Winetech Technical Yearbook 2022

AUGUST

Hyperspectral – the answer to water stress? (PART 2)

THE RESEARCH PRESENTED IN PART 2 AIMS TO DERIVE A TWO-BAND OPTIMISED VEGETATION INDEX USING HYPERSPECTRAL DATA CAPTURED ACROSS THE VISIBLE NEAR-INFRARED (VNIR) REGION OF THE ELECTROMAGNETIC (EM) SPECTRUM.

BY MARC DUKES, NITESH POONA & KYLE LOGGENBERG

The HySpex VNIR-1800 hyperspectral camera.

BACKGROUND Vineyard water stress detection is essen tial to the sustainability of healthy and high-quality grapes. The early detection of water-stressed vines can aid in the preven tion of crop loss and increase productivity. Hyperspectral remote sensing techniques, coupled with the advanced analytics of machine learning, could provide an effec tive means of water stress detection. Part 1 of this two-part article series, published in June 2022, demonstrated the feasibility of using hyperspectral data to improve the modelling of vineyard water stress. In Part 2, the narrowband characteristics of hyperspectral data are exploited to develop vegetation indices that are optimised for detecting water stress in Shiraz vineyards. Vegetation indices are widely regarded as an industry standard due to their interpretabil ity and ease of use for various applications, such as vine row delineation and biomass estimation. Therefore, optimised vegetation indices for water stress detection are ideally suited for industry end-users.

TABLE 1. Spectral datasets used for developing optimal water stress index. Dataset time periods (T0) Date Use

Total samples

T1 (Stressed and non-stressed vines)

16th January Model training

240

T2 (Stressed and non-stressed vines)

23rd January Model testing

240

T3 (Stressed and non-stressed vines)

30th January Model testing

240

T4 (Stressed and non-stressed vines)

13th February Model testing

240

MATERIALS AND METHODS Multi-temporal data of water-stressed and non-stressed Shiraz vines were captured between 16 January and 13 February 2019. Leaf samples were collected in-field and imaged in a laboratory setting. Leaves were imaged using the HySpex VNIR 1800 hyperspectral camera (Norsk Elektro Optikk, Norway), which captured 186 wavebands across the VNIR (400 nm - 1 000 nm). Four datasets (table 1) were gen erated, comprising 120 leaf spectra sam

ples, per class (stressed and non-stressed) across four different acquisition dates. The optimised index was developed us ing a two-band ratio method (Eq 1) and a wrapper-based feature selection approach. Feature selection was undertaken using the Boruta wrapper 1 to identify the wave bands most relevant for discriminating wa ter-stressed from non-stressed vines. Once the important wavebands were identified, they were combined using Eq 1 to generate the optimised indices.

27

WINETECH TECHNICAL YEARBOOK 2022