There are the Supplementary Materials for the article, which is cited as "Zhang, P., Zhang, Z., Yang, J., Cheng, Q., 2022. Machine Learning Prediction of Ore Deposit Genetic Type Using Magnetite Geochemistry. Natural Resources Research. https://doi.org/10.1007/s11053-022-10146-4".
Detailed descriptions are as follows: Supplementary Material 1: Table S1. LA–ICP‒MS trace element compositions of magnetite from published literature. Supplementary Material 2: Table S2. Processed LA–ICP‒MS data used to build the model, Table S3. The training data in the study. Supplementary Material 3: Table S4. Electron probe microanalysis (wt.%) of magnetite from the Makeng and Luoyang Fe deposits. Supplementary Material 4: Table S5. LA–ICP‒MS trace element compositions of magnetite from the Makeng and Luoyang Fe deposits. Supplementary Material 5: Analytical methods, Figure S1 (Electron microscope images of magnetite from the Makeng and Luoyang deposits), Figure S2 (Learning curve of the RF, SVM and MLP algorithm), Figure S3(Magnetite trace element concentrations for different deposit types (without removing outliers)), Figure S4 (Confusion matrices of the validation set (without removing outliers)), Table S6 (All hyperparameters in the models and the optimal values), Table S7 (Classification report for the RF and SVM classifiers (without removing outliers)). Supplementary Material 6: Zip file with an executable program (Magnetite_Classifier), Table S8 (Test set data for Chuquicamata porphyry deposit), Table S9 (Test set data for Kalatonke magmatic Cu-Ni sulfide deposit), Table S10 (Test set data for the Makeng deposit), Table S11 (Test set data for the Luoyang deposit).