Work Packages
Coordination and Management
Aim: To manage the project time & budget; Monitor all activities, implementation plan & data management.
Deliverables: D1.1-Project management Plan, D1.2-Quality Assurance Plan & D1.3-Data Management Plan
WP1
WP2
Data collection and Indicator Framework
Aim: To exploit existing databases, to define the indicators for agroecosystem resilience and management interventions, to perform data acquisition and curation and to develop a database/datacube
Deliverables: D2.1-Report for the exploitation of existing databases, D2.2-Indicator framework for agroecosystem resilience and management interventions & D2.3-Datacube with Analysis Ready Datasets
Climaca Deliverable 2.3 develops and deploys a scalable data processing pipeline for agricultural monitoring, built around the Open Data Cube (ODC) framework. The pipeline is centered around efficiently leveraging Sentinel-1 and Sentinel-2 imagery – however, it will be extended to other data sources (e.g., meteorological, crop type, soil organic carbon).
The key components include:
a harvester module for efficient data retrieval; preprocessing workflows for both Sentinel-1 and Sentinel-2 data management; and cloud masking using dual algorithms (Sen2Cor and Fmask). The processed data is converted to Cloud Optimized GeoTIFFs (COGs) and integrated into ODC for seamless storage and querying. The pipeline incorporates STAC and pgSTAC for metadata cataloging along with datacube-ows and TerriaJS for real-time data visualization, enabling rapid and scalable access to Big Earth Observation data.
By automating these processes, the pipeline significantly reduces manual intervention, ensures continuous data availability, and enhances decision-making capabilities for sustainable agricultural practices.
EO-based tools for monitoring agroecosystem practices and condition
Aim: Analyse past and future trends of agroecosystem quality; Define causal graphs depicting the complex relationships between agricultural systems, management interventions, and potential boundary conditions; Assess the impact of the possible drivers on agricultural resilience through causal ML; Evaluate recommendations for various management interventions via explainable AI.
Deliverables: D4.1 Report on the historical analysis of ES, D4.2 Causal graphs depicting the relationship among agroecosystems’ components, D4.3 Report on the effects of potential drivers on agricultural resilience & D4.4 Impact assessment of interventions for defining optimal management options
WP3
WP4
Artificial Intelligence for Agricultural Resilience
Aim: To exploit existing databases, to define the indicators for agroecosystem resilience and management interventions, to perform data acquisition and curation and to develop a database/datacube
Deliverables: D2.1-Report for the exploitation of existing databases, D2.2-Indicator framework for agroecosystem resilience and management interventions & D2.3-Datacube with Analysis Ready Datasets
Policy Recommendation System
Aim: To provide spatially personalized policy recommendations and actionable advice through a web application and policy briefs to CAP-related policymakers for the sustainable practices that can support resilient agricultural systems.
Deliverables: D5.1-Policy recommendation system modules, D5.2-A roadmap for spatially personalized policy making to support sustainable and resilient agricultural ecosystems