Digital mapping of soil attributes using machine learning

Resumo

Mapping the chemical attributes of the soil on a large scale can result in gains when planning the use and occupation of the land. There are different techniques available for this purpose, whose performance should be tested for different types of landscapes. The aim of this study was to spatialize chemical attributes of the soil, comparing eight methods of prediction. Forty morphometric attributes, generated from a digital elevation model, were used as independent variables, in addition to geophysical data, images from the Landsat 8 satellite and the NDVI. All possible combinations between the satellite bands were calculated, generating 28 new variables. Combinations between the Th, U and K bands obtained from the geophysical data were also calculated, generating a further three variables. The final variables to be calculated were the distances between the four points of the edges of the basin (d1, d2, d3 and d4). The dependent variables for the model were Al, Ca, Fe, K, Mg, Na, Si, Ti, Cr, Cu, Mn, Ni, P, Pb, V, Zn, Zr, S and Cl. A total of 200 soil samples were used, which were collected from 100 points at two depths (0-10 and 10-30 cm); the total elements were determined using an X-ray fluorescence analyzer. The Random Forest algorithm proved to be superior to the others in predicting the chemical attributes of the soil at both depths, and is suitable for predicting soil attributes in the study region. Spatial variables are essential, and should be considered when modelling chemical elements in the soil. Using the methods under test, it is possible to predict elements with R² values ranging from 0.32 to 0.62.