A novel fusion Python application of data mining techniques to evaluate airborne magnetic datasets.

A novel fusion python application of data mining techniques (DMT) was designed and implemented to locate, identify, and delineate the subsurface structural pattern (SSP) of source rocks for the features of interest underlain the study area. The techniques of machine learning tools (MLT) helped to define magnetic anomaly source (MAS) rock and the various depths of these subsurface source rock features. The principal objective is to use straightforward DMT to locate magnetic anomaly features of interest that host mineralization. The required geo-referenced radiometric data, which facilitated the delineation of SSP, were sufficiently covered by combining the application of the Oasis Montaj\c{opyright} 2014 source parameter imaging functions. Relevance basic filtering techniques of data reduction were used to improve the signal-to-noise (S/N) ratio and hence automatically determine depths to the various engrossed features from gridded geo-referenced airborne magnetic datasets before the DMT application was performed. Geological source rock models (GSRM) (i.e., rock contacts, dykes) served as the delineated features based on their structural index (SI) values. The anomalies were perpendicularly oriented, with few inconsequential nonvertical features, and all were generally aligned in NNE-SSW and NE-SW directions. The DMT approach showed that magnetic anomaly patterns (MAP) control the SSP and the ground surface stratigraphy (GSS) on a geological time-scale (GTS) by fusing the subsurface gravitational structural features (SGSF) in the area. The DMT facilitated the determination of depths to these subsurface geological source rock features with a maximum depth of approximately 1.277 km using a 3x3 window size to map the concealed features of interest.