Smart e-Nose development for grapevine Erysiphe necator detection
Bachelor, Master, Diplom
Cover

Grapevine powdery mildew (GPM) is one of the most destructive fungal diseases in viticulture and lead to severe yield losses and reduced grape quality. GPM is caused by Erysiphe necator fungi. Early and accurate detection of GPM is crucial for effective disease management to minimize fungicide use and ensure sustainable viticulture. However, traditional detection methods, such as visual inspection, molecular diagnostics, and spectral analysis, are often time-consuming, labor-intensive, or require expensive equipment. Electronic noses (e-Noses) offer a promising alternative by detecting volatile organic compounds (VOCs) emitted by infected plants. AI-powered e-Noses, integrating advanced machine learning algorithms with gas sensor arrays, can identify subtle VOC patterns associated with E. necator infection at an early stage. This approach enables real-time, non-invasive monitoring, improving disease prediction and management in vineyards.
Main task:
[1]. Sensor fabrication, including material selection and functionalization for enhanced sensitivity and selectivity.
[2]. Gas sensing measurement work towards various conditions of VOC biomarkers from Erysiphe necator fungi.
[3]. Develop machine learning models for VOC pattern recognition and disease classification.
Student background:
[1]. A good background in materials science, electrical engineering, chemistry, or artificial intelligence.
[2]. Experience with gas sensors, machine learning, and VOC-based disease diagnostics is desirable.
[3]. Experience with experimental design, data analysis, and sensor characterization techniques (e.g., GC-MS, SEM, EIS) would be a plus.
[4]. Programming skills (e.g., Python) for machine learning and data processing are beneficial.
Benefits to the student:
[1]. Gain hands-on experience in sensor development, AI-driven analysis, and agricultural disease diagnostics.
[2]. Develop practical skills in sensor fabrication, machine learning, and environmental monitoring.
[3]. Contribute to cutting-edge research in precision agriculture and smart viticulture.

Reference:
[1]. Kassemeyer, Hanns-Heinz. "Fungi of grapes." Biology of Microorganisms on Grapes, in Must and in Wine (2017): 103-132.
[2]. Romanazzi, Gianfranco, Valeria Mancini, Erica Feliziani, Andrea Servili, Solomon Endeshaw, and Davide Neri. "Impact of alternative fungicides on grape downy mildew control and vine growth and development." Plant disease 100, no. 4 (2016): 739-748.
[3]. Huang, Shirong, Alexander Croy, Antonie Louise Bierling, Vyacheslav Khavrus, Luis Antonio Panes-Ruiz, Arezoo Dianat, Bergoi Ibarlucea, and Gianaurelio Cuniberti. "Machine learning-enabled graphene-based electronic olfaction sensors and their olfactory performance assessment." Applied Physics Reviews 10, no. 2 (2023).



Group
Projects
Smart e-Nose development for grapevine Erysiphe necator detection
Bachelor, Master, Diplom
Cover

Grapevine powdery mildew (GPM) is one of the most destructive fungal diseases in viticulture and lead to severe yield losses and reduced grape quality. GPM is caused by Erysiphe necator fungi. Early and accurate detection of GPM is crucial for effective disease management to minimize fungicide use and ensure sustainable viticulture. However, traditional detection methods, such as visual inspection, molecular diagnostics, and spectral analysis, are often time-consuming, labor-intensive, or require expensive equipment. Electronic noses (e-Noses) offer a promising alternative by detecting volatile organic compounds (VOCs) emitted by infected plants. AI-powered e-Noses, integrating advanced machine learning algorithms with gas sensor arrays, can identify subtle VOC patterns associated with E. necator infection at an early stage. This approach enables real-time, non-invasive monitoring, improving disease prediction and management in vineyards.
Main task:
[1]. Sensor fabrication, including material selection and functionalization for enhanced sensitivity and selectivity.
[2]. Gas sensing measurement work towards various conditions of VOC biomarkers from Erysiphe necator fungi.
[3]. Develop machine learning models for VOC pattern recognition and disease classification.
Student background:
[1]. A good background in materials science, electrical engineering, chemistry, or artificial intelligence.
[2]. Experience with gas sensors, machine learning, and VOC-based disease diagnostics is desirable.
[3]. Experience with experimental design, data analysis, and sensor characterization techniques (e.g., GC-MS, SEM, EIS) would be a plus.
[4]. Programming skills (e.g., Python) for machine learning and data processing are beneficial.
Benefits to the student:
[1]. Gain hands-on experience in sensor development, AI-driven analysis, and agricultural disease diagnostics.
[2]. Develop practical skills in sensor fabrication, machine learning, and environmental monitoring.
[3]. Contribute to cutting-edge research in precision agriculture and smart viticulture.

Reference:
[1]. Kassemeyer, Hanns-Heinz. "Fungi of grapes." Biology of Microorganisms on Grapes, in Must and in Wine (2017): 103-132.
[2]. Romanazzi, Gianfranco, Valeria Mancini, Erica Feliziani, Andrea Servili, Solomon Endeshaw, and Davide Neri. "Impact of alternative fungicides on grape downy mildew control and vine growth and development." Plant disease 100, no. 4 (2016): 739-748.
[3]. Huang, Shirong, Alexander Croy, Antonie Louise Bierling, Vyacheslav Khavrus, Luis Antonio Panes-Ruiz, Arezoo Dianat, Bergoi Ibarlucea, and Gianaurelio Cuniberti. "Machine learning-enabled graphene-based electronic olfaction sensors and their olfactory performance assessment." Applied Physics Reviews 10, no. 2 (2023).



Group
Projects