More efficient fruit cultivation with data and precision technology
Labor availability in agriculture and horticulture is decreasing, while the demand for efficiency and sustainability is increasing. Aurea Imaging investigates how technologies such as robotics, image analysis, AI, and data platforms can contribute to labor efficiency and improved cultivation strategies. This project validates the use of sensors for precision thinning and its impact on yield and fruit quality.
Innovation package, use case, and type of trial
Open Teelten
Handsfree Orchards
Status: evaluation report
Technical functionality
Broad research question
How can technology support labor and craftsmanship in fruit cultivation?
Manual thinning and crop assessment require significant labor and expertise. This study focuses on whether sensor- and data-driven methods can provide a reliable alternative to apply fruit thinning more efficiently and with higher precision.
Approach
Sensors and precision thinning in four orchards
In four orchards, including Proeftuin Randwijk, observations and validations were carried out. Treescout cameras mounted on a tractor collected data on blossoms and growth vigor, which were compared with manual measurements. Based on this data, precision thinning treatments were applied and evaluated against conventional methods.
Goal
Validation of Treescout technology and its impact on yield
The project tests the accuracy of Treescout sensors and evaluates how precision thinning affects yield and fruit quality. Additionally, it examines how this data-driven approach compares to traditional thinning strategies and whether it can contribute to more efficient farm management.
Results and reflection
Reliable sensor data and improved fruit set
The results show that Treescout sensors provide a reliable indication of blossom and growth vigor, with some variation depending on timing and location.
Successes:
Precision thinning achieved a better balance in fruit set and positively influenced yield and fruit quality.
The sensor data proved useful in supporting and optimizing manual measurements.
Lessons learned:
The effectiveness of thinning agents partly depends on weather conditions and location-specific factors.
Further refinement of measurement methods can improve the accuracy of sensor-driven decisions.