It all starts with a scan from the sensors of the SoilCares Lab-in-a-Box or Scanner, that produces a spectral image. From these spectra, several regression models produce the numerical predictions that are returned to the client as a soil status. Indeed, the real intelligence of our solutions lies in the database and its algorithms.
It is really by creating and training machine learning regression models that SoilCares has made it possible to predict the content of a soil sample from a spectrum.
These regression models are developed country by country by our team of experts. Our agronomists first determine the number and location of samples required to cover the full spectral range of a country using data like soil type, land use, fertiliser and crop residue management, satellite crop development images, climate and elevation.
Sampling team in the Philippinnes