Applications of hyperspectral imaging in plant phenotyping. (March 2022)

• Record Type: Journal Article
• Authors: Sarić, Rijad; Nguyen, Viet D.; Burge, Timothy; Berkowitz, Oliver; Trtílek, Martin; Whelan, James; Lewsey, Mathew G.; Čustović, Edhem
• Is Part Of: Trends in plant science. Volume 27:Number 3(2022)
• Page Start: 301
• Page End: 315
• Publication Date: 2022-03
• Subjects: plant phenotyping -- noninvasive imaging -- hyperspectral imaging -- traits; Botany -- Periodicals; Botanique -- Périodiques; Botany; Periodicals; 580.5
• DOI: 10.1016/j.tplants.2021.12.003
• Languages: English
• ISSNs: 1360-1385

Abstract

Abstract : Our ability to interrogate and manipulate the genome far exceeds our capacity to measure the effects of genetic changes on plant traits. Much effort has been made recently by the plant science research community to address this imbalance. The responses of plants to environmental conditions can now be defined using a variety of imaging approaches. Hyperspectral imaging (HSI) has emerged as a promising approach to measure traits using a wide range of wavebands simultaneously in 3D to capture information in lab, glasshouse, or field settings. HSI has been applied to define abiotic, biotic, and quality traits for optimisation of crop management. Highlights: Hyperspectral imaging captures both spectral (λ) and spatial ( x, y ) information and merges these into a 3D data matrix termed a 'hyperspectral data cube' (hypercube). A 3D hyperspectral data cube consists of 2D of spatial information plus one spectral dimension that contains information for hundreds of spectral bands. Hyperspectral imaging has been applied to detect abiotic, biotic, and quality traits in plants in indoor and outdoor growing conditions. Hyperspectral imaging can be applied from a cellular to landscape scale to determine plant traits. Data processing and mining tools are still evolving, with machine learning and deep learning algorithms being used in order to assist scientists in predicting traits.