Computational solutions for modeling and controlling plant response to abiotic stresses: a review with focus on iron deficiency

Tong, Haonan; Madison, Imani; Long, Terri A.; Williams, Cranos M.

doi:10.1016/j.pbi.2020.05.006

Cited by 17 publications

(9 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The emergence of advanced machine learning techniques, along with high-performance computational power, has provided new opportunities to translate image-based datasets into novel insights. In agriculture, machine learning and deep learning have been recently implemented to analyze images captured for various applications, such as biotic stress detection [26,27], abiotic stress detection [28,29], nitrogen estimation [30,31], spectral features selection for high-throughput phenotyping [32], weed detection [33,34] and yield prediction [17,35].…”

Section: Introductionmentioning

confidence: 99%

A Novel Machine Learning Approach to Estimate Grapevine Leaf Nitrogen Concentration Using Aerial Multispectral Imagery

et al. 2020

View full text Add to dashboard Cite

Assessment of the nitrogen status of grapevines with high spatial, temporal resolution offers benefits in fertilizer use efficiency, crop yield and quality, and vineyard uniformity. The primary objective of this study was to develop a robust predictive model for grapevine nitrogen estimation at bloom stage using high-resolution multispectral images captured by an unmanned aerial vehicle (UAV). Aerial imagery and leaf tissue sampling were conducted from 150 grapevines subjected to five rates of nitrogen applications. Subsequent to appropriate pre-processing steps, pixels representing the canopy were segmented from the background per each vine. First, we defined a binary classification problem using pixels of three vines with the minimum (low-N class) and two vines with the maximum (high-N class) nitrogen concentration. Following optimized hyperparameters configuration, we trained five machine learning classifiers, including support vector machine (SVM), random forest, XGBoost, quadratic discriminant analysis (QDA), and deep neural network (DNN) with fully-connected layers. Among the classifiers, SVM offered the highest F1-score (82.24%) on the test dataset at the cost of a very long training time compared to the other classifiers. Alternatively, QDA and XGBoost required the minimum training time with promising F1-score of 80.85% and 80.27%, respectively. Second, we transformed the classification into a regression problem by averaging the posterior probability of high-N class for all pixels within each of 150 vines. XGBoost exhibited a slightly larger coefficient of determination (R2 = 0.56) and lower root mean square error (RMSE) (0.23%) compared to other learning methods in the prediction of nitrogen concentration of all vines. The proposed approach provides values in (i) leveraging high-resolution imagery, (ii) investigating spatial distribution of nitrogen across a vine’s canopy, and (iii) defining spatial zones for nitrogen application and smart sampling.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Machine Learning Approach to Estimate Grapevine Leaf Nitrogen Concentration Using Aerial Multispectral Imagery

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In plant research, prediction using ensemble of neural networks is quite popular. The prediction performance of phenotype depends on the predictive modeling and analytics and is an exhaustive subject that has been reviewed recently (Kim & Tagkopoulos, 2018; Tong et al., 2020).…”

Section: Systems Biologymentioning

confidence: 99%

Systems biology for crop improvement

et al. 2021

View full text Add to dashboard Cite

In recent years, generation of large-scale data from genome, transcriptome, proteome, metabolome, epigenome, and others, has become routine in several plant species.Most of these datasets in different crop species, however, were studied independently and as a result, full insight could not be gained on the molecular basis of complex traits and biological networks. A systems biology approach involving integration of multiple omics data, modeling, and prediction of the cellular functions is required to understand the flow of biological information that underlies complex traits. In this context, systems biology with multiomics data integration is crucial and allows a holistic understanding of the dynamic system with the different levels of biological organization interacting with external environment for a phenotypic expression. Here, we present recent progress made in the area of various omics studies-integrative and systems biology approaches with a special focus on application to crop improvement. We have also discussed the challenges and opportunities in multiomics data integration, modeling, and understanding of the biology of complex traits underpinning yield and stress tolerance in major cereals and legumes.

show abstract

“…Systemic approaches could bring many advantages and pave the way toward comprehensive modelling. To obtain a comprehensive view of plant responses to environmental stresses, it will be important to integrate omics data with systemic biology data and to develop computational models [11,14,15]. In their review, Cramer et al [14] explored the perspectives of systemic approaches in determining molecular responses to abiotic stresses.…”

Section: Introductionmentioning

confidence: 99%

“…Although many of the functions of individual parts are unknown, their function can sometimes be inferred through association with other known parts, providing a better understanding of the biological system as a whole [14]. New models can be formed from the large amount of data collected and can lead to new hypotheses generated by these [15]. The most used models to describe signalling or metabolic pathways are based on theoretical models [15][16][17].…”

Section: Introductionmentioning

confidence: 99%

“…New models can be formed from the large amount of data collected and can lead to new hypotheses generated by these [15]. The most used models to describe signalling or metabolic pathways are based on theoretical models [15][16][17]. These models are based on the laws of physics and use differential or algebraic equations to represent biological processes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Meta-Analysis as a Tool to Identify Candidate Genes Involved in the Fagus sylvatica L. Abiotic Stress Response

Garosi

Ferrante

Vettori

et al. 2022

Forests

View full text Add to dashboard Cite

In this study, we aimed to evaluate whether candidate genes for abiotic stresses in Fagus sylvatica L. are also candidate genes for herbaceous plants, with the purpose of better defining the abiotic stress response model of F. sylvatica. Therefore, a meta-analysis was performed on published papers related to abiotic stress. Firstly, we carried out a systematic review regarding the activity of 24 candidate genes selected for F. sylvatica under abiotic stress reported in 503 articles. After choosing the inclusion criteria, 73 articles out of 503, regarding 12 candidate genes, were included in this analysis. We performed an exploratory meta-analysis based on the random-effect model and the combined effect-size approach (Cohen’s d). The results obtained through Forest and Funnel plots indicate that the candidate genes for F. sylvatica are considered to be candidate genes in other herbaceous species. These results allowed us to set up models of plants’ response to abiotic stresses implementing the stress models in forest species. The results of this study will serve to bridge knowledge gaps regarding the pathways of response to abiotic stresses in trees based on the meta-analysis. The study approach used could be extended to observe larger gene databases and different species.

show abstract

Computational solutions for modeling and controlling plant response to abiotic stresses: a review with focus on iron deficiency

Cited by 17 publications

References 55 publications

A Novel Machine Learning Approach to Estimate Grapevine Leaf Nitrogen Concentration Using Aerial Multispectral Imagery

A Novel Machine Learning Approach to Estimate Grapevine Leaf Nitrogen Concentration Using Aerial Multispectral Imagery

Systems biology for crop improvement

Meta-Analysis as a Tool to Identify Candidate Genes Involved in the Fagus sylvatica L. Abiotic Stress Response

Contact Info

Product

Resources

About