Soil texture is a key soil property influencing many agronomic practices including fertilization and liming. Therefore, an accurate estimation of soil texture is essential for adopting sustainable soil management practices. In this study, we used different machine learning algorithms trained on vis–NIR spectra from existing soil spectral libraries (ICRAF and LUCAS) to predict soil textural fractions (sand–silt–clay %). In addition, we predicted the soil textural groups (G1: Fine, G2: Medium, and G3: Coarse) using routine chemical characteristics as auxiliary. With the ICRAF dataset, multilayer perceptron resulted in good predictions for sand and clay (R2 = 0.78 and 0.85, respectively) and categorical boosting outperformed the other algorithms (random forest, extreme gradient boosting, linear regression) for silt prediction (R2 = 0.81). For the LUCAS dataset, categorical boosting consistently showed a high performance for sand, silt, and clay predictions (R2 = 0.79, 0.76, and 0.85, respectively). Furthermore, the soil texture groups (G1, G2, and G3) were classified using the light gradient boosted machine algorithm with a high accuracy (83% and 84% for ICRAF and LUCAS, respectively). These results, using spectral data, are very promising for rapid diagnosis of soil texture and group in order to adjust agricultural practices.
Visible and near-infrared diffuse reflectance spectroscopy (VIS-NIR) has shown levels of accuracy comparable to conventional laboratory methods for estimating soil properties. Soil chemical and physical properties have been predicted by reflectance spectroscopy successfully on subtropical and temperate soils, whereas soils...
Sorghum crop is grown under tropical and temperate latitudes for several purposes including production of health promoting food from the kernel and forage and biofuels from aboveground biomass. One of the concerns of policy-makers and sorghum growers is to cost-effectively...
CONTEXT
Big data applications in agriculture evolve fast, as more experience, applications, good practices and computational power become available. Actual solutions to real-life problems are scarce. What characterizes the adoption of big data problems to solutions and to what extent...
A fragmented digital agriculture ecosystem has been linked to the slow scale-out of digital platforms and other digital technology solutions for agriculture. This has undermined the prospects of digitalizing agriculture and increasing sectoral outcomes in sub-Saharan African countries. We conceptualized...
Scaling is a ubiquitous concept in agricultural research in the global south as donors require their research grantees to prove that their results can be scaled to impact upon the livelihoods of a large number of beneficiaries. Recent studies on...