Hyperspectral imaging facilitates early detection of Orobanche cumana below-ground parasitism on sunflower under field conditions

Atsmon, Guy; Nehurai, Omer; Kizel, Fadi; Eizenberg, Hanan; Lati, Ran Nisim

doi:10.1016/j.compag.2022.106881

Cited by 12 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionsupporting

confidence: 55%

“…Furthermore, the accuracy level of the HSI methodology was high (>90%) and remained robust throughout the experiment, which confirms the suitability of HSI for this detection task. The use of ML models to analyze the spectral data produced accurate and robust detection results, as was previously found for early detection of other stresses and pests (Abdulridha et al, 2020;Atsmon et al, 2022;Lowe et al, 2017). Spatial aspects are also highly important for effective detection of non-optimal weed control, and any method that purports to be motivated by practicability should be designed to take large-scale high-throughput capabilities into consideration (van Evert et al, 2017).…”

Section: Discussionmentioning

confidence: 72%

See 1 more Smart Citation

Early detection of the herbicidal effect of glyphosate and glufosinate by using hyperspectral imaging

Nehurai,

Atsmon,

Kizel

et al. 2023

Agronomy Journal

Self Cite

View full text Add to dashboard Cite

Early detection of non‐optimal weed control is now a priority to ensure herbicide efficacy. This study aimed to evaluate the potential of hyperspectral imaging (HSI) for early detection of the effects of glyphosate and glufosinate on weeds. Specific features (bands and vegetation indices [VIs]) were extracted as indicators for glyphosate and glufosinate efficacy. Black nightshade (Solanum nigrum L.) was used as the model weed and treated with glyphosate or glufosinate at the fourth‐leaf stage. Plants were imaged in the laboratory at 6, 24, 48, 72, and 96 hours after treatment (HAT) with a 204‐wavelength (400–1000 nm) hyperspectral camera. The impact of the herbicide treatments on the spectral reflectance values was analyzed using the two‐sided Mann–Whitney U test, followed by classification with a machine learning (ML) model applied on the full spectrum and on 12 VIs. In addition, the contribution of the different wavelengths (features) to classification accuracy was assessed using a feature selection process. For glufosinate, 95% classification accuracy was observed as early as 6 HAT, with four features from the green region required. For glyphosate, four features from the red, red‐edge, and green regions were used to achieve 88% classification accuracy at 24 HAT. The accuracy of VIs‐based classification was generally lower than that of the full spectrum classification accuracy. Above 85% classification accuracy was achieved only at later imaging campaigns, starting at 48 HAT. This study thus demonstrates that non‐optimal application of glyphosate and glufosinate can indeed be detected using spectral imaging.

show abstract

Section: Discussionsupporting

confidence: 55%

Section: Discussionmentioning

confidence: 72%

Early detection of the herbicidal effect of glyphosate and glufosinate by using hyperspectral imaging

Nehurai,

Atsmon,

Kizel

et al. 2023

Agronomy Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…Sunflower is affected by nutritional disorders caused by a holoparasite, a broomrape (Orobanche cumana Wallr.). Logistic regression enables the classification of infected and non-infected sunflowers [197]. An interesting study was conducted on sunflower leaves to classify leaf spots, rust, and powdering mildew with respect to healthy leaves [198].…”

Section: Overview Of Digital Sunflower Phenotypingmentioning

confidence: 99%

An Overview of Machine Learning Applications on Plant Phenotyping, with a Focus on Sunflower

Centorame,

Gasperini,

Ilari

et al. 2024

Agronomy

View full text Add to dashboard Cite

Machine learning is a widespread technology that plays a crucial role in digitalisation and aims to explore rules and patterns in large datasets to autonomously solve non-linear problems, taking advantage of multiple source data. Due to its versatility, machine learning can be applied to agriculture. Better crop management, plant health assessment, and early disease detection are some of the main challenges facing the agricultural sector. Plant phenotyping can play a key role in addressing these challenges, especially when combined with machine learning techniques. Therefore, this study reviews available scientific literature on the applications of machine learning algorithms in plant phenotyping with a specific focus on sunflowers. The most common algorithms in the agricultural field are described to emphasise possible uses. Subsequently, the overview highlights machine learning application on phenotyping in three primaries areas: crop management (i.e., yield prediction, biomass estimation, and growth stage monitoring), plant health (i.e., nutritional status and water stress), and disease detection. Finally, we focus on the adoption of machine learning techniques in sunflower phenotyping. The role of machine learning in plant phenotyping has been thoroughly investigated. Artificial neural networks and stacked models seems to be the best way to analyse data.

show abstract

“…An often neglected limitation is the availability of fast but sufficiently reliable screening techniques that allow us to find what we need [87]. Hyperspectral imaging is being adjusted for early detection of broomrape infection to help with precise herbicide application in terms of time and space [169], with continuous attempts also to automate image phenotyping in seedling responses in rhizotrons [170], which is still too laborious and time-consuming. As a result, sources of resistance to broomrape are limited and poorly characterized.…”

Section: Potential Applications Of Biotechnology In Broomrape Resista...mentioning

confidence: 99%

Managing Root Parasitic Weeds to Facilitate Legume Reintroduction into Mediterranean Rain-Fed Farming Systems

Rubiales

2023

Soil Systems

View full text Add to dashboard Cite

Grain and forage legumes are important sources of food and feed, key for sustainable agriculture given the environmental services they provide. However, their cultivation is hampered in the Mediterranean Basin and Near East by the widespread occurrence of the root parasitic weed crenate broomrape (Orobanche crenata). Other broomrape species such as O. minor, O. foetida, and Phelipanche aegyptica are also of local importance. As for other parasitic weeds, a number of management strategies have been proposed, but considering that temperate legumes in the area are low-input crops, these strategies are largely uneconomical or hard to achieve, leaving the use of resistant cultivars as the most desirable option. Breeding for broomrape resistance is not an easy task, but significant progress has been achieved by classical breeding and selection and will profit from recent developments in phenomics and genomics. Here, achievements and prospects in broomrape management and resistance breeding are presented and critically discussed.

show abstract

Hyperspectral imaging facilitates early detection of Orobanche cumana below-ground parasitism on sunflower under field conditions

Cited by 12 publications

References 28 publications

Early detection of the herbicidal effect of glyphosate and glufosinate by using hyperspectral imaging

Early detection of the herbicidal effect of glyphosate and glufosinate by using hyperspectral imaging

An Overview of Machine Learning Applications on Plant Phenotyping, with a Focus on Sunflower

Managing Root Parasitic Weeds to Facilitate Legume Reintroduction into Mediterranean Rain-Fed Farming Systems

Contact Info

Product

Resources

About