We use cookies to enable you to make the best possible use of our website. Only cookies that are necessary for the operation of the site are set. Details in our privacy policy.
Data Protection Declaration
Imprint
Development of a Digital Phenotyping Method for Assessing Fruit Load in Apple Genetic Resources
Project
Project code: JKI-ZO-23-4266
Contract period: 01.08.2023
- 31.12.2026
Purpose of research: Experimental development
Keywords: phenotyping, digital innovation, machine learning, alternance, genetic resources, fruit, apple
This project aims to develop a digital method for automatically assessing the fruit load in apple trees. This technology is intended to help predict apple tree yields more accurately and detect fluctuations in biennial bearing, to breed more yield-stable apple varieties. In apple cultivation, it is important to accurately measure the fruit load of a tree to estimate yield and evaluate fruit quality. However, fruit set fluctuates significantly from year to year, negatively impacting both harvest stability and fruit quality. These fluctuations are known as biennial bearing. Until now, the assessment of fruit load has been carried out manually, which is time-consuming and prone to errors. As part of the project, drone flights will be conducted over an apple collection at the Julius Kühn Institute (JKI) over two years. High-resolution images of the apple trees will be captured during these flights. These images will then be used to label the fruits using software and to create a database. The data will be used to develop a machine learning model that can automatically detect and count the fruits. Once the model is sufficiently accurate, it will be tested with new images to confirm its reliability. The new digital method is expected to significantly improve the efficiency and accuracy of fruit load assessment. This will enhance research in apple breeding by enabling larger datasets to be analyzed more quickly. In the long term, the project aims to contribute to the breeding of more yield-stable apple varieties that produce high-quality fruits. With this technology, apple cultivation could become more stable and sustainable by breeding apple trees that consistently produce high yields and are less prone to harvest fluctuations
Section overview
Subjects
- Plant Breeding
- Arboriculture
- Genetic Resources
- Computer science
