We use cookies on our website. Some are necessary for the operation of the website. You can also allow cookies for statistical purposes. You can adjust the data protection settings or agree to all cookies directly.
Collaborative project: 'Deep Phenotyping' of disease resistance based on hyperspectral imaging and data mining methods in high troughput. Subproject 1 (DePhenSe)
Project
Project code: 2818204615
Contract period: 01.02.2017
- 31.03.2020
Budget: 193,892 Euro
Purpose of research: Applied research
Within the project DePhenSe the implementation of hyperspectral measurements in automated processes as well as an extension to the UV range for plant phenotyping of relevant crops was achieved by the partners Uni Bonn, IfZ, Uni Darmstadt and LemnaTec GmbH. Based on these results, hyperspectral measurements in the UV range can be performed for plant phenotyping. The establishment of new deep learning methods could also define relevant spectral regions, which can lead to a specification of sensor technologies. High-dimensional data sets can thus be interpreted more easily and the extension of hyperspectral measurements to the UV range showed that hyperspectral measurements in the UV range allow differentiation of various host-pathogen interactions as well as resistance responses, and spectral changes can be linked to changes in plant compounds. The developed methods are the basis for high throughput methods and for the establishment of software routines.
Section overview
Subjects
- Plant Breeding
- Crop Protection
- Computer science