I develop data-driven decision systems for sustainable crop production, integrating field experiments, sensor data, and crop and weed modelling. My research focuses on translating complex agroecological interactions into actionable management strategies under real farming conditions.
By combining autonomous robotic and UAV-based phenotyping, machine learning, and process-based modelling, I develop robust and scalable decision-support approaches for crop management. My work aims to reduce nitrogen losses, improve resource-use efficiency, and support biodiversity in agricultural systems.
My research is structured around three main areas:
1. Data-driven agronomic decision-making
Development of decision frameworks that integrate sensor data, modelling, and field observations to support practical crop management under uncertainty.
2. Crop–weed–environment interactions
Quantification and modelling of interactions in diversified systems, including intercropping and weed dynamics, to improve yield stability and ecological performance.
3. Field validation and implementation
Design and execution of field experiments and on-farm trials to validate digital tools and ensure applicability under real farming conditions.
I actively contribute to interdisciplinary research projects, such as Horizon Europe, by linking phenotyping, modelling, and agronomy.
I am interested in collaboration on:
