Applications of a Hyperspectral Imaging System Used to Estimate Wheat Grain Protein: A Review

Abstract

Recent research advances in wheat have focused not only on increasing grain yields, but also on establishing higher grain quality. Wheat quality is primarily determined by the grain protein content (GPC) and composition, and both of these are affected by nitrogen (N) levels in the plant as it develops during the growing season. Hyperspectral remote sensing is gradually becoming recognized as an economical alternative to traditional destructive field sampling methods and laboratory testing as a means of determining the N status within wheat. Currently, hyperspectral vegetation indices (VIs) and linear nonparametric regression are the primary tools for monitoring the N status of wheat. Machine learning algorithms have been increasingly applied to model the nonlinear relationship between spectral data and wheat N status. This study is a comprehensive review of available N-related hyperspectral VIs and aims to inform the selection of VIs under field conditions. The combination of feature mining and machine learning algorithms is discussed as an application of hyperspectral imaging systems. We discuss the major challenges and future directions for evaluating and assessing wheat N status. Finally, we suggest that the underlying mechanism of protein formation in wheat grains as determined by using hyperspectral imaging systems needs to be further investigated. This overview provides theoretical and technical support to promote applications of hyperspectral imaging systems in wheat N status assessments; in addition, it can be applied to help monitor and evaluate food and nutrition security.

Ensuring Explainability and Dimensionality Reduction in a Multidimensional HSI World for Early XAI-diagnostics of Plant Stress

“…It was shown that when using several popular classical ML methods, including Multi Layer Perceptron (MLP), the accuracy of plant drought state detection based on the full spectral characteristic of plants HSI, as well as its derivative, turned out to be higher than the accuracy obtained on a combination of 9 vegetation indices. Review [14] over the past almost 25 years is devoted to the development, based on ML and HSI data, of algorithms for detecting the quality of wheat grain protein and its relationship with nitrogen status.…”

Reviving grain quality in wheat through non‐destructive phenotyping techniques like hyperspectral imaging

“…Recently, significant progress has been made in the field of reflectance spectral analysis of different vegetation indices (VIs), including normalised difference vegetation index (NDVI) (Hansen & Schjoerring, 2003 ), medium terrestrial chlorophyll index (MTCI) and normalised pigments chlorophyll ratio index (NPCRI) (Tan et al, 2018 ), normalised water index (NWI) (Babar et al, 2006 ) and structural insensitive pigment index (SIPI) (Robles‐Zazueta et al, 2021 ) which are derived from the canopy with respect to plant nitrogen content. HSI application using different VIs to estimate plant nitrogen content has been reviewed elsewhere (Ma et al, 2022 ).…”

“…Recent reviews have focused on the use of HSI to investigate quality characteristics in cereals, including wheat (Caporaso et al, 2018b ), wheat grain protein estimation (Ma et al, 2022 ), quality assessment at different stages of supply chain (Karmakar et al, 2022 ), application of HSI in plant phenotyping (Sarić et al, 2022 ) and comparison of HSI with near infrared spectroscopy to investigate quality characteristics (Tahmasbian et al, 2021 ). In contrast, we will discuss in this review how the loss of genetic diversity in modern wheat breeding could have led to selection against grain quality and key traits that influence the nutritional value of wheat.…”

Hyperspectral remote sensing for tobacco quality estimation, yield prediction, and stress detection: A review of applications and methods

“…Fortunately, HRS technology, with its contactless observation, high spectral resolution, and flexibility, is gradually becoming recognized as a suitable alternative to traditional field sampling methods to obtain crop information ( Park and Lu, 2015 ; Ma et al., 2022 ). In the field of agricultural, the most important ability of HRS is that it can obtain sufficient hyperspectral reflectance data of crops with a non-destructive mean, and with the assistance of various regression modeling algorithms, the relationship between reflectance data and various crop agronomic traits (e.g., leaf nitrogen, chlorophyll, water content, etc.)…”

“…Thus, references cited in this review were mainly published from 2010 to 2022. Furthermore, according to our retrieval results, the existing reviews related HRS and agriculture applications cover various aspects: UAV-borne HRS ( Xiang et al., 2019 ), hyperspectral imaging technologies ( Adão et al., 2017 ; Mahlein et al., 2018 ), precision agricultural applications ( Bégué et al., 2018 ; Latif, 2018 ), leaf area index (LAI) ( Ke et al., 2016 ), crop yield prediction and nitrogen status assessment ( Chlingaryan et al., 2018 ; Fu et al., 2021 ), wheat grain protein ( Ma et al., 2022 ), etc. The rest of this article is organized as follows: in section 2, we introduce the principles and workflow of HRS applications for PTA; in section 3, we compare three commonly used hyperspectral data acquisition system platforms; the details of specific applications and methodologies are presented in section 4; the discussion of issues and recommendations is arranged in section 5; the conclusion is in section 6.…”