xrf4473XGBoostTrace.quant

Extreme gradient boosting machine learning (XGBoost) models were used with data from portable XRF instrument serial number 900F4473 for the Manure Trace Calibration (35 kV, 35 μA and 90 seconds, Filter- Cu 75um:Ti 25um:Al 200um. Elemental Range: K, Ca, Ti, Cr, Mn, Fe, Co, Ni, Cu, Zn, As, Se, Mo, Cd, and P). For example, trees can be built from randomly selected columns (Energies for pXRF spectra) and rows (standards). XGBoost (0.82.1) models were run using 400 rounds with a variable tree depth ranging from 5 to 25. Learning rates (eta) were constrained to values between 0.1 and 0.3, with gamma regularization ranging from 0 to 0.1. The minimal child weight (controls the model complexity) was limited to 1. Unique combinations of these variables were run over 32 iterations with kfold using caret (6.0–82) and the best model was selected using root mean square error (RMSE). Calibrations were created using CloudCal (v3) Spectra are saved in this file in RDS format and they work with open-source code repositories.