Improving Global Agricultural Data (IGAD) Community of Practice - Third IGAD Annual Virtual Meeting 2023

You are here

21 Jun 2023 UTC

Improving Global Agricultural Data (IGAD) Community of Practice - Third IGAD Annual Virtual Meeting 2023

21 Jun 2023 to 30 Jun 2023

The co-chairs of the Research Data Alliance (RDA) Improving Global Agricultural Data (IGAD) Community of Practice are thrilled to host our third annual meeting between June 21 and June 30, 2023.  The meeting will consist of six sessions held virtually to allow members and interested attendees from all over the world to participate.  


There are individual registration links for each virtual session: check the individual sessions in the program below. Interested participants are encouraged to register for multiple sessions based on interests and needs. The full schedule of presentations and registration links for the virtual meeting are available in this document. If you have any comments or suggestions please contact us at

Participants in the 2023 RDA/IGAD annual meeting are encouraged to follow along and contribute to the conversation on social media using #RDA_IGAD2023. Follow @FAOAIMS, @resdatall, @RDA_Europe, and @RDA_us to stay informed throughout the annual meeting. 

The co-chairs of the Improving Global Agricultural Data (IGAD) Community of Practice: 
Debora Ducker (EMBRAPA), Cynthia Parr (USDA Agricultural Research Service), Valeria Pesce (Global Forum on Agricultural Research and Innovation,  GFAR), Marina Razmazde (Institute for Scientific and Technical Information - TECHINFORMI), Piotr Zaborowski (Open Geospatial Consortium)



Wednesday, 21 June, 12:00 to 14:00 UTC: Data and Agrisemantics Crosswalks and Ontologies
     recording available: 

Monday. 26 June, 07:00 to 08:30 AM UTC: Ethical and legal issues around agricultural data - part 1
     recording available:

Monday, 22 August, 10:00 to 11:00 AM UTC: WorldFAIR Case Study on Plant-pollinator Interactions Data

     recording available:

Monday, 26 June, 15:00 to 16:30 UTC: Ethical and legal issues around agricultural data - part 2
     recording available:

Tuesday, 27 June, 10:00am to 12:00 AM UTC: IGAD/RDA: Sharing Experiences and Creating Digital Dialogues in Eastern Europe
     recording available:

Friday, 30 June, 14:00 to 16:00 UTC: Farm data for Advanced Analytics
     recording available:

Details about the sessions

Data and Agrisemantics Crosswalks and Ontologies

Wednesday, June 21. 12:00 to 14:00 UTC

Organizer: Piotr Zaborowski (Open Geospatial Consortium)

Recording available:

Registration Link:  

Speakers and Information about the presentations

The heterogeneity of the agriculture data ecosystem has already been a driver of the IGAD working groups' work on the semantics, vocabularies and ontologies that would help unambiguously understand data. Best practices and guidance enabled some harmonization of efforts and directions. Now with some ontologies defined, both domain overlaps in definitions and gaps are observed. High-performance computing and AI promise new benefits of semantically enabled data, but also new requirements are identified that require both traversals and cross-domain representations. The session encourages ideas and lessons learned exchange on topics like data and metadata crosswalks, ontologies for general agriculture, ontologies and vocabularies of subdomains (soils, EV, etc.), generic data description (lineage, training ML, etc.), semantically enabled data processing.

Dr. Sagi Katz, Agmatix
Dr. Sagi Katz,  VP of agronomy at Agmatix, has practiced agriculture since childhood. His Ph.D. in Soil and Water Science specialized in the ecosystem of biofilms in treated wastewater usage for agriculture practices. After the academy, he worked in the Israeli ag-tech environment including a plant sensors company with a strong data platform. 
As the VP of the agronomy team at Agmatix, he is responsible for the company's Ontology engine, making sure digital agronomic data can be analyzed smartly, and leading the professional aspect of the company’s product.

Title: Successful modeling relies on better data - the potential of data sharing and standardization to boost decision support systems Case study: crop disease modeling, with an application to Soybean SDS in the US
Abstract: Onset of diseases is affected by several factors, including (among others) weather, soil pathogens, crop genetics, and different management decisions. These factors impose an immense parameter space that needs to be explored and understood to allow mitigation efforts. Addressing this task necessitates a collaborative approach between researchers and other stakeholders, which can be hampered by a myriad of data sources, formats and notations used by the participating groups. Data standardization platforms streamline collaborations, enable more efficient research progress, and help capitalize on a big-data approach. This presentation will present the role of data standardization in creating high quality data for modeling, coming from several research contributors. Using the Axiom platform (by Agmatix) as an example, observational data of sudden death syndrome (SDS) in soybean crops from 7 states in the US and Canada (2472 observations), collected between 2012-2016, was used to develop a machine learning prediction model. The data was collected by more than 16 different people that preserved it differently. The ability to improve the data quality post collection by unique standardization and harmonization processes enabled the ability to train predictive models on the data.  Agmatix ontology and taxonomy engine is a unique property that contains 9 domains covering the ability to capture inputs from irrigation, chemicals, genetics and plant nutrition data in addition to the wide variety of agronomical practices. All the above is connected to an automated process allowing us to rapidly convert fragmented data to structured one. The model, built as an ensemble of decision trees, was able to predict SDS occurrence with an accuracy of 80% across the different production environments. Sensitivity analysis found the key factors affecting SDS in our data: i) crop genetics, ii) precipitation during specific growth periods, and iii) seed treatments. This analysis demonstrates the usefulness of standardization to foster collaborative efforts, and to leverage the collective power to cover critical research gaps.

