Combining mechanistic plant modeling with AI to improve phenology prediction

In agriculture, the phenological development of a crop serves as the main indicator for determining the optimal timing of management practices. For farmers, agricultural advisors and scientists, knowledge of plant phenology is crucial as it helps to determine the best time for crop protection measures, irrigation, fertilisation and harvesting. When crops are planted and harvested at the right time, crop yield can be increased and the highest quality of produce can be guaranteed, while minimising the use of resources. The ‘PhenAI’ project will develop a hybrid model that combines the advantages of a solid mechanistic crop growth model with AI to significantly improve our ability to predict phenological stages for different crops. Only the combination of these approaches makes it possible to contribute to the development of an approach that surpasses the state of the art. While many research results from digitalisation only reach a small percentage of farmers in developed countries, this project is aimed at all farmers and private gardeners as it provides an easy-to-use prediction of crop phenology for a better understanding and management of a plant's needs.