Deep Learning in Image-Based Plant Phenotyping

Murphy, Katherine M.; Ludwig, Ella; Gutierrez, Jorge; Gehan, Malia A.

doi:10.1146/annurev-arplant-070523-042828

Cited by 4 publications

(1 citation statement)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides ChatGPT as a tool to ask or write texts, among other tasks (OpenAI; https://chat.openai.com/chat ), probably one of the best-known tools now in life sciences, is AlphaFold and its successor Alphafold2, a model that can predict almost all protein tertiary structures (Senior et al 2020 ; Jumper et al 2021 ). Other examples are the use of AI in image analysis and image-based phenotyping, having autonomous robots and/or drones for plant phenotyping, pest management, fertilizer management, or harvesting (Harfouche et al 2023 ; Holzinger et al 2023 ; Murphy et al 2024 ). Furthermore, AI can be applied in bioinformatic analysis, to improve genome annotations, predict with high accuracy specific motifs in regulatory regions, gene function prediction, or predict the import nucleotide region or gene(s) in EMS screens or QTL analysis, etc.…”

Section: Conclusion and Perspectivementioning

confidence: 99%

Plant genome information facilitates plant functional genomics

Bernal-Gallardo,

de Folter

2024

Planta

View full text Add to dashboard Cite

Main conclusion In this review, we give an overview of plant sequencing efforts and how this impacts plant functional genomics research. Abstract Plant genome sequence information greatly facilitates the studies of plant biology, functional genomics, evolution of genomes and genes, domestication processes, phylogenetic relationships, among many others. More than two decades of sequencing efforts have boosted the number of available sequenced plant genomes. The first plant genome, of Arabidopsis, was published in the year 2000 and currently, 4604 plant genomes from 1482 plant species have been published. Various large sequence initiatives are running, which are planning to produce tens of thousands of sequenced plant genomes in the near future. In this review, we give an overview on the status of sequenced plant genomes and on the use of genome information in different research areas.

show abstract

Section: Conclusion and Perspectivementioning

confidence: 99%

Plant genome information facilitates plant functional genomics

Bernal-Gallardo,

de Folter

2024

Planta

View full text Add to dashboard Cite

show abstract

A New Intrusion Detection Model for Using CNN-LSTM with CatBoost for Detecting Known and Innovative Cyberattacks

Nithialakshmi,

Roselin,

Mohanapriya

2024

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)

View full text Add to dashboard Cite

Accurate classification of wheat freeze injury severity from the color information in digital canopy images

Zhang,

Huan,

Qiu

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

This paper explores whether it is feasible to use the RGB color information in images of wheat canopies that were exposed to low temperatures during the growth season to achieve fast, non-destructive, and accurate determination of the severity of any freeze injury it may have incurred. For the study presented in this paper, we compared the accuracy of a number of algorithmic classification models using either meteorological data reported by weather services or the color gradation skewness-distribution from high-definition digital canopy images acquired in situ as inputs against a reference obtained by manually assessing the severity of the freeze injury inflicted upon wheat populations at three experimental stations in Shandong, China. The algorithms we used to construct the models included in our study were based on either K-means clustering, systematic clustering, or naïve Bayesian classification. When analyzing the reliability of our models, we found that, at more than 85%, the accuracy of the Bayesian model, which used the color information as inputs and involved the use of prior data in the form of the reference data we had obtained through manual classification, was significantly higher than that of the models based on systematic or the K-means clustering, which did not involve the use of prior data. It was interesting to note that the determination accuracy of algorithms using meteorological factors as inputs was significantly lower than that of those using color information. We also noted that the determination accuracy of the Bayesian model had some potential for optimization, which prompted us to subject the inputs of the model to a factor analysis in order to identify the key independent leaf color distribution parameters characterizing wheat freeze injury severity. This optimization allowed us to improve the determination accuracy of the model to over 90%, even in environments comprising several different ecological zones, as was the case at one of our experimental sites. In conclusion, our naïve Bayesian classification algorithm, which uses six key color gradation skewness-distribution parameters as inputs and involves the use of prior data in the form of manual assessments, qualifies as a contender for the development of commercial-grade wheat freeze injury severity monitoring systems supporting post-freeze management measures aimed at ensuring food security.

show abstract

Deep Learning in Image-Based Plant Phenotyping

Cited by 4 publications

References 62 publications

Plant genome information facilitates plant functional genomics

Plant genome information facilitates plant functional genomics

A New Intrusion Detection Model for Using CNN-LSTM with CatBoost for Detecting Known and Innovative Cyberattacks

Accurate classification of wheat freeze injury severity from the color information in digital canopy images

Contact Info

Product

Resources

About