The project aims to develop predictive solutions to detect the onset of potato sprouting at an early stage. An accurate prediction allows for optimized use of anti-sprouting agents such as Orange Oil—a natural but expensive solution whose effectiveness depends on being applied at least two weeks before visible root emergence.
The award-winning paper, titled Machine Learning-based Early Detection of Potato Sprouting Using Electrophysiological Signals, proposes an innovative approach based on Machine Learning techniques. The method leverages electrophysiological signals recorded from tubers via sensors to forecast sprouting.
The goal is to provide a reliable and timely prediction of the exact day sprouting begins, thereby improving post-harvest management and the sustainability of storage practices.
PRONTO is funded by Innosuisse and carried out in collaboration with several agricultural and food industry partners, including Vivent Biosignals, UPL, Fenaco, and Zweifel. The project also involves the Federal Competence Center Agroscope and the Fernfachhochschule Schweiz, through its Web Science Lab.