The paper presents simple machine learning models used for prediction of some soil properties based on the NIR spectral response. Data on mineral soils from Poland were taken from the LUCAS dataset. Machine learning model was used that is included in the category of so-called multilayer perceptron (MLP). The MLP model input was a vector of combined, transformed inputs made by means of the PLSR (partial last squares regression) algorithm (45 inputs in total). The output was a vector of properties, reduced to 9 components due to poor modelling effects of the P and K components. The estimation errors for texture, soil organic carbon (SOC) and carbonates can be considered acceptable from the point of view of their suitability in the development of cartographic documentation. It can be supposed that further regionalization will improve these results. ...
The paper presents the diversity of soil organic carbon (SOC) contents in soils of three reclaimed objects: external dumping grounds of mines Bełchatów, Machów and Turów. Sites vary in soil texture, age of tree stands and their species composition. The largest carbon pool in the organic level (litter) is in a dumping ground for the Turów mine,- the oldest of the objects. Similarly, the total SOC pool in the organic layer and the mineral to 30 cm deep in the soil is the largest dumping ground, Turów. The average annual increase in SOC stocks varied from about 0.5 t/ha/year in Bełchatów, after more than 1.2 t/ha/year in Machów. The annual deposition of organic carbon can be estimated at 1.7-2.5 t / ha / year. ...
