Processing