Scientists developed a novel method of automatic soil mapping
A team of soil scientists developed a new approach to the automatic generation and updating of soil maps. Having applied machine learning technologies to a set of rules traditionally used by experts in manual mapping, the team obtained a highly accurate model that provides easy-to-interpret results. The study was published in ISPRS International Journal of Geo-Information.
Many software solutions for digital soil mapping are based on statistical models. The accuracy of such programs is limited because statistical models depend on the quality and quantity of field data and can ignore local irregularities in soil properties. It is difficult to obtain accurate and useful information from ...











