Strawberry Breeding Assisted with Plant Phenome AI Model
Applied Research
Wael Elwakil
Extension Agent II, Fruit & Vegetable Production
UF/IFAS Extension, Hillsborough County
Seffner
Abstract
Introduction: Traditional strawberry breeding is tasking research that requires the evaluation of plant phenome of thousands of individual plants to be narrowed down to one or two commercially viable varieties. Evaluation of plant phenome characteristics such as morphology, physiology, and development is an intensive, time and resource-consuming process. The use of an AI model to assist in data collection and analysis can offer a huge advantage to plant breeders to increase is breeding lines’ evaluation capability with reduced time and invested resources. Hypothesis: An AI-based model can greatly assist strawberry breeders and speed up the release of new commercial varieties. Objectives: Use Plant Phenome AI model to accelerate the plant breeding process and reduce required intensive resources and time demands of traditional breeding. Methods: Aerial or ground-based images of strawberry plants are captured in the field. Images are uploaded to the cloud for raw processing and plant phenome characterization. Various data parameters such as biomass, and development rate are evaluated to advise the variety selection process. Results: Nondestructive imaging sampling over time of breeding lines provides the biomass and growth rates data. These plant phenome data parameters are plotted to differentiate among breeding lines being evaluated. Conclusion: Using this plant phenome AI model offers a nondestructive sampling method to measure strawberry plant growth and reproduction parameters. This is a great advantage in comparison to traditional destructive sampling methods which require more man hours, plants, field or greenhouse space, and associated higher costs. This AI model offers a big stepping stone for automating plant runner management, plant growth monitoring, and possibly yield estimations in commercial production.
Poster has NOT been presented at any previous NACAA AM/PIC
This poster is being submitted for judging. It will be displayed at the AM/PIC if not selected as a State winner. The abstract will be published in the proceedings.
Click to view Poster
Authors: Wael Elwakil, Xu Wang
-
Elwakil, W. Extension Agent II, Fruit & Vegetable Production, University of Florida, Florida, 33584
-
Wang, X. Assistant Professor of Plant Phenomics, University of Florida, Agricultural and Biological Engineering, Florida, 33598