Bite+

CGIAR’s Platform for Big Data in Agriculture and its Data Ecosystem: Global Agricultural Research Data Innovation and Acceleration Network (GARDIAN)

"Easily discoverable, well-annotated, interoperable data assets are critical to catalyzing transformation of the agricultural sector"

The CGIAR system and others working in the agriculture for development realm are charged with tackling challenges at a variety of scales from the local to the global, which generally means being able to query and/or aggregate a variety of ... view more

VIDEO

Opening Remarks: How can we generate, organize, and use data for transforming our food systems?  Data needs to be accessed, managed and unionized to ease the processes around its efforts.

VIDEO

From Data to Insight - Medha Devare Presentation 1: Where can I find data on nutritional status of women? What does variation in crop response to fertilizer look like for Sub-Saharan Africa? How do I make my data Interoperable, Reusable and Findable? 

VIDEO

From Data to Insight - Medha Devare Presentation 2: The Big Data platform enables the use of Machine Learning technologies to operate over data sets and understand the rules governing its use.  Watch the Bite video to learn about what Findable Accessible Interoperable Reusable (FAIR) data means.

VIDEO

From Data to Insight - Medha Devare Presentation 3: What can you do once the data is FAIR? Watch the Bite video to get a demo of semantically-enabled data, which means data that is adherent to ontologies and vocabularies.

VIDEO

Part 5 - Remarks by Erick Fernandes, Lead Agriculture Specialist, SAGDR: Using modern data management, data classification ontologies and scraping techniques can enable us to aggregate different data sets depending on questions and allow us to use that data for decision support. 

VIDEO

Part 6 - Remarks by  Jonathan Wadsworth,  Lead Climate Change Specialist, SSCD1: The story started with open access. It should be a duty of organizations and national systems to make sure the data is curated, collected and made Findable Accessible Interoperable Reusable (FAIR).

VIDEO

Part 7 - Remarks by Jonathan G. Kastelic, Survey Specialist, Development Data Group DECPM: How do we improve the quality of the data? How do we leverage data for development, both micro data and big data? Where is the place for household surveys in this? 

VIDEO

Q & A - Part 1: When presenting GARDIAN to non-scientists and non-researchers, what is the kind of push back received from government officials and other stakeholders? What are the statistics on who the GARDIAN's users are? 

VIDEO

Q & A - Part 2: The GARDIAN platform brings together the different data sources, though how is pre-processing part of accessing these data sets? Are there restrictions on researchers who might want to upload their own data and make the data available? How is the private sector cooperating with the GARDIAN data ecosystem? 

VIDEO

Q & A - Part 3: As the databases are aggregated, have the data sets gotten large enough that anomalies revealing biases in the data can be identified? 

About the Presenters

Medha Devare

Senior Research Fellow at IFPRI

Medha Devare leads one of the three Modules of the CGIAR Platform for Big Data in Agriculture. She led the Open Access/Open Data Initiative from the CGIAR System Office in France, and currently spearheads efforts to operationalize the FAIR Principles towards Findable, Accessible, Interoperable, and Reusable data across CGIAR Centers. Medha is an agronomist and microbial ecologist with significant experience working on and leading projects addressing food and nutritional security and sustainable resource management in South Asia. She also has experience in data management and semantic web standards and tools. Before she moved to France, Medha was a Scientist at CIMMYT based in Nepal, where she led the USAID-funded Cereal Systems Initiative for South Asia in Nepal (CSISA-NP) to increase the productivity and profitability of small farmers and the sustainability of farming systems in western Nepal. Prior to her position at CIMMYT, Medha worked at Cornell University, where she also received her PhD, and where she helped develop VIVO, a semantic web application for representing research and scholarship.