Jun 20, 2021
Towett, Erick K.; Drake, Lee B.; Acquah, Gifty E.; Haefele, Stephan M.; McGrath, Steve P.; Shepherd Keith D., 2020, "Replication Data for: Comprehensive Nutrient Analysis in Agricultural Organic Amendments Through Non-Destructive Assays Using Machine Learning", https://doi.org/10.34725/DVN/YTJTZQ, World Agroforestry - Research Data Repository, V2, UNF:6:bmSAWgS3un1yCIZ6kBgkyw== [fileUNF]
Portable X-ray fluorescence (pXRF) and Diffuse Reflectance Fourier Transformed Mid-Infrared (DRIFT-MIR) spectroscopy are rapid and cost-effective analytical tools for material characterization. We developed machine learning methods to rapidly quantify the concentrations of macro-... |
Tab-Delimited - 4.0 MB - MD5: af113c123eafb0e178d1fff26ead388f
Averaged MIR spectra of the manure standards run on the HTS-XT instrument |
Tab-Delimited - 1.7 MB - MD5: 04321069d86a1809483d5371167fc029
Averaged MIR spectra of the manure standards run on the MPA instrument |
Tab-Delimited - 16.8 KB - MD5: bf77e2d569443faabf9c4bbfe1623db9
Manure standards reference data |
Unknown - 81.6 MB - MD5: a6b8d8504ce61253cae2079c2f3885ed
Using forest regression machine learning models, excellent calibration functions could be established using the MIR spectra. Forest models for there DRIFT-MIR spectra were run using 1500 trees with 200 resampling events using k-fold cross validation over 25 iterations based on th... |
Tab-Delimited - 2.9 MB - MD5: 8362ced45ea5d1bdce9773d08bb21e9a
MIR spectra of the manure standards using Alpha KBr instrument |
Tab-Delimited - 1.8 MB - MD5: b56570fc695ece2feb1d58627985846c
MIR spectra of the manure standards using Alpha ZnSe instrument |
Unknown - 29.3 MB - MD5: ac2c20646882bb5b387f26ed9ed53cae
Extreme gradient boosting machine learning (XGBoost) models were used with data from
DRIFT-MIR spectroscopy and these differ from forest in that trees can be weighted differently, have fixed depths, and different resembling. XGBoost (0.82.1) models were run using 400 rounds with... |
Tab-Delimited - 5.1 KB - MD5: e5f50e7daea6b4594069806a2f0de5f3
Variables description file |
Unknown - 6.8 MB - MD5: 2a26970f2271fee45954c97ad6bd68bd
Forest models for pXRF spectra from the instrument serial number 900F4473 Light Calibration (10 kV, 70 μA and 90 seconds, No filter. Elemental Range: Na, Mg, Al, Si, P,
S, K, Ca, Ti, Cr, Mn, and Fe) were run using 1500 trees with 200
resampling events using k-fold cross valida... |

