Fecha de publicación: -- Fuente: Wipo "precision agriculture" The present disclosure provides an intelligent real-time variable rate nutrient application system, as well as a system and process for creating a digitally characterized physical synthetic soil state library. In aspects, the disclosure provides systems and methods for real-time soil sensing and nutrient application. A machine-mounted sensor device generates soil state data as a machine moves through a field. The soil state data is processed using a trained machine learning model to generate a real-time nutrient amendment instruction, and an on-machine nutrient application device is actuated based on the instruction to deliver a nutrient amendment to the soil. In certain embodiments, the machine learning model is trained using a synthetic soil state library.