Ben Craker, AgGateway
Ben Craker is the Portfolio Manager at AgGateway, a global nonprofit organization whose members develop standards and other resources across agricultural industry sectors by providing a unique forum where companies can meet to solve digital challenges. In this role Ben helps facilitate the efforts of working groups as they meet to develop digital resources solving pain points identified by member organizations. He has also served as the president of the Ag Data Coalition since it was founded in 2016. The ADC has been working to establishing an independent data repository farmers, researchers, and industry can use to store and share data. The ultimate ADC goal is to make data storage a pre-competitive space in the agricultural industry.

Title: Modus 2.0 Ag Lab Data Standard

Abstract: Exchanging agricultural lab test data is fundamental, but currently difficult. Current trends in sustainability, traceability, and compliance reporting demand that growers gather and report ever-increasing amounts of data to justify their operations. To meet these needs AgGateway established two working groups that are coordinating efforts between North and South America to formalize and build on the existing Modus standard. Modus emerged from a collaboration among a group of companies, academics, and soil test laboratories. It’s currently a set of XML schema files and code lists of laboratory test methods. It is the most widely adopted format among North American soil labs. However, the licensing and governance were somewhat ambiguous limiting adoption by some organizations. AgGateway worked with the founders to transition Modus to be managed under AgGateway’s antitrust and intellectual property framework.  Transitioning support to AgGateway also provides a clear mechanism for ongoing updates, improvements, and support for Modus.
The initial focus has been to enhance the controlled vocabulary of soil laboratory test methods and the accompanying schema. Since soil test data is a cornerstone in digital agriculture that drives agronomic decisions, the ability to record and report it seamlessly and accurately is essential. A common soil test data format across regions and platforms that removes uncertainty about units of measure and methods used is critical to meet the evolving needs of the industry. The team has completed updating the original Modus soils list with more precise method descriptions by applying ISO1956 principles to unambiguously reporting results from observations and measurements. This increased precision as well as incorporating some newer soil health methods grew the code list by approximately 200 codes from v1 to v2. To help wit the transition from v1 to v2, the team also mapped v1 codes to v2 so there is backward compatibility with the codes already being used in the industry. 
The second working group operates under AgGateway Latin America, focusing on gap checking the methods to ensure the needs for more tropical soil types in countries like Brazil were included in the method lists. Both groups are also contributing to updating the schema. Currently Modus is only available in XML and there is a strong desire within the industry to also be able to exchange data utilizing JSON. 
While Modus is best known for its soil method list, it also supports other lab test matrix. The team is currently working through updating these other lists to the new ISO19156 structure. As work is completed v2 Modus code lists will be available for botanical, water, manure/amendment, nematode, and feed test methods. The group is working with experts in each area of lab testing to ensure the methods are properly documented complete with citations in addition to the method descriptions and units of measure. 
AgGateway’s Laboratory Data Standardization Working Groups were created not just to update Modus code lists and schemas. The team also implemented a more transparent system for requesting changes and additions to the code lists. The process is clearly documented on the Modus web page using a form that drives consistent terminology and helps ensure methods being added are not already in the list, reducing the likelihood of duplicate entries. 

Chai Miaoling, Chinese Academy of Sciences
Chai Miaoling, library Science Master, the associate research librarian/associate professor at the Chengdu Documentation and Information Center/Chengdu Library and Information Center, Chinese Academy of Sciences, China, library and information science Master instructor of the Sichuan University. From Sep. 2015 to Feb. 2016, work in Food and Agriculture Organization of the United Nations as Consultant. Her research interests are Multi source heterogeneous data fusion, Knowledge Organization around Agriculture and Food. Published 30 papers in Chinese or English as first author, and host more than 20 research projects as the leader. 

Title: Research on the Method and Example of Using Ontology to Construct Multi source Heterogeneous Data Fusion——from the Perspective of Agricultural Science and Technology Management in China

Abstract: This paper funded by 2017 Sichuan Province International Cooperation Project, No.2017HH0094
The study proposes a metadata-ontology fusion method from the perspective of agricultural science and technology management in China, which aims to provide a method and case for cross-departmental and cross-domain scientific data sharing and fusion in China's agricultural science and technology management. 
Firstly, the study presents the connotation and methods of the correlation between scientific data and S&T literature, and analyzes unstructured data. Secondly, the data characteristics of agricultural science and technology management are explored. Thirdly, the ontology of agricultural science and technology management is constructed to support the integration of multi-source heterogeneous data. 
In the empirical part, the data requirements of agricultural science and technology management in Sichuan are targeted, and the industrial chain and data chain are integrated to propose 20 data requirements. Finally, the ontology is established and revised, and the linkage between scientific data and S&T literature is realized on a demonstration platform. There are three issues that need to be addressed in ontology research. They are semantic granularity, concept supplementation, and different classification perspectives.
The study builds two demonstration platforms, integrates 24,200 data, realizes the correlation of 16 types of agricultural science data and 4 types of S&T literature, and the correlation and fusion of multi-language (Chinese/English) data. The ontology of agricultural industry management is realized.

R. Andres Ferreyra, Syngenta Digital
As Data Asset Mgr., Andres leads Syngenta Digital’s Observations & Measurements platform. He has also led, as Product Mgr., Syngenta’s machinery Integration, Cropwise Analytics and Corn Tools products.  Andres is active in the ag data standards space, having held several leadership positions in AgGateway, and contributed to ASABE, AEF and ISO projects. He served as co-convener of ISO’s Strategic Advisory Group for Smart Farming, diagnosing the gaps in ISO’s agrifood systems standards and delivering a prioritized strategic roadmap for future development. Andres has a PhD in Agricultural & Biological Engineering, an MS in Agrometeorology and an Electrical & Electronic Engineer degree.

Title: Data Standards as tools for Enabling Data-Driven Agrifood Systems and Progress on the SDGs: The ISO Strategic Advisory Group on Smart Farming
Abstract: Agriculture is an increasingly complex, data-driven activity. Climate and supply chain disruptions challenge traditional farm decision-making, yet human-capital-intensive advisory services are unavailable in many parts of the world, especially to smallholders. Digital tools (e.g., mobile apps) have shown promise as vehicles for automated decision support, but their adoption is limited by a lack of FAIR data and the infrastructure, standards and support for such data at scale.
The International Organization for Standardization, ISO, chartered a Strategic Advisory Group for Smart Farming (SAG-SF) to create a strategic roadmap for advancing smart farming in support of the UN Sustainable Development Goals (SDGs) focusing on standardization of data interoperability needs. 
The scope of the SAG-SF was very broad (whole agrifood-system scale) and available time was very limited (16 months), but the SAG-SF’s 175+ experts explored a wide range of topics, including implications for smallholders. 
The SAG-SF’s final report provided ISO with a capability model and 49 recommendations:
•        10 general recommendations pertaining to internal and external coordination, communications, and outreach to communities of standards users, including the urgent need to coordinate landscaping and standardization efforts with other standards organizations.
•        5 recommendations proposing new ISO technical committees (to focus on specific aspects of agrifood systems data not covered elsewhere) including a Technical Committee on Data-Driven Agrifood Systems and an Agrisemantics Working Group within it. 
•        5 recommendations proposing specific inter-ISO-committee coordination activities; and
•        32 agrifood-data-domain-specific recommendations, several of which emphasize the need for standards for data type registries, FAIR data, and several forms of much-needed agricultural reference data.
A selection of these recommendations is discussed in detail, including potential synergies with IGAD / RDA outputs.

Ethical and legal issues around agricultural data - part 1

Monday. June 26 - 07:00 to 08:30 AM UTC

Organizers & moderators: Marcus Schmidt (Leibniz Center for Agricultural Landscape Research, ZALF, & Federal Research Centre for Cultivated Plants, JKI) and Valeria Pesce (Global Forum on Agricultural Research and Innovation, GFAR) 

Recording available:

Registration link: 

Speakers and Information about the presentations

Legal and ethical issues are an integral part of data management in agricultural research. Political agendas demand FAIR (findable, accessible, interoperable and re-usable) data management now and in the future, which implies data availability over long periods of time. To achieve this, legal issues must be clarified, and awareness of the problem must be raised at an early stage in the data life cycle. Which licenses can we offer and how do they affect data use in the future? It is also our moral obligation to make sure that agricultural data can be used by everyone and will not be exploited by large companies at the cost of other farmers (who may have helped to collect them in the first place). How might anonymizing data impact scientific integrity while allowing access to data that would otherwise have remained inaccessible? These and more questions, we would like to share in an interactive session with participants experienced or interested in this complex area of research data management. 
This session will feature short presentations and a panel discussion involving the following speakers & talks:

Talk 1
Gabi Ceregra

Data Policy Manager, Federation University Australia
Gabi is a data governance specialist, experienced in data management across health, financial services, government, and agriculture. Gabi has managed small and large scale data projects and operational data governance teams, and developed policies and standards on how data is created, managed, and used across global organisations.

Industry adoption of the Australian Farm Data Code and Data Sharing Agreement
A presentation on the work being done to develop and gain industry adoption of the Australian Farm Data Code and Data Sharing Agreement. The presentation will examine the required conditions for trust, specifically applied to the context of farmers and parties wanting to use farmers' data. It will demonstrate how the Australian Farm Data Code and Data Sharing Agreement can aid in addressing some of the power imbalances that exist between farmers and receiving parties.  

Talk 2
Marcus Schmidt, Florian Beyer, Carsten Hoffmann & Nikolai Svoboda

Project members of the Consortium FAIRagro within the German National Research Data Infrastructure (NFDI), from Leibniz Center for Agricultural Landscape Research (ZALF) & Federal Research Centre for Cultivated Plants (JKI)
Marcus coordinates the Data Steward Service Center (DSSC) within FAIRagro. Florian is one of the data stewards within the center, specialized on large geodata. Carsten acts as FAIRagro project manager and Nikolai is leader of the DSSC and the RDM working group at ZALF.

Legal and ethical concerns during the data life cycle from the perspective of the FAIRagro Data Steward Service Center (DSSC)
The FAIRagro consortium is part of the German National Research Data Infrastructure (NFDI). We focus on agricultural landscape data and aim to support related research in all steps of the data life cycle from setting up a research management plan all the way to data reuse. To address specific questions in agricultural data management as well as the challenges in the processing of big data ranging from geodata, standardized soil and plant data, we are building the FAIRargo Data Steward Service Center (DSSC) with a threefold support system available through a Help Desk infrastructure and trainings: online material, personal support and expert knowledge. One DSSC topic will be the handling of requests that contain legal and ethical issues concerning agricultural landscape data. We aim to (a) shortly present the structure of our DSSC, (b) highlight the role of the data stewards, especially the one concerned with legal and ethical issues. We want to finish with a short discussion with you on how to best address these issues in structured and transparent ways which are replicable and scalable to larger data sets and a larger number of service requests. 
After these two talks, we aim to engage further in a group discussion on the topics given by the speakers and elaborate together which challenges may be on the horizon for the agricultural data community.
We see this workshop as an opportunity to expand the network of (agricultural) data stewards with knowledge in these areas. It is a great opportunity to network and meet scientists who may consider becoming associated with our infrastructure and foster expertise in legal and ethical issues in agricultural data management and service.

WorldFAIR Case Study on Plant-pollinator Interactions Data

Tuesday, August 22, 10:00 to 11:00 UTC

Organizer: Debora Drucker (Brazilian Agricultural Research Corporation, Embrapa)

Recording available:

About the Webinar

A webinar providing an overview of what WorldFAIR WP10 (Agricultural Biodiversity) have produced at the discovery phase: FAIR assessments, good practices, tools and examples to create, manage and share data related to plant-pollinator interactions. 
About the WorldFAIR Project: In the WorldFAIR project, CODATA ( the Committee on Data of the International Science Council) and RDA (the Research Data Alliance), work with a set of 11 disciplinary and cross-disciplinary case studies to advance the implementation of the FAIR principles and, in particular, to improve interoperability and reusability of digital research objects, including data. Particular attention is paid to the articulation of an interoperability framework for each case study and research domain.  The core of the WorldFAIR project is the 11 case studies, which represent a wide range of sciences, communities and challenges, with global geographical coverage. 

Ethical and legal issues around agricultural data - part 2

Monday, June 26. 15:00 to 16:30 UTC

Organizers & moderators: Valeria Pesce (Global Forum on Agricultural Research and Innovation, GFAR) and Marcus Schmidt (Leibniz Center for Agricultural Landscape Research, ZALF, & Federal Research Centre for Cultivated Plants, JKI) 

Recording available:

Registration Link: 

Speakers and Information about the presentations

This session will feature three presentations and a discussion on ethical and legal issues around agricultural data, more specifically on creating an enabling ethical/legal environment for a fair data ecosystem for agriculture, considering power imbalances in the use of agri-food data, how data rights can counterbalance them, and examples of instruments.
There will be a summary from the session on the same theme held in the morning, a final discussion among the presenters and a Q&A session.

Jane Ezirigwe
Dr. Jane Ezirigwe is an Open AIR Postdoctoral Fellow on Global Data Governance for Food and Agriculture at the University of Ottawa.  She is also a Senior Research Fellow at the Nigerian Institute of Advanced Legal Studies. Jane holds a PhD in law from the University of Cape Town and has over 18 years of experience in legal research,  legal advocacy, legal education, as well as in mobilizing and translating knowledge for wider usage. Her research interests are in the areas of food & agricultural law, international trade, and natural resource development.  She is also committed to mainstreaming gender in her research and is focused on using socio-legal methods to produce evidence-based research

Presentation: Power Contestations in the Use of Agri-Food Data: Towards a Sustainability Governance Approach 
Law is intrinsically embedded in politics. Background forces, norms, and rules can significantly impact whatever new rules we come up with. Therefore, we need to interrogate the spectrum of engagements of any given subject or phenomenon with the law. In the context of global governance of food and agricultural data, this presentation will examine how power manifests in the generation and use of agri-food data, how power could construct global rules on the use of agri-food data, and how the global community should respond to this realization. It will highlight the politics of technology and data, the increasing influence of private corporate power on global public rules, and how these drive inequalities and inequities among certain actors and groups, with intersectionality affecting some groups more than others. These insights make important contributions to the debate on the global governance of food and agricultural data, by contributing broadly to the academic discourse on the use of technology for development, and more narrowly, to the analytical frameworks on power and technology in the agri-food industry. It invites policymakers to recognize the unequal political economy within which the global governance of agri-food data is negotiated and offers some justifications on why, and how such an opportunity should be used to correct these imbalances and redistribute the benefits of agri-food data to all stakeholders. It further proffered a lens to the public to see trans-corporations as both economic and political actors that wield tremendous power and how they use this power to make private and public rules that impact development, food security, equality, and sustainability.

Gerard Sylvester
Gerard Sylvester is investment officer for digital agriculture at the Food and Agriculture Organization of the United Nations (FAO). He is an expert in Digital for development, with a multidisciplinary skill set and over 15 years of experience in developing, implementing and evaluating development projects, for international organizations, focusing on the use of emerging technologies to address developmental challenges in agriculture. 

Presentation: Importance of data governance for smallholder farmers 
In order to increase smallholder farmers' productivity, profitability, and resilience in the face of global issues including climate change, population expansion, and food insecurity, data governance is crucial. If the challenges are addressed, huge potential and value could be built for agricultural stakeholders, including farmers, extension workers, researchers, policymakers, and commercial sector actors through building a data ecosystem. Public and commercial sector players must work together to utilize their individual capabilities and resources in order to form partnerships that can develop a sustainable and inclusive data ecosystem for smallholder farmers. Additionally, there is a need to increase capacities at many levels, from individual farmers to institutional actors, in order to improve their data and digital skills and competencies. Furthermore, there is a need for frameworks that can guide the design, implementation, and evaluation of data governance policies and practices that are context-specific and adaptive.

Dominik Bednarczyk
Dominik Bednarczyk is a Co-op student at McMaster University majoring in Biotechnology. He is building the framework for the World Data System – International Technology Office’s (WDS-ITO) Biodiversity Project. He researches and discusses the current climate of Biodiversity research and data collection. He is working with Maui Hudson and Local Contexts on the Traditional Knowledge (TK) Labels. Before WDS-ITO he worked at Canadian Nuclear Laboratories (CNL) studying chimney swifts, and Blanding’s turtles, performing biodiversity fieldwork, and community outreach.

Presentation: Biodiversity Metadata, Sustainability, and Indigenous Traditional Knowledge in Agriculture
The Indigenous communities of North America revolutionized agriculture by practicing in such a way to maintain soil nutrition and balance with the surrounding biodiversity. ENRICH/ Local Contexts ( is an international initiative dedicated to addressing the critical issue of cultural and intellectual property rights pertaining to Indigenous communities in the digital landscape. Within this realm, traditional knowledge, cultural expressions, and heritage are frequently exposed to the risks of misappropriation, misrepresentation, and unauthorized use. In response to these challenges, ENRICH/Local Contexts strives to advocate for the widespread adoption of Traditional Knowledge Labels (TK Labels) as a means of safeguarding Indigenous cultural protocols and rights associated with digital content. TK Labels play a pivotal role in providing comprehensive information about the appropriate utilization, attribution, and access restrictions surrounding Indigenous digital content. By incorporating TK Labels, ENRICH/Local Contexts ensures the preservation of Indigenous perspectives and values, which are integral to the representation and responsible usage of traditional knowledge. Significant progress has been made by developing an extensive array of labels that explicitly identify the incorporation of traditional knowledge in research endeavors. However, the integration of these labels into existing metadata standards remains a complex endeavor. The World Data System International Technology Office (WDS-ITO) is working with community partners to establish TK Labels as a universally recognized and standardized practice, which would enable comprehensive and accurate representation of traditional knowledge across diverse platforms. We are observing the current global biodiversity research and data collection landscape to inform collaboration facilitation between multiple data repositories and to ultimately create a united system for studying our environment from multiple research discipline perspectives. Additionally, streamlining current metadata standards will necessarily contribute to making research more accessible, respectful, and ethical in all fields. The TK labels are a start to actively engage Indigenous communities in decision-making processes and empower them to assert control over their cultural heritage in the digital sphere. In this presentation, I will present the current state of the project, upcoming milestones, and applications to the agriculture research and business sectors.

Marcus Schmidt
Summary of the morning session on the same topic.

IGAD/RDA : Sharing Experiences and Creating Digital Dialogues in Eastern Europe
>> session held in Russian <<

Tuesday, June 27th  10:00 AM to 12:00 UTC

Organizer and moderator: Dr.Marina Razmadze (Institute for Scientific and Technical Information - TECHINFORMI) 

Recording available:

Registration Link:

Speakers and Information about the presentations

This session will feature three presentations and discussion on digitalization of agricultural data. Sharing Experiences and case studies between countries from South Caucasus and Republic of Moldova. 
There will be a summary from the session,  final discussion among the presenters and a Q&A session.
The session will be held in Russian.

Dr.Viorica Lupu
Viorica Lupu holds a Bachelor degree in Library and Information Sciences and a Master degree in Communication Sciences. She is working as a vice-director at the Scientific Library of the Technical University of Moldova.  The main areas of her responsibility are concentrated on the library technologies coordination, information literacy teaching, digital repository, service support for research and scientific communication. She participates in developing policies, recommendations, tools and materials to support researchers in Open Science, Research Data Management and provides assistance and trainings.

Presentation: Agricultural research data landscape in the Republic of Moldova
Universities and scientific institutions should implement a research data management system to ensure the sustainable use of research data and to use its full potential. The presentation will describe how scientific institutions and agricultural researchers in the research ecosystem of the Republic of Moldova are involved in sharing research data, as well as the challenges they face in their data exchange practices and the implementation of FAIR principles.

Dr. Sos Khachikyan 
Coordinator of the Center for Digital Transformation and Data Analyses at the ASUE since February 2023. From 2018 to Feb 2023 was the Dean of the Faculty of Computer Science and Statistics of the ASUE. Project development and management through innovative tools are the main activities within NGOs, local and international organizations. 

Presentation: RDA-Based Development of Agro-Tourism Cluster of Armenia through Digital Transformation
The liquidation of the Ministry of Agriculture of Armenia has left the management system of the agrarian sector with a weak foundation. The governance of the agrarian sector is delegated to a department within the Ministry of Economy, which does not have the capacity to provide innovative approaches in the framework of contemporary trends within limited resources. In this situation data-based modeling and knowledge-driven management through the RDA platform could be a true solution for both innovative management and sustainable development of this sphere. The tourism of Armenia is another sector under the weak regulation of a department of the Ministry of Economy. This emerging sector is far from the innovations and technologies in the sense of management. In order to improve this situation it is necessary to join tourism destinations and infrastructures with agriculture under the agro-tourism cluster and initiate management based on FAIR data and RDA principles. In this regard, the Georgian advanced experience in the management of agro-data through RDA solutions can be introduced in Armenia. The role of the Ministry of Education, Science, Culture and Sport to develop FAIR data strategy at national level is significant. This strategy will support the agro-tourism cluster to have technology-based development. This means that digital transformation of agro-tourism clusters is crucial in Armenia; the methodical and technological contribution of RDA is a priority. The Armenian-Georgian cooperation in this sphere has increasing potential taking into consideration both Georgian achievement in tourism and experience in agro-data interoperability within relations with RDA. The integration of agro and tourism data of Armenia with the leading platform like RDA in the framework of the open science strategy will enable to develop agro-tourism clusters based on knowledge and innovations, providing cohesion between local needs and global value chain. It would be effective to be based on Georgian experience and partnership in this process to achieve a high level of regional tech-development.

Prof. Arzu Huseynova
Doctor of Economic Sciences (D.S.), Arzu Dogru HUSEYNOVA works closely with the formation and development of the national innovation system in the republic, also researching the innovation processes in the republic. She is the author of many ACS programs as a programmer. A.Huseynova is engaged in research in the field of information systems, innovation potential management, creation of a database of advanced technologies and innovations, evaluation of innovation activities and improvement of innovation efficiency. She conducts research in the field of scientometrics. A.Huseynova is the author of 9 books and over 100 scientific articles. Most of them are published abroad in influential journals and conference materials. A.Huseynova has 3 copyright certificates. A.Huseynova is engaged in pedagogical activity. Worked in many international and budget projects, Canadian society, AAEP Distance Education Academy; She was awarded the title of distance education consultant by the council of International Research and Exchanges Board (IREX) funded by the USA government.

Presentation: Digital Skills and Competences in Agriculture 
In today's world, decision-making is based on data.  In agriculture there is even more demand for data: data on land, weather, crops, treatments, varieties, etc. Therefore, it is very important not only to collect data, but also to process and analyze it. There are many digital tools and data processing methods for this. The digitalization of agriculture requires new skills and knowledge from agricultural workers

Farm data for Advanced Analytics 

Friday, June 30 from 14:00 to 16:00 UTC

Organizers & moderators:  Cynthia Parr (US Department of Agriculture, Agricultural Research Service)

Recording available:

Registration Link:

Speakers and Information about the presentations

Michael Ikehi
Dr. Michael Ikehi is a lecturer at the Department of Agricultural Education, University of Nigeria, Nsukka, where he holds a PhD in Agribusiness. His has researcher on several topics related to agribusiness development, agricultural innovation system, agricultural policies and data, climate change and teaching and learning in agriculture. He is an enthusiast of RDA conferences, and has participated since the first conference.

Presentation: Data on Successive National Agricultural Policies/Programs, Growth of Gross Domestic Product (GDP) and Expansion of Agribusinesses in Nigeria
Agriculture remains an important aspect of many countries’ economy, especially in developing countries. In Sub Saharan Africa, agriculture’s contribution to employment and Gross Domestic Product (GDP) is estimated to be higher than other sectors. Policies designed and implemented for the agricultural sector could be an influencing factor to the variations in the contributions of agriculture to the annual national GDP. These policies are believed to have shaped and (some) still shaping the landscape of agriculture and national economy. Based on this, the study analysed agriculture’s GDP contribution during the implementation of various national agricultural policies and the potentials of the implemented policies to foster agribusiness development in Nigeria. The study used secondary data from the Nigeria’s Federal Ministry of Agriculture and Rural Development (FMARD), World Bank and the National Bureau of Statistics. The study linked the performance of implemented agricultural policies to agriculture’s GDP contributions and national GDP growth between 2000 and 2021. Findings revealed that successive implemented agricultural policies had little influence on the agricultural sector’s percentage contribution to national GDP. However, changes in agriculture’s GDP contribution had a significant impact on national GDP growth. The duration of active life of the policies did not influence their performance, like the Root and Tuber Expansion Program (RTEP) which lasted longer performed less than the National Special Program on Food Security (NSPFS) in terms of improvement in agriculture’s GDP contributions during implementation. All the policies implemented had several limitations in their ability to foster agribusinesses in Nigeria. The study recommended that future policies should focus on providing frameworks for business development in the agricultural value chain in developing countries.

Ronald Munatse
Ronald Munatsi is the Founding Director of the Zimbabwe Evidence Informed Policy Network (ZeipNET). ZeipNET works to interface evidence and policy through capacity building and active stakeholder engagement. Some projects he has successfully led include Embedding Rapid Reviews in Health Systems Decision Making in Zimbabwe (ERAZ) supported by WHO, Building Capacity to Use Research Evidence Supported by DFID, Strengthening Research and Knowledge Systems, supported by the International Network for Advancing Science and Policy. He has participated in several research studies and evaluations on various projects, for instance, APRA’s research on pathways to agricultural commercialisation in Africa

Presentation: Using Artificial Intelligence, Machine and Deep Learning to Enhance Evidence-Informed Decision Making in Agriculture
There is pressure for evidence-informed decision-making (EIDM) emanating from sustainable agriculture challenges and a demand for inclusivity, transparency, and accountability in agricultural decision-making processes. The agriculture sector is heavily dependent on knowledge. To increase productivity, adopt sustainable practices, and alleviate global food shortages, various forms of evidence generated by the public sector, private sector, and civil society, including academia, are critical. For this evidence to be useful for decision-making, it must be accessible, and there must be tools to facilitate its synthesis, communication, and use by decision-makers. While the significance of evidence is well-documented, the agriculture industry has recently realised the benefits of open data and the need to develop tools and systems to efficiently generate, synthesise, share, and exploit this evidence in decision-making to enhance policy and overall agro-business efficiency. Machine learning (ML) and Deep learning (DL) technologies using Artificial intelligence (AI) can improve EIDM by easing complex agricultural decision-making processes. There is significant evidence of the effectiveness of these technologies in processing 'big data' too intricate for conventional processing approaches. Still, a gap exists in using them to support EIDM in agriculture. The review draws from a rapid review of relevant literature to validate the assertion that 'ML and DL technologies using AI can enhance EIDM in the agricultural sector.' Findings show that initially, computer applications were more practical at transaction processing levels and less useful in complex agricultural decision support systems. Developments in AI systems have changed this. Data management, analytics, and visualisation agencies now exist, enabling evidence integration by applying erudite analytics - rendering the evidence easily usable by decision-makers through intuitive visualisation. Complex decision-making can now be automated using AI, making it possible to analyse data trends, develop data consistency, forecast, quantify uncertainty, anticipate user information needs, provide information in the most appropriate form, and suggest numerous courses of action. It is now feasible to forecast the effects of future decisions. This way, policymakers can obtain transformational insights to improve agricultural policy and other decision outcomes in the sector.

Scout Calvert
Scout Calvert is a research data librarian at University of Nebraska-Lincoln. Dr. Calvert's research background is in science and technology in society. She is co-director of the National Agricultural Producers Data Cooperative project at UNL. Her current projects trace the social aspects of data-centric knowledge production among genealogists, cattle breeders, and citizen historians. Dr. Calvert also investigates data infrastructure and practice in libraries and among academic researchers, informing data policy issues in academic libraries. 

Presentation: National Agricultural Producers Data Cooperative (NAPDC)
This presentation will introduce the National Agricultural Producers Data Cooperative (NAPDC), a collaborative project launched in 2021 by the USDA to design and initiate a national ‘open’ data framework for producers ( . Framework development involves both `horizontal’ and `vertical’ components such as data ownership, data federation, public-private partnerships, education and training, and pilot studies, and a diversity of stakeholders across career stages, economic sectors, and institutions. We have hosted monthly webinars on activities relevant to the framework and supported a group of initial `convening awards’ to support community engagement and information gathering activities. The NAPDC held an initial all-hands meeting in May 2023 with presentations, panel discussions, and structured activities designed to gather community input on the framework components and ideas for development, including critical use cases. We will present some of our key findings and invite discussion of NAPDC among attendees. 

Laurent Tits 
Laurent Tits (PhD in Bioscience Engineering) is currently the team leader of the agricultural applications team at VITO Remote Sensing, Belgium. With his team, current agricultural applications of EO data encompass the broad range of very precise UAV data for detailed monitoring and phenotyping, up to the general monitoring of all the agricultural production areas on a global scale and everything in between. His main focus was on the use of EO data in Africa, and in a development context. He is involved in opening agro-data for global monitoring capacities, and he initiated the recently started HE ScaleAgData project on in-situ sensor data for European-wide agro-environmental monitoring.

Presentation: Scaling agricultural sensor data for improved monitoring of agri-environmental conditions
Clear targets have been defined by the EU for a more competitive and sustainable agriculture (Green Deal). This requires data-driven decision making for farmers, governments and other policy makers, yet there is a severe reference-data gap when observations are needed at the local level. An underexploited source of data is generated by sensors used in agriculture, as they capture crucial information on the crops and the surrounding agri-environmental conditions. Tapping into this source and upscaling them the integration with other data (e.g. satellite) could result in enhanced capacities for regional agri-environmental monitoring. This would require a paradigm shift on how the monitoring systems work, and on the issues of data ownership and governance.
The vision of the recently EU-funded ScaleAgData project is thus to gain insight in (i) how these data streams should be governed to the benefit of all stakeholders, especially the farmers, and (ii) how these data can be integrated in the regional agri-environmental monitoring datasets. Through this upscaling, this wealth of information can be shared with a larger farmer community, thus shrinking the technological inequality in the sector. Specific attention will be paid to innovations in sensor technology, edge computing, data analytics, and novel EO-based products. It is especially in this latter aspect that the use of novel AI methodologies is foreseen, with innovations in for example privacy-preserving AI technologies such as federated learning, or novel methodologies to make optimal use of the available sensor data. These encompass innovations in applications with only limited amount of sensor data (e.g. self-supervised learning, few-shot learning), how to update trained models with newly incoming sensor data (e.g. continuous learning), or how to improve model outputs with the NRT sensor data ( e.g. AI-based data assimilation methods).
These innovations will be co-designed and showcased in 6 Research and Innovation Labs, each with their specific thematic focus and spread across Europe. This will enable the assessment of the proposed innovations and data governance frameworks, and demonstrating added values of the improved monitoring capabilities for a range of users, including small-scale and agro-ecological farmers, the financial sector, and policy makers.
With these outcomes, ScaleAgData aims at contributing to the overall competitiveness and sustainability performance of the European agricultural sector, and to the work of the HE candidate partnership “Agriculture of Data” and the Soil Mission.
The project started at the beginning of the year, and we will showcase the general objective of the project, the different research labs, and the foreseen strategy to reach the project objectives.

Dagafu Hunde
I am a graduate of Master’s Degree (MSC) in Computer Science and a Bachelor Degree (B.Sc.) in Computer Science and IT, from Wollega University. I have also a certificate of CCNA from Jimma University. At present, I am working for Ethiopian Institute of Agricultural Research (EIAR) where I am responsible for tasks and activities given for the position System Analyst III at this Institute. 

Presentation: [Title TBA]
In order to revitalize the agricultural extension practice, we need a national platform for the extension workers and farmers to communicate from afar and to enhance the provision of information and new technology. With greater access to such information, farmers are able to improve their production, incomes and standard of living. In Ethiopia currently now we are focusing on revitalizing agricultural extension services by empowering and equipping extension workers with IT skills to support farmers in the areas of wheat rust advisory information in different languages like English , Amahric , Afan Orommo and Tigrigna using modern web portal system, give training for the extension agents using e-learning platform due to COVID 19, monitor and report the farmers research extension group about their yield information using GPS based system and linked with the national research activity, track the LSD (Large scale demonstration) information using digital interactive dashboard about the cluster, demonstrated research technology, total number farmers participated in a gender sensitivity format, disseminating newly published research publication using 7604 SMS based system (e.g. proceeding , journals, production manuals etc.) about wheat and dairy research areas, preparing agricultural technology variety database this changes the extension practice in the country to the next level by providing farmers with knowledge and tools about modern agricultural practices and linking them to new technology. 

IGAD celebrates the RDA 10th anniversary year

The IGAD virtual annual meeting will be promoted as part of RDA’s Agricultural and Environmental Data month (see The RDA's 10th Anniversary Events and Activities | RDA (

Formed in 2013, the Interest Group on Agricultural Data (IGAD) has grown to over 200 members. In 2021 we became RDA’s first Community of Practice. IGAD works on all issues related to Improving Global Agriculture Data. It represents stakeholders in managing data for agricultural research and innovation, including producing, aggregating and consuming data. It is a forum for sharing experiences and providing visibility to research and work in agricultural data. One of IGAD’s main roles is to facilitate creation of domain-specific Working Groups. Beyond this IGAD promotes good practices in research with regard to data sharing policies, data management plans, and data interoperability.