Application of Machine Learning in Mineral Mapping Using Remote Sensing

The machine learning is an effective approach toward acquiring patterns on voluminous data popularly termed big data. Remote sensing is one such field that can be employed with the ML concepts to ascertain solutions to several environmental problems. With the raw spatial data captured by the sensors like LANDSAT, meaningful insights can be drawn adhering to the specifics of the arena. The images are captured in the form of electromagnetic waves often termed as spectral signatures based on the reflectance properties of elements on the earth’s surface. The paper intends to showcase the relevance of machine learning concepts pertaining to a specific area of application in geosciences with the identification of potential mineral mapping areas as the key objective. To derive the most appropriate results, the key indicators on the earth’s surface are focused where the dataset is band mapped with multispectral data. The spectral resolution is a key concept that provides an unambiguous picture of mineral spectra across the spectral regions. The image classification provides the classifiers which can be further accurately assessed to determine the several regions including vegetation, soil, and water. The paper intends to delve into the intricacies of remote sensing as an effective tool of data capturing in the form of spectral signatures and the role of machine learning algorithms for effective geospatial analysis to derive regions of exploration interest with extensive scrutiny of work under the study arena.