file

A - index of original raw hyperspectral image

B - index of an object on the image (of a particular potato plant)

C - index of slice extracted from the image

L - labels of plants on the image

X - index of the imaging session

ID - string identifier

• Description of labels (L):

V-T-N (e.g. KK-K-04)

V - variety (KK - KIS Krka or KS - KIS Savinja)

T - treatment (K - control or S, drought)

N - index of a particular plant

• Image properties:

Width of the image: 64

Height of the image: 64

Number of spectral bands: 448

Spectral range: 410nm - 2510nm

Image values are expressed in reflectance

Additional links:

Code where the dataset was used for the entire analysis could be found here:

https://github.com/Manuscripts-code/Potato-plants-drought--plants-2024