Periodic Reporting for period 1 - OB-VISLY (An Ontology-based Visual Analytics Approach to Big Data from Agricultural Monitoring Infrastructure)
Periodo di rendicontazione: 2020-10-05 al 2022-10-04
Demand for specific agricultural product quality characteristics and changing climate are significant forces behind innovation in the farming sector. To remain profitable, agricultural practices must continue to innovate and discover new crops and varieties to adapt to the changing environment. Increasing agricultural production challenges, such as climate change, environmental concerns, energy demands, and growing consumer expectations, have necessitated innovation through data-driven approaches like visual analytics.
OB-VISLY had focused on developing a prototype visual analytics system for an apple variety testing program in South Tyrol, Italy. The objectives are to establish an interface that integrates and harmonizes information about apple variety testing and climate interactions via a semantic model and to create a single user interface that turns data into actionable knowledge for domain experts.
OB-VISLY had focused on developing a prototype visual analytics system for an apple variety testing program in South Tyrol, Italy. The objectives are to establish an interface that integrates and harmonizes information about apple variety testing and climate interactions via a semantic model and to create a single user interface that turns data into actionable knowledge for domain experts.
The main scientific and technological achievements include the development of a novel ontology-based visual analytics framework for agricultural big data. The multi-source and multi-scale data have been integrated within a visual analytics framework, which enabled efficient knowledge extraction. This framework helps extract information about the interaction of an apple variety testing program with the climate data. The main innovation outcomes of the project include the publication of a comprehensive ontology for apple traits, which standardizes and facilitates the understanding and analysis of apple-related data. Additionally, the project developed an advanced visual analytics interface that significantly enhances the interaction between the apple variety testing program and climate. This interface allows for more intuitive and efficient exploration and interpretation of agricultural data, leading to better-informed decision-making and optimization of agricultural practices. These innovations collectively contribute to advancing precision agriculture and integrating diverse data sources within the agricultural sector.
The OB-VISLY project achieved several key milestones across its work packages.
In WP1 Data Ecosystem, I collected data on fruit-growing activities and environmental parameters, created and enhanced ontologies for selected case studies, and harmonized data to establish FAIR ontologies.
In WP2 Data Analytics, I conducted a stakeholder workshop to define analytical requirements, linked structured data from various sources, and integrated data mining algorithms and predictive data analytics.
For WP3 Visual Analytics, I developed a visual analytics interface, realized data visualization, and established an iterative development workflow to ensure stakeholder satisfaction.
Finally, in WP4: Evaluation, I conducted a usability test to improve the developed tools and pave the path for future work.
The OB-VISLY project achieved several key milestones across its work packages.
In WP1 Data Ecosystem, I collected data on fruit-growing activities and environmental parameters, created and enhanced ontologies for selected case studies, and harmonized data to establish FAIR ontologies.
In WP2 Data Analytics, I conducted a stakeholder workshop to define analytical requirements, linked structured data from various sources, and integrated data mining algorithms and predictive data analytics.
For WP3 Visual Analytics, I developed a visual analytics interface, realized data visualization, and established an iterative development workflow to ensure stakeholder satisfaction.
Finally, in WP4: Evaluation, I conducted a usability test to improve the developed tools and pave the path for future work.
The main research and innovation of the OB-VISLY project focus on developing a cutting-edge visual analytics framework tailored for the agricultural domain applied to apple variety testing data. This framework integrates multi-source and multi-scale data, enabling efficient knowledge extraction and providing a comprehensive strategy for exploring heterogeneous data within a unique interface. Stakeholder engagement has been a crucial component of the project, ensuring that the insights generated are practical and beneficial for real-world applications. By involving stakeholders throughout the process, the project has ensured that the solutions developed are aligned with their needs and challenges, ultimately driving advancements in precision agriculture and improving decision-making processes within the apple production sector.
The project's contribution to the state of the art lies in its unconventional use of visual analytics methods and innovative approaches to knowledge structuring. By integrating visual analytics with ontology-based data integration, the project has advanced the application of these techniques in agriculture. This has led to enhanced precision agriculture practices through innovative data visualization methods, which allow for the more effective exploration and understanding of complex agricultural data.
The scientific and technological quality of the results is reflected in my advanced training and the establishment of a strong scientific network. Through this project, I have gained extensive expertise in cutting-edge techniques such as ontology-based data integration and visual analytics, significantly enhancing my capabilities in agricultural data analytics. Additionally, I have built a robust scientific network, enabling collaboration and knowledge exchange with leading experts and institutions in the field. This network has not only enriched the quality and impact of my research but has made another step towards the uptake of a data-driven approach in the field of agriculture.
The project's contribution to the state of the art lies in its unconventional use of visual analytics methods and innovative approaches to knowledge structuring. By integrating visual analytics with ontology-based data integration, the project has advanced the application of these techniques in agriculture. This has led to enhanced precision agriculture practices through innovative data visualization methods, which allow for the more effective exploration and understanding of complex agricultural data.
The scientific and technological quality of the results is reflected in my advanced training and the establishment of a strong scientific network. Through this project, I have gained extensive expertise in cutting-edge techniques such as ontology-based data integration and visual analytics, significantly enhancing my capabilities in agricultural data analytics. Additionally, I have built a robust scientific network, enabling collaboration and knowledge exchange with leading experts and institutions in the field. This network has not only enriched the quality and impact of my research but has made another step towards the uptake of a data-driven approach in the field of agriculture.