Big Data in
CGIAR
Elizabeth Arnaud
Bioversity International
22nd September, IGAD pre-
meeting, INRA, Paris
CIAT: Big Data for Climate
Smart Agriculture
 CIAT analysis large, real-world data sets from annual survey
on rice to produce recommendations much more quickly.
1. Harvest results of annual surveys and agronomic experiments
from National Private Companies
2. Get Planting times for specific sites and seasonal forecasts
3. pairing historical records with state-of-the-art seasonal
forecasts
4. Analyses with advanced algorithms from biology, robotics and
neurosciences
5. Searches for weather patterns in previous years and checked
which varieties did best in those years
 Result: Identify the most productive rice varieties and
planting times for specific sites and seasonal forecasts.
Recommendations could potentially boost yields by 1 to 3
tons per hectare.
Crowdsourcing varieties
500 farmers per site will be given 3 blind varieties in small quantities to
be tested under their own conditions (the crowdsourcing approach)
CGIAR Big Data
 Large amounts of data accumulated by
CGIAR Centers to be published as Open
Data Highthrouput production of data:
 Highthrouput Genotyping
 Highthrouput Phenotyping
 Remote Sensing data
 Citizen Sciences ( Crowd Sourcing)
 Open Data-Open Access Strategy for CGIAR
8 Agrifood System research
programmes
 Big Data platform will support the 8 CRPs
1. Dryland Cereals and Legumes Agri-food
System
2. Fish Agri-food Systems
3. Forest and Agroforestry Landscapes
4. Livestock Agri-food Systems
5. Maize Agri-food Systems
6. Rice Agri-food Systems
7. Roots, Tubers and Bananas Agri-food
Systems
8. Wheat Agri-food Systems
5 Global Integrative
Programmes
 to ensure that research results deliver solutions at
the national level that can be scaled up and out
to other countries and regions.
1. Genebanks ++
2. Nutrition and Health
3. Water Land and Ecosystems (including
soils);
4. Climate Change
5. Policies, Institutions and Markets
research
Big Data and ICT: Call for
Expressions of Interest
 A number of scientific organizations developed high
performance computing facilities and big data
analytical capabilities.
 A major opportunity exists for the CGIAR to leverage
this investment in capability and infrastructure
 Strong partnerships across the Consortium and
beyond it,
 work with existing and promising efforts to support
the creation of a global-agri-informatics platform
and network that ensures compliance with Linked
Open Data and other standard interoperability
protocols.
IFPRI-led EOI: Tools for Driving
Interdisciplinary and Collaborative
Big Data Analytics
 Implementation of CGIAR Survey Platform Data
for data collected through mobile phones
 from connected sensor network across trial sites
 Further development of agricultural ontologies
with research communities’ inputs
 Implementing Linked Open Data and APIs in
data repositories
 Enabling Data Discovery
 Use cases:
 Scalable Satellite-based Crop Yield Mapper
(SYCM):
 Crop Water Productivity (CWP)
 Remote Sensing for Agro-biodiversity Monitoring
Call for Pre-proposals for
CGIAR Research Programmes
 http://www.cgiar.org/our-
strategy/second-call-for-cgiar-research-
programs/crp-2nd-call-pre-proposal-
submissions/

SC2 Workshop 1: Big Data in CGIAR

  • 1.
    Big Data in CGIAR ElizabethArnaud Bioversity International 22nd September, IGAD pre- meeting, INRA, Paris
  • 2.
    CIAT: Big Datafor Climate Smart Agriculture  CIAT analysis large, real-world data sets from annual survey on rice to produce recommendations much more quickly. 1. Harvest results of annual surveys and agronomic experiments from National Private Companies 2. Get Planting times for specific sites and seasonal forecasts 3. pairing historical records with state-of-the-art seasonal forecasts 4. Analyses with advanced algorithms from biology, robotics and neurosciences 5. Searches for weather patterns in previous years and checked which varieties did best in those years  Result: Identify the most productive rice varieties and planting times for specific sites and seasonal forecasts. Recommendations could potentially boost yields by 1 to 3 tons per hectare.
  • 3.
    Crowdsourcing varieties 500 farmersper site will be given 3 blind varieties in small quantities to be tested under their own conditions (the crowdsourcing approach)
  • 4.
    CGIAR Big Data Large amounts of data accumulated by CGIAR Centers to be published as Open Data Highthrouput production of data:  Highthrouput Genotyping  Highthrouput Phenotyping  Remote Sensing data  Citizen Sciences ( Crowd Sourcing)  Open Data-Open Access Strategy for CGIAR
  • 5.
    8 Agrifood Systemresearch programmes  Big Data platform will support the 8 CRPs 1. Dryland Cereals and Legumes Agri-food System 2. Fish Agri-food Systems 3. Forest and Agroforestry Landscapes 4. Livestock Agri-food Systems 5. Maize Agri-food Systems 6. Rice Agri-food Systems 7. Roots, Tubers and Bananas Agri-food Systems 8. Wheat Agri-food Systems
  • 6.
    5 Global Integrative Programmes to ensure that research results deliver solutions at the national level that can be scaled up and out to other countries and regions. 1. Genebanks ++ 2. Nutrition and Health 3. Water Land and Ecosystems (including soils); 4. Climate Change 5. Policies, Institutions and Markets research
  • 7.
    Big Data andICT: Call for Expressions of Interest  A number of scientific organizations developed high performance computing facilities and big data analytical capabilities.  A major opportunity exists for the CGIAR to leverage this investment in capability and infrastructure  Strong partnerships across the Consortium and beyond it,  work with existing and promising efforts to support the creation of a global-agri-informatics platform and network that ensures compliance with Linked Open Data and other standard interoperability protocols.
  • 8.
    IFPRI-led EOI: Toolsfor Driving Interdisciplinary and Collaborative Big Data Analytics  Implementation of CGIAR Survey Platform Data for data collected through mobile phones  from connected sensor network across trial sites  Further development of agricultural ontologies with research communities’ inputs  Implementing Linked Open Data and APIs in data repositories  Enabling Data Discovery  Use cases:  Scalable Satellite-based Crop Yield Mapper (SYCM):  Crop Water Productivity (CWP)  Remote Sensing for Agro-biodiversity Monitoring
  • 9.
    Call for Pre-proposalsfor CGIAR Research Programmes  http://www.cgiar.org/our- strategy/second-call-for-cgiar-research- programs/crp-2nd-call-pre-proposal- submissions/

Editor's Notes

  • #4 Citizen science Parallel to the mother and baby trials, 500 farmers per site will be given 3 blind varieties in small quantities to be tested under their own conditions (the crowdsourcing approach) and will be asked to evaluate the material and provide feedback on their preferences, they will become citizen scientists. Data and feedback will be collected by ERMCSD with the engagement of extension services after receiving appropriate training by Bioversity. The feedback will be collected using a simple questionnaire using mobile phones/tablets for immediate submissions to the data manager. This data will be linked to a global portal developed by Bioversity and CIAT to upscale the approach and will be analyzed using ClimMob software developed by Bioversity (van Etten, 2014).