Offer summary

Qualifications:

PhD in related field, 8 years of experience, Knowledge of forecasting and time series analysis, Familiar with ML and AI techniques, Proficient in data management and analysis.

Key responsabilities:

Conduct systematic review for demand estimation

Predict cultivation area, production, and yield

Prepare technical reports and briefs

Collaborate with digital team on tool integration

Create manuscript for peer-reviewed journal

Job description

This is a remote position.

About CIP

CIP is a not-for-profit international agricultural research organization with a global mandate to conduct research on potatoes, sweetpotatoes, Andean root and tuber crops, and sustainable management of natural resources. CIP’s vision is to contribute from its areas of expertise to the fulfillment of the Millennium Development Goals (MDGs), in particular those goals that relate to poverty, hunger, child and maternal mortality, and sustainable development. CIP has its headquarters in Lima, Peru with staff and activities in locations across Africa, Asia and Latin America. CIP, a member of the One CGIAR, a global research partnership for a food-secure future. One CGIAR science is dedicated to transforming food, land and water systems in a climate crisis, and it is carried out by 13 CGIAR Centers/Alliances in close collaboration with hundreds of partners, including national and regional research institutes, civil society organizations, academia, development organizations and the private sector

Background

We have developed the Seed Requirement Estimation (SRE) tool to estimate the seed needed at every stage of the seed value chain ( https://mt.co.ug/bid_tools ). Currently, the tool relies on a series of assumptions to estimate the actual seed requirements at each stage. These estimates are fully dependent on the area under cultivation for vegetatively propagated crops (VPCs). At present, we use a linear projection model, but this model lacks accuracy level as compared to estimation measured using Machine Learning (ML) or Artificial Intelligence (AI). Therefore, we aim to integrate machine learning and AI tools to predict the area under cultivation, production, and yield for VPCs across various market segments. Our focus includes Uganda, Tanzania, and India, specifically for crops like potato, sweetpotato, and cassava. Additionally, we have introduced specific varieties in each selected country tailored to specific market segments.

Objective

• Conduct a systematic review for the demand estimation, particular interest on VPCs.

• Predict area under cultivation for each VPC, production (tons) and yield (tons/ha) based on historical data and other factors that influence these indicators using time series analysis, ML and AI technique.

• Prepare a technical report and brief(s)

• Work closely with SRE digital team and assist the digital team to integrate this information in the SRE tool and validate the tool with potential users.

• Prepare a manuscript for the peer-reviewed journal.

Deliverables

• Study design and preliminary desk study

• Preliminary report for comments.

• Final report, briefs, manuscript.

Requirements

Selection Criteria

PhD in Agribusiness, Agricultural Economics, Applied Econometrics, time series analysis related area.
At least eight (8) years’ experience.
Knowledge in forecasting and time series analysis, Machine learning and Artificial Intelligence, ARIMA models, ARCH and GARCH models.
Excellent writing skills (English), data management and analysis skills, ability to interact with multidisciplinary teams from private and public partners.