Prediction of soil organic matter content by combining data from Nix Pro™ color sensor and portable X-ray fluorescence spectrometry in tropical soils

Soil organic matter (SOM) measurement is of great agricultural and environmental importance. Thus, the development of rapid, environmentally-friendly, economical and reliable assessment methods is challenging. Soil proximal sensors have become an important approach for SOM prediction worldwide, but require regional calibration. This work aimed to assess the efficiency of SOM content prediction using the Nix Pro (TM) color sensor and portable X-ray fluorescence (pXRF) spectrometry, either separately or combined. The type of soil horizon collected (A or B) was used as auxiliary input data. A total of 705 Brazilian variable soil samples were analyzed in the laboratory for SOM content and scanned by Nix Pro (TM) and pXRF. Via Nix Pro (TM), samples were analyzed both dry and moist since moisture changes their color. Prediction models were built using 70% of the data via the stepwise multiple linear regression (SMLR), support vector machine with linear kernel (SVM) and random forest (RF). Validation was performed with the remaining 30% of the data through the coefficient of determination (R-2), the root mean square error (RMSE) and the residual prediction deviation (RPD). SOM content was predicted with good accuracy (R-2 = 0.73, RMSE = 1.09% and RPD = 2.00) using the RF algorithm trained with combined data from the Nix Pro (TM) and pXRF sensors. Soil horizons and Ca content were the two most important predictor variables. The combination of data obtained by Nix Pro (TM) and pXRF yielded accurate SOM predictions for a wide variety of Brazilian soils, in addition to being environmentally-friendly, without generating chemical waste.

Automated summary

This study evaluated the efficiency of predicting soil organic matter (SOM) content using the Nix Pro (TM) color sensor and portable X-ray fluorescence (pXRF) spectrometry. By combining the data obtained from these sensors and training a random forest algorithm, accurate predictions of SOM content for various Brazilian soils were achieved.