Jonathan Klein ^1* Rebekah Waller ¹ Sören Pirk ² Wojtek Pałubicki ³ Mark Tester ¹ Dominik L. Michels ¹

• ¹ King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
• ² Department of Computer Science, Faculty of Engineering, University of Kiel, Kiel, Schleswig-Holstein, Germany
• ³ Adam Mickiewicz University, Poznań, Greater Poland, Poland

The rise of artificial intelligence (AI) and in particular modern machine learning (ML) algorithms during the last decade has been met with great interest in the agricultural industry. While undisputedly powerful, their main drawback remains the need for sufficient and diverse training data. The collection of real datasets and their annotation are the main cost drivers of ML developments, and while promising results on synthetically generated training data have been shown, their generation is not without difficulties on their own. In this paper, we present a development model for the iterative, cost-efficient generation of synthetic training data. Its application is demonstrated by developing a low-cost early disease detector for tomato plants (Solanum lycopersicum) using synthetic training data. A neural classifier is trained by exclusively using synthetic images, whose generation process is iteratively refined to obtain optimal performance. In contrast to other approaches that rely on a human assessment of similarity between real and synthetic data, we instead introduce a structured, quantitative approach. Our evaluation shows superior generalization results when compared to using non-task-specific real training data and a higher cost efficiency of development compared to traditional synthetic training data.