Skip to main content

ORIGINAL RESEARCH article

Front. Plant Sci.
Sec. Sustainable and Intelligent Phytoprotection
Volume 15 - 2024 | doi: 10.3389/fpls.2024.1409821
This article is part of the Research Topic AI, Sensors and Robotics in Plant Phenotyping and Precision Agriculture, Volume III View all 5 articles

Deep learning-based hyperspectral imaging provides whole vine characterization of rootstock influence on grapevine scion photosynthesis

Provisionally accepted
Prakriti Sharma Prakriti Sharma Imasha Thilakarathna Imasha Thilakarathna Anne Y. Fennell Anne Y. Fennell *
  • South Dakota State University, Brookings, United States

The final, formatted version of the article will be published soon.

    Rootstocks are gaining importance in viticulture as a strategy to combat abiotic challenges, as well as, enhancing scion physiology. Photosynthetic parameters such as maximum rate of carboxylation of RuBP (Vcmax) and the maximum rate of electron transport driving RuBP regeneration (Jmax) have been identified as ideal targets for potential influence by rootstock and breeding. However, leaf specific direct measurement of these photosynthetic parameters is time consuming, limiting the information scope and the number of individuals that can be screened. In contrast, hyperspectral imaging using the optical properties of the entire vine provides the potential to predict these physiological traits at canopy level. In this study, estimates of Vcmax and Jmax were assessed using canopy reflectance metrics obtained for wavelengths ranging from 400 to 1000nm integrated through artificial intelligence-based (AI) model algorithms. Prediction models were developed using two growing seasons data, from Vitis hybrid ‘Marquette’ grafted to five commercial rootstocks and homografted to ‘Marquette’. For the six different rootstocks, significant differences in photosynthetic efficiency (Vcmax and Jmax) were noted for both direct and indirect measurements, indicating that rootstock genotype has a significant influence on scion photosynthesis. Evaluation of multiple feature-extraction algorithms indicated the proposed Vitis base model incorporating a 1D-Convolution neural Network (CNN) had the best prediction performance with an R2 of 0.60 for Vcmax and Jmax. Inclusion of weather and chlorophyll parameters slightly improved model performance for both both photosynthetic parameters Integrated AI and hyperspectral remote sensing provide potential for high-throughput whole vine assessment of photosynthetic performance and selection of rootstock genotypes that confer improved photosynthetic performance potential in the scion.

    Keywords: V. hybrid 'Marquette', graft, Vitis, Convolution Neural Network, Computer Vision, machine learning, Artificial intelligence (AI)

    Received: 31 Mar 2024; Accepted: 12 Aug 2024.

    Copyright: © 2024 Sharma, Thilakarathna and Fennell. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Anne Y. Fennell, South Dakota State University, Brookings, United States

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.