Extrapolation of fertilizer recommendations in West Africa

Site-specific fertilizer recommendations for major food crops in West Africa have been updated and mapped by ISRIC in collaboration with the International Fertilizer Development Centre (IFDC) and experts from the NARs of Benin, Burkina Faso and Ghana. The project was carried out within the context of the West Africa Fertilizer Program (USAID WAFP) which IFDC has implemented over last five years in collaboration with the Economic Community of West African States (ECOWAS). 

The work provides a proof of concept for progressive updating and upscaling of fertilizer recommendations across the region. The results were presented to approximately 160 participants of the regional forum ‘From soil analysis to delivering more profitable fertilizers to farmers’ in Lomé, Togo (11-13 April 2017). The forum was organised by the West Africa Fertilizer Program (WAFP), the Four-Country Cotton Partnership (C4CP) and the Feed the Future Ghana Agricultural Technology Transfer Project, all implemented by IFDC, in collaboration with ECOWAS, to agree on pathways to delivering fertilizer recommendations that will result in sustaining greater returns on fertilizer investments, and yields, particularly for smallholder farmers. The proof of concept was well received by the various stakeholders and provides a pathway together with an operational framework for concrete collaborative follow up.

A tiered approach was applied which makes use of the recently released soil nutrient maps for Africa (SoilGrids). These maps present estimates for all macro, meso and most micro nutrients at a resolution of 250m and were produced using soil analytical data from over 50,000 sample locations. QUEFTS was used to model and map crop nutrient uptake and use-efficiencies and corresponding fertilizer recommendations for millet, sorghum, maize, rice and cassava. These first tier maps were added to other spatial covariates of the region to model and extrapolate fertilizer recommendations, reported for point locations, in a second tier using machine learning. The crop and site specific fertilizer recommendations can be readily updated and mapped upon the availability of additional, adequate, soil-crop data.