PI: S. Fountas and I. Athanasiadis.
Spray your way to systainability in agriculture
Due to a lack of a holistic approach combining physical and digital assets for optimal field performance and minimum environmental impact, AI models, data and autonomous robotic systems in crop care tasks have not reached a mature technological level. The conventional spraying methods result in excessive pesticide and fertilizer use, posing severe environmental impact - being responsible for soil, water and air pollution, and harming non-target plants, insects, animals and humans. Smart Droplets’ main objective is to advance both hardware and software capabilities to deliver a holistic system capable of translating large amounts of data into meaningful information and impactful spraying commands on the field. To demonstrate substantial impact on the Green Deal, Smart Droplets will implement Autonomous retrofit tractors with Direct Injection System (DIS) for intelligent spraying - avoiding exposure of farmers to hazardous chemicals. Through the combination of high-level technologies (>TRL 7), Smart Droplets adopts a hybrid approach for spraying operations, combining Data/AI/Digital Farm Twin technologies designed to translate data into actionable information, and real-time data collected from Field demonstrators evaluating and demonstrating optimised technologies in the real environments. Smart Droplets will exploit synergies with relevant stakeholders, and intensify Community & Capacity building through dedicated training programs designed for non-expert users of AI, data and robotics systems. The Smart Droplets Consortium consists of all agricultural AI, data and robotics value chain actors, and is well balanced in terms of expertise, entity type, and geographical distribution necessary to meet its objectives. Smart Droplets will demonstrate how autonomous robotic platforms, innovative spraying, digital twin and AI models, can deliver environmental, economic, regulatory, business, scientific, and societal benefits, assisting in the achievement of Green Deal goals.
- M.G.J. Kallenberg, B. Maestrini, R. van Bree, P. Ravensbergen, C. Pylianidis, F. van Evert, I.N. Athanasiadis, Integrating processed-based models and machine learning for crop yield prediction, ICML Workshop on the Synergy of Scientific and Machine Learning Modelling, 2023, doi:10.48550/arXiv.2307.13466.
- M.G. Kallenberg, H. Overweg, R. van Bree, I.N. Athanasiadis, Nitrogen management with reinforcement learning and crop growth models, Environmental Data Science, 2:e34, 2023, Cambridge University Press, doi:10.1017/eds.2023.28.
- M. Turchetta, L. Corinzia, S. Sussex, A. Burton, J. Herrera, I. N. Athanasiadis, J. M. Buhmann, A. Krause, Learning long-term crop management strategies with CyclesGym, Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2022.