SYSTEM AND METHOD FOR GRADE ESTIMATION USING GRADIENT BOOSTED DECESION TREE BASED MACHINE LEARNING ALGORITHIMS

摘要

#$%^&*AU2020100630A420200604.pdf#####ABSTRACT The present disclosure provides systems and methods for predicting ore grade of given locations that are unknown. The prediction systems and methods described herein can include or leverage one or more machine-learned models that assist in predicting ore grade for any given locations. As an example, in some implementations, the prediction system can include a machine-leamed XGBoost, a machine-learned LightGBM, a machinelearned CatBoost, and/or other machine-learned models. The use of machine-learned models can improve the speed, quality, and/or accuracy of the generated predictions. predictions.6 100 104 104 104 106_ ----- ------------------------------------------- a------- ------- ------- ------1010 I---- ---------------------------------------------- ---------- ------------ ---------------------------------- ------ ---------------------------------- - - - - -106 106 Figure 1. Data olletion200 tuning- - -- - ------------------------ ------------------------------------------------------ /. .. ye-armtr Hyperpnr~-patrameter Figure2.lihtBMW-