Workplan

infography

WP1. Technical monitoring and coordination

T1.1 Technical monitoring and coordination

DELIVERABLES

D1.1 – Technical risk plan

D1.2 – Periodic report #1

D1.3 – Periodic report #2

D1.4 – Periodic report #3

D1.5 – Data Management Plan


WP2. Agronomic models and ontologies for crop characterization and fertigation optimization

T2.1 Regulatory and ethical framework for the application of fertilizers and phytosanitary products on crops

T2.2 Study of agronomic models for the prediction of evapotranspiration, abiotic stress, fungal disease, and pest in woody crops

T2.3 Research on geospatial information modelling techniques from agriculture data (e.g., GIS, IoT, Copernicus)

T2.4 Research and design of ontologies for the characterization of processes and AI models in the agri-food chain

DELIVERABLES

D2.1 – White paper on the regulatory framework for fertigation on woody crops

D2.2 – List of woody plants and datasets of plant tolerance to biotic and abiotic stresses in relation to specific climatic conditions

D2.3 – Ontologies for the characterization of agricultural processes


WP3. Big Data, Low-Power Internet of Things and Digital Twins for crop sensing, modelling and simulation

T3.1 Big Data and information fusion techniques from sensor data, multispectral imagery and weather forecasting

T3.2 Hybridisation of LP-WAN and WLAN technologies for connectivity in remote agricultural environments

T3.3 Cyber-Physical Systems for crop, water and nutrient monitoring and automated fertigation control

T3.4 Research of Digital Twins and Multi-Agent Systems for agri-food chain characterisation and simulation

DELIVERABLES

D3.1 – Edge Computing -based device for Machine Learning model execution and fertigation decision making

D3.2 – DTs and VAOs environment for the interaction between fertigation decision-making agents and real-world agricultural entities


WP4. eXplainable Artificial Intelligence and Cognitive Computing for crop fertigation optimisation

T4.1 Explainable recurrent neural networks for crop evapotranspiration prediction from IoT and satellite imaging

T4.2 Ensemble learning models for predicting crop phenotype and yield according to water and nutrient inputs

T4.3 Explainable recurrent convolutional networks for disease prediction from sensorics and multispectral imaging

T4.4 Cognitive systems and fuzzy logic for the optimisation of fertigation and crop protection application in crops

DELIVERABLES

D4.1 – Explainable neural and ensemble models for yield and disease prediction

D4.2 – Cognitive engine for fertigation and phytosanitary treatment recommendation


WP5. Experimentation and validation

T5.1 Definition of evaluation metrics and small-scale implementation

T5.2 Experimentation on a small scale

T5.3 Results analysis and reporting

T5.4 Refinement of algorithms and models

DELIVERABLES

D5.1 – Report on experimentation results in relevant environment