Dynamic optimization of predictors selection for spatial smallholder yield forecasts


Dynamic optimization of predictors selection for spatial smallholder yield forecasts

Host institution : ICRISAT / agCelerant-Ethiopia, Addis Ababa

Supervisors: Pierre C. Sibiry Traore / Kindie Tesfaye / Vakhtang Shelia

Project Description:
The CCAFS Regional Agricultural Forecasting Tool (CRAFT) allows for multi-model forecasting of crop yields based on various predictors such as sea surface temperature (SSTs) and model output statistics (MOS). Identifying SSTs and MOS sets that have skill for specific agricultural production environments may involve expert knowledge which is not always locally available. This internship will develop a procedure for optimal predictor selection as a prerequisite for CRAFT operations, contributing to the CASCAID 2.0 (CCAFS) project and informing the NADiRA innovation action.

Expected outcome:

Efficient predictor selection enhances the relevance of spatial yield forecasts, control of aggregate risk, and decision making leading to food security.

Applications for this internship should be submitted via the online application system, stating clearly the title of the internship.

Deadline for applications: January 20th, 2020 – 11:59 PM (EAT).

Any inquiries about these internships should be sent to:
aims-ms4cr.internship@nexteinstein.org.