Assessment of the soil fertility status in Benin - Digital soil mapping using machine learning
Indicators of soil production function such as soil fertility index can potentially be a key decision tool in spatial planning for sustainable land management. The establishment of such soil fertility index requires basic soil properties which can be modelled for spatial mapping. The objective of this study was to take advantage of the soil legacy data of Benin to produce a digital soil map of soil fertility index at a national scale based on 8 soil properties (soil organic carbon matter, nitrogen, pH, exchangeable potassium, assimilable phosphorus, sum of base, cation exchange capacity and base saturation). Speciﬁc research aims were: (1) to model and develop digital soil maps; (2) to identify important factors influencing soil nutrients; (3) to establish soil fertility potentials using digital soil maps. For each soil property, modelling procedures involved the use of diﬀerent covariates including soil type, topographic, bioclimatic and spectral data along with the comparative assessment of the Cubist and Random Forest model. Results revealed that apart from N and exchangeable K, significant models can be produced for most of the soil properties with R-square varying between 28% and 72% with the Random Forest presenting a more accurate prediction interval coverage probability. The analysis revealed that the distance to the nearest stream has strong predictive ability for all the soil properties along with the bioclimatic variables. Visualisation of the soil fertility map showed that most of the soils in Benin have low fertility level suggesting that the use of fertilizers and organic materials will be critical in sustaining crop productivity. A limited number of high and average fertility level soils were found in the low elevation areas of southern Benin and policy could advocate for their sole use for agriculture purpose as well as promote sustainable management practices. A data visualization and decision support tool is under development to support the effective use of the project results.
Leveraging Agricultural and Environmental Potential of West Africa
HCS entered in a joint-venture with experienced German partners to develop/test sound ecological/green solutions to secure and leverage African agricultural and environmental potential. These solutions are expected to support efficient/sustainable agriculture and public area greening under salty soil, severe water scarce, harsh climate and environmental conditions. In general, farmers need products which are able to store nutrients and water and keep them long-lasting available to plants. In this context, possible solutions will have to consider combining specific water absorber (e.g. cross-linked polymers) with Potassium to drastically reduce required water amounts for crop growth and prevent salt toxicity effects. This may require the use of colloidal technology with a determined rate of Nitrogen-Phosphorus depending on the initial soil conditions. Two main research axes are considered:
products/solutions based on the colloidal technological approach applicable in context of forestry and landscape maintenance (including trees, grass, lawn, parks gardens, etc.), which must contain everything that plants are in need of, like main elements – bound Nitrogen, Trace elements, Vitamins, organic materials, etc. They must support good and deep growing root systems under salty soil or very harsh hydro-climate and environmental conditions. They also have to include surface stabilizers and demonstrate the ability to penetrate immediately the soil.
water storing and amending solutions/products for all types of soils, but mainly for sandy and salty soils, capable of absorbing large quantities of water. Water must be made available only to the plants to reduce irrigated water. These solutions are highly expected to be applied in Horticulture, agriculture in general, tree transplantations, protection of trees during bare-rooted transport, creation of lawns, etc.
HCS will consider setting-up a significant number of trials in various agroecologic zones under two contrasted sub-Saharan African conditions: (1) a dry/semi-arid condition in Burkina Faso; and (2) semi-humid condition in Benin Republic where salt content in soil is prejudicial to plant growth in the coastal area. It is worth mentioning that the Benin Government is implanting right at the sea beach hectares of coconut trees, which visibly show damaging salt effects. HCS will likely support the implementing agency to face the challenge.