Geomagnetic Survey Interpolation with the Machine Learning Approach
This work addresses interpolation challenges in geomagnetic surveys using UAV data, but it is incremental as it builds on a basic algorithm with minor enhancements.
The paper tackles the problem of interpolating UAV magnetometry survey data, which is characterized by linear spatial sampling, and achieves an interpolation error of less than 5% by augmenting the Nearest Neighbors algorithm with a machine learning approach.
This paper portrays the method of UAV magnetometry survey data interpolation. The method accommodates the fact that this kind of data has a spatial distribution of the samples along a series of straight lines (similar to maritime tacks), which is a prominent characteristic of many kinds of UAV surveys. The interpolation relies on the very basic Nearest Neighbours algorithm, although augmented with a Machine Learning approach. Such an approach enables the error of less than 5 percent by intelligently adjusting the Nearest Neighbour algorithm parameters. The method was pilot tested on geomagnetic data with Borok Geomagnetic Observatory UAV aeromagnetic survey data.