A high‐resolution model of the grapevine leaf morphospace predicts synthetic leaves

Societal Impact Statement Grapevine leaves are emblematic of the strong visual associations people make with plants. Leaf shape is immediately recognizable at a glance, and therefore, this is used to distinguish grape varieties. In an era of computationally enabled machine learning‐derived represent...

Full description

Saved in:
Bibliographic Details
Main Authors: Daniel H. Chitwood, Efrain Torres‐Lomas, Ebi S. Hadi, Wolfgang L. G. Peterson, Mirjam F. Fischer, Sydney E. Rogers, Chuan He, Michael G. F. Acierno, Shintaro Azumaya, Seth Wayne Benjamin, Devendra Prasad Chalise, Ellice E. Chess, Alex J. Engelsma, Qiuyi Fu, Jirapa Jaikham, Bridget M. Knight, Nikita S. Kodjak, Adazsofia Lengyel, Brenda L. Muñoz, Justin T. Patterson, Sundara I. Rincon, Francis L. Schumann, Yujie Shi, Charlie C. Smith, Mallory K. St. Clair, Carly S. Sweeney, Patrick Whitaker, James Wu, Luis Diaz‐Garcia
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Plants, People, Planet
Subjects:
Online Access:https://doi.org/10.1002/ppp3.10561
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850264707919773696
author Daniel H. Chitwood
Efrain Torres‐Lomas
Ebi S. Hadi
Wolfgang L. G. Peterson
Mirjam F. Fischer
Sydney E. Rogers
Chuan He
Michael G. F. Acierno
Shintaro Azumaya
Seth Wayne Benjamin
Devendra Prasad Chalise
Ellice E. Chess
Alex J. Engelsma
Qiuyi Fu
Jirapa Jaikham
Bridget M. Knight
Nikita S. Kodjak
Adazsofia Lengyel
Brenda L. Muñoz
Justin T. Patterson
Sundara I. Rincon
Francis L. Schumann
Yujie Shi
Charlie C. Smith
Mallory K. St. Clair
Carly S. Sweeney
Patrick Whitaker
James Wu
Luis Diaz‐Garcia
author_facet Daniel H. Chitwood
Efrain Torres‐Lomas
Ebi S. Hadi
Wolfgang L. G. Peterson
Mirjam F. Fischer
Sydney E. Rogers
Chuan He
Michael G. F. Acierno
Shintaro Azumaya
Seth Wayne Benjamin
Devendra Prasad Chalise
Ellice E. Chess
Alex J. Engelsma
Qiuyi Fu
Jirapa Jaikham
Bridget M. Knight
Nikita S. Kodjak
Adazsofia Lengyel
Brenda L. Muñoz
Justin T. Patterson
Sundara I. Rincon
Francis L. Schumann
Yujie Shi
Charlie C. Smith
Mallory K. St. Clair
Carly S. Sweeney
Patrick Whitaker
James Wu
Luis Diaz‐Garcia
author_sort Daniel H. Chitwood
collection DOAJ
description Societal Impact Statement Grapevine leaves are emblematic of the strong visual associations people make with plants. Leaf shape is immediately recognizable at a glance, and therefore, this is used to distinguish grape varieties. In an era of computationally enabled machine learning‐derived representations of reality, we can revisit how we view and use the shapes and forms that plants display to understand our relationship with them. Using computational approaches combined with time‐honored methods, we can predict theoretical leaves that are possible, enabling us to understand the genetics, development, and environmental responses of plants in new ways. Summary Grapevine leaves are a model morphometric system. Sampling over 10,000 leaves using dozens of landmarks, the genetic, developmental, and environmental basis of leaf shape has been studied and a morphospace for the genus Vitis predicted. Yet, these representations of leaf shape fail to capture the exquisite features of leaves at high resolution. We measure the shapes of 139 grapevine leaves using 1672 pseudo‐landmarks derived from 90 homologous landmarks with Procrustean approaches. From hand traces of the vasculature and blade, we have derived a method to automatically detect landmarks and place pseudo‐landmarks that results in a high‐resolution representation of grapevine leaf shape. Using polynomial models, we create continuous representations of leaf development in 10 Vitis spp. We visualize a high‐resolution morphospace in which genetic and developmental sources of leaf shape variance are orthogonal to each other. Using classifiers, Vitis vinifera, Vitis spp., rootstock and dissected leaf varieties as well as developmental stages are accurately predicted. Theoretical eigenleaf representations sampled from across the morphospace that we call synthetic leaves can be classified using models. By predicting a high‐resolution morphospace and delimiting the boundaries of leaf shapes that can plausibly be produced within the genus Vitis, we can sample synthetic leaves with realistic qualities. From an ampelographic perspective, larger numbers of leaves sampled at lower resolution can be projected onto this high‐resolution space, or, synthetic leaves can be used to increase the robustness and accuracy of machine learning classifiers.
format Article
id doaj-art-985054801be4423eb8a6e896cc79abe9
institution OA Journals
issn 2572-2611
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Plants, People, Planet
spelling doaj-art-985054801be4423eb8a6e896cc79abe92025-08-20T01:54:38ZengWileyPlants, People, Planet2572-26112025-01-017113314610.1002/ppp3.10561A high‐resolution model of the grapevine leaf morphospace predicts synthetic leavesDaniel H. Chitwood0Efrain Torres‐Lomas1Ebi S. Hadi2Wolfgang L. G. Peterson3Mirjam F. Fischer4Sydney E. Rogers5Chuan He6Michael G. F. Acierno7Shintaro Azumaya8Seth Wayne Benjamin9Devendra Prasad Chalise10Ellice E. Chess11Alex J. Engelsma12Qiuyi Fu13Jirapa Jaikham14Bridget M. Knight15Nikita S. Kodjak16Adazsofia Lengyel17Brenda L. Muñoz18Justin T. Patterson19Sundara I. Rincon20Francis L. Schumann21Yujie Shi22Charlie C. Smith23Mallory K. St. Clair24Carly S. Sweeney25Patrick Whitaker26James Wu27Luis Diaz‐Garcia28Department of Horticulture Michigan State University East Lansing Michigan USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Horticulture Michigan State University East Lansing Michigan USADepartment of Plant, Soil, and Microbial Sciences Michigan State University East Lansing Michigan USADepartment of Land, Air, & Water Resources University of California at Davis Davis California USADepartment of Horticulture Michigan State University East Lansing Michigan USADepartment of Horticulture Michigan State University East Lansing Michigan USADepartment of Horticulture Michigan State University East Lansing Michigan USADepartment of Horticulture Michigan State University East Lansing Michigan USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Land, Air, & Water Resources University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Horticulture Michigan State University East Lansing Michigan USADepartment of Horticulture Michigan State University East Lansing Michigan USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USADepartment of Viticulture and Enology University of California at Davis Davis California USASocietal Impact Statement Grapevine leaves are emblematic of the strong visual associations people make with plants. Leaf shape is immediately recognizable at a glance, and therefore, this is used to distinguish grape varieties. In an era of computationally enabled machine learning‐derived representations of reality, we can revisit how we view and use the shapes and forms that plants display to understand our relationship with them. Using computational approaches combined with time‐honored methods, we can predict theoretical leaves that are possible, enabling us to understand the genetics, development, and environmental responses of plants in new ways. Summary Grapevine leaves are a model morphometric system. Sampling over 10,000 leaves using dozens of landmarks, the genetic, developmental, and environmental basis of leaf shape has been studied and a morphospace for the genus Vitis predicted. Yet, these representations of leaf shape fail to capture the exquisite features of leaves at high resolution. We measure the shapes of 139 grapevine leaves using 1672 pseudo‐landmarks derived from 90 homologous landmarks with Procrustean approaches. From hand traces of the vasculature and blade, we have derived a method to automatically detect landmarks and place pseudo‐landmarks that results in a high‐resolution representation of grapevine leaf shape. Using polynomial models, we create continuous representations of leaf development in 10 Vitis spp. We visualize a high‐resolution morphospace in which genetic and developmental sources of leaf shape variance are orthogonal to each other. Using classifiers, Vitis vinifera, Vitis spp., rootstock and dissected leaf varieties as well as developmental stages are accurately predicted. Theoretical eigenleaf representations sampled from across the morphospace that we call synthetic leaves can be classified using models. By predicting a high‐resolution morphospace and delimiting the boundaries of leaf shapes that can plausibly be produced within the genus Vitis, we can sample synthetic leaves with realistic qualities. From an ampelographic perspective, larger numbers of leaves sampled at lower resolution can be projected onto this high‐resolution space, or, synthetic leaves can be used to increase the robustness and accuracy of machine learning classifiers.https://doi.org/10.1002/ppp3.10561ampelographygrapevineleaf developmentleaf shapemorphospaceVitis
spellingShingle Daniel H. Chitwood
Efrain Torres‐Lomas
Ebi S. Hadi
Wolfgang L. G. Peterson
Mirjam F. Fischer
Sydney E. Rogers
Chuan He
Michael G. F. Acierno
Shintaro Azumaya
Seth Wayne Benjamin
Devendra Prasad Chalise
Ellice E. Chess
Alex J. Engelsma
Qiuyi Fu
Jirapa Jaikham
Bridget M. Knight
Nikita S. Kodjak
Adazsofia Lengyel
Brenda L. Muñoz
Justin T. Patterson
Sundara I. Rincon
Francis L. Schumann
Yujie Shi
Charlie C. Smith
Mallory K. St. Clair
Carly S. Sweeney
Patrick Whitaker
James Wu
Luis Diaz‐Garcia
A high‐resolution model of the grapevine leaf morphospace predicts synthetic leaves
Plants, People, Planet
ampelography
grapevine
leaf development
leaf shape
morphospace
Vitis
title A high‐resolution model of the grapevine leaf morphospace predicts synthetic leaves
title_full A high‐resolution model of the grapevine leaf morphospace predicts synthetic leaves
title_fullStr A high‐resolution model of the grapevine leaf morphospace predicts synthetic leaves
title_full_unstemmed A high‐resolution model of the grapevine leaf morphospace predicts synthetic leaves
title_short A high‐resolution model of the grapevine leaf morphospace predicts synthetic leaves
title_sort high resolution model of the grapevine leaf morphospace predicts synthetic leaves
topic ampelography
grapevine
leaf development
leaf shape
morphospace
Vitis
url https://doi.org/10.1002/ppp3.10561
work_keys_str_mv AT danielhchitwood ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT efraintorreslomas ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT ebishadi ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT wolfganglgpeterson ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT mirjamffischer ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT sydneyerogers ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT chuanhe ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT michaelgfacierno ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT shintaroazumaya ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT sethwaynebenjamin ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT devendraprasadchalise ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT elliceechess ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT alexjengelsma ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT qiuyifu ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT jirapajaikham ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT bridgetmknight ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT nikitaskodjak ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT adazsofialengyel ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT brendalmunoz ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT justintpatterson ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT sundarairincon ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT francislschumann ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT yujieshi ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT charliecsmith ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT mallorykstclair ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT carlyssweeney ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT patrickwhitaker ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT jameswu ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT luisdiazgarcia ahighresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT danielhchitwood highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT efraintorreslomas highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT ebishadi highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT wolfganglgpeterson highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT mirjamffischer highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT sydneyerogers highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT chuanhe highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT michaelgfacierno highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT shintaroazumaya highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT sethwaynebenjamin highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT devendraprasadchalise highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT elliceechess highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT alexjengelsma highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT qiuyifu highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT jirapajaikham highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT bridgetmknight highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT nikitaskodjak highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT adazsofialengyel highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT brendalmunoz highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT justintpatterson highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT sundarairincon highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT francislschumann highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT yujieshi highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT charliecsmith highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT mallorykstclair highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT carlyssweeney highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT patrickwhitaker highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT jameswu highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves
AT luisdiazgarcia highresolutionmodelofthegrapevineleafmorphospacepredictssyntheticleaves