A probabilistic graphical model for describing the grape berry maturity

Baudrit, Cédric; Perrot, Nathalie; Brousset, Jean Marie; Abbal, Philippe; Guillemin, Hervé; Perret, Bruno; Goulet, Etienne; Guérin, Laurence; Barbeau, Gérard; Picque, Daniel

doi:10.1016/j.compag.2015.08.019

Cited by 8 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Statistical methods suitable for unbalanced one-way factorial dataset are needed to determine if one variable is significantly different among fruit species. To this end, “gao_cs” function of “nparcomp” package was applied to conduct a non-parametric multiple comparison ( Baudrit et al, 2015 ). Principal component analysis (PCA) was performed on mean-centered and scaled data with “dudi.pca” function of “ade4” package ( Dray and Dufour, 2007 ), in order to compare three drivers of soluble sugar concentration among fruit species.…”

Section: Methodsmentioning

confidence: 99%

Inter-Species Comparative Analysis of Components of Soluble Sugar Concentration in Fleshy Fruits

Dai

Baldazzi

et al. 2016

Front. Plant Sci.

View full text Add to dashboard Cite

The soluble sugar concentration of fleshy fruit is a key determinant of fleshy fruit quality. It affects directly the sweetness of fresh fruits and indirectly the properties of processed products (e.g., alcohol content in wine). Despite considerable divergence among species, soluble sugar accumulation in a fruit results from the complex interplay of three main processes, namely sugar import, sugar metabolism, and water dilution. Therefore, inter-species comparison would help to identify common and/or species-specific modes of regulation in sugar accumulation. For this purpose, a process-based mathematical framework was used to compare soluble sugar accumulation in three fruits: grape, tomato, and peach. Representative datasets covering the time course of sugar accumulation during fruit development were collected. They encompassed 104 combinations of species (3), genotypes (30), and growing conditions (19 years and 16 nutrient and environmental treatments). At maturity, grape showed the highest soluble sugar concentrations (16.5–26.3 g/100 g FW), followed by peach (2.2 to 20 g/100 g FW) and tomato (1.4 to 5 g/100 g FW). Main processes determining soluble sugar concentration were decomposed into sugar importation, metabolism, and water dilution with the process-based analysis. Different regulation modes of soluble sugar concentration were then identified, showing either import-based, dilution-based, or import and dilution dual-based. Firstly, the higher soluble sugar concentration in grape than in tomato is a result of higher sugar importation. Secondly, the higher soluble sugar concentration in grape than in peach is due to a lower water dilution. The third mode of regulation is more complicated than the first two, with differences both in sugar importation and water dilution (grape vs. cherry tomato; cherry tomato vs. peach; peach vs. tomato). On the other hand, carbon utilization for synthesis of non-soluble sugar compounds (namely metabolism) was conserved among the three fruit species. These distinct modes appear to be quite species-specific, but the intensity of the effect may significantly vary depending on the genotype and management practices. These results provide novel insights into the drivers of differences in soluble sugar concentration among fleshy fruits.

show abstract

Section: Methodsmentioning

confidence: 99%

Inter-Species Comparative Analysis of Components of Soluble Sugar Concentration in Fleshy Fruits

Dai

Baldazzi

et al. 2016

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…Another approach to address ignorance or potential uniformity is to use credal networks (Baudrit et al 2016), which are an extension of BNs as a safer option to model imprecise information using convex sets of probabilities. To better describe the observed "plateau" effect of the TMPs with the limiting Jp, dynamic BNs (Baudrit et al, 2015) could be useful for predicting TMP as soon as Jp no longer changes.…”

Section: Discussionmentioning

confidence: 99%

“…Uncertainty in the system is considered by quantifying the dependence between variables in the form of conditional probabilities. The use of BNs has been investigated recently in agri-food domains (Baudrit et al 2015;Drury et al 2017;Chapman et al 2018). This article discusses a numerical workflow to treat data and knowledge that combines ontologies, databases and computer calculation tools based on the theory of belief functions and BNs.…”

Section: Introductionmentioning

confidence: 99%

Decision Support Tool for the Agri-Food Sector Using Data Annotated by Ontology and Bayesian Network

Baudrit

Buche

Leconte

et al. 2022

International Journal of Agricultural and Environmental Information Systems

Self Cite

View full text Add to dashboard Cite

The scientific literature is a valuable source of information for developing predictive models to design decision support systems. However, scientific data are heterogeneously structured expressed using different vocabularies. This study developed a generic workflow that combines ontology, databases and computer calculation tools based on the theory of belief functions and Bayesian networks. The ontology paradigm is used to help integrate data from heterogeneous sources. Bayesian network is estimated using the integrated data taking into account their reliability. The proposed method is unique in the sense that it proposes an annotation and reasoning tool dedicated to systematic analysis of the literature, which takes into account expert knowledge of the domain at several levels: ontology definition, reliability criteria and dependence relations between variables in the BN. The workflow is assessed successfully by applying it to a complex food engineering process: skimmed milk microfiltration. It represents an original contribution to the state of the art in this application domain.

show abstract

“…For example the tool « Epicure » developed by the French Vineyard Institute (IFV) for managing phytosanitary risks (Raynal, et al 2010), or a work on the prediction of kinetics of fermentation in wine processes like (Goelzer et al, 2009). For the grape ripeness prediction, a model has been developed by (Baudrit, et al, 2015), (Perrot, et al, 2015) linking chemical indicators to weather conditions on Cabernet Franc grape berries. The approach presented in this paper is an extension of this latter work, with several important differences: (i) the target grape berries are for the Chenin wine, and this also reflects on the different structure of the dynamic Bayesian network; (ii) in contrast with the approach outlined in (Perrot, et al, 2015), no expert system is used to integrate the data set, as the available quantity of data is larger in this case; (iii) for the first time, a link between variables related to grape berries ripening and wine quality is provided, thanks to a fuzzy system.…”

Section: Introductionmentioning

confidence: 99%

A decision-support system to predict grape berry quality and wine potential for a Chenin vineyard

Perrot

Tonda

Brunetti

et al. 2022

Computers and Electronics in Agriculture

Self Cite

View full text Add to dashboard Cite

A probabilistic graphical model for describing the grape berry maturity

Cited by 8 publications

References 18 publications

Inter-Species Comparative Analysis of Components of Soluble Sugar Concentration in Fleshy Fruits

Inter-Species Comparative Analysis of Components of Soluble Sugar Concentration in Fleshy Fruits

Decision Support Tool for the Agri-Food Sector Using Data Annotated by Ontology and Bayesian Network

A decision-support system to predict grape berry quality and wine potential for a Chenin vineyard

Contact Info

Product

Resources

About