Many African countries are chronically dependent on food imports, as agricultural productivity growth has not kept pace with the significant rise in food demand associated with population growth. In order to improve agricultural productivity, it is necessary to fully understand soil fertility and establish fertilization management technology based on the soil information. It is known that there are various agroecosystems in Africa, and that the chemical and physical properties, which are indicators of soil fertility, are extremely variable. Moreover, even at short distances, it is affected by micro-topography and its properties change significantly.

In order to deepen the understanding of soil fertility in Africa, various surveys have been conducted to establish appropriate fertility management techniques. In recent years, a large amount of data has been compiled and the construction of a digital map of soil fertility is in progress. This time, a team of researchers conducting joint research with JIRCAS and CGIAR has developed a new soil map with a 30m resolution which was published in Scientific Reports.

Soil fertility characteristics such as soil pH, organic carbon, and total nitrogen predicted using 150,000 soil samples and earth observation data obtained by remote sensing technology were used for the preparation. Its prediction accuracy is improved compared to the existing 250m mesh map. This 30m mesh soil information is expected to provide basic information for improving agricultural productivity and contribute to the establishment of fertilizer management technology according to the soil information. This map information is now available on this site.

Reference

Hengl, T., Miller, M.A.E., Križan, J. et al. African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. Sci Rep 11, 6130 (2021). https://doi.org/10.1038/s41598-021-85639-y

Contributor: SAITO Kazuki (Africa Rice Center / Social Sciences Division)