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: Aphid Identification by Artificial Intelligence - subproject A (AI2)
Project
Project code: 28DK106A20
Contract period: 01.05.2021
- 31.08.2024
Budget: 364,036 Euro
Purpose of research: Applied research
Keywords: environment and nature protection, digital world, crop protection, plant health, precision farming, AI Artificial Intelligence, animal pathogens, monitoring
Aphids are one of the most important insect pests in arable crops in Germany. Their importance has even increased in recent years. For an optimal aphid pest control, it is important to know their temporal and spatial occurrence and to correctly identify individual species. This identification based on morphological features is extremely time-consuming hence costly and, due to the complexity, requires high expertise, which is constantly disappearing. In the practice of pest insect monitoring, shortages of personnel often arise at the crop protection services during the peak of the migration phases. The aim of this project is to develop tools based on deep learning and the use of artificial intelligence (AI) for an automated detection and classification of aphids from mass catches, such as suction traps or yellow pan traps. An AI offers extensive advantages for pest monitoring: 1) Significant reduction in processing time, largely independent of personnel, 2) Standardized results without individual personal errors, 3) Use of the AI at multiple locations, e.g. all crop protection services, 4) faster detection of invasive insect pests thanks to timely sample processing. All of these aspects will allow monitoring to be expanded in the future, including a further improvement of warnings.
Section overview
Subjects
- Crop Protection
Framework programme
Funding programme
Excutive institution
Federal Research Centre for Cultivated Plants – Julius Kühn-Institut (JKI)