Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines)

Machine learning methods that have been used in data-driven predictive modeling of mineral prospectivity (e.g., artificial neural networks) invariably require large number of training prospect/locations and are unable to handle missing values in certain evidential data. The Random Forests (RF) algorithm, which is a machine learning method, has recently been applied to data-driven predictive mapping of mineral prospectivity, and so it is instructive to further study its efficacy in this particular field. This case study, carried out using data from Abra (Philippines), examines (a) if RF modeling can be used for data-driven modeling of mineral prospectivity in areas with few (i.e., <20) mineral occurrences and (b) if RF modeling can handle evidential data with missing values. We found that RF modeling outperforms weights-of-evidence (WofE) modeling of porphyry-Cu prospectivity in the Abra area, where 12 porphyry-Cu prospects are known to exist. Moreover, just like WofE modeling, RF modeling allows analysis of the spatial associations of known prospects with individual layers of evidential data. Furthermore, RF modeling can handle missing values in evidential data through an RF-based imputation technique whereas in WofE modeling values are simply represented by zero weights. Therefore, the RF algorithm is potentially more useful than existing methods that are currently used for data-driven predictive mapping of mineral prospectivity. In particular, it is not a purely black-box method like artificial neural networks in the context of data-driven predictive modeling of mineral prospectivity. However, further testing of the method in other areas with few mineral occurrences is needed to fully investigate its usefulness in data-driven predictive modeling of mineral prospectivity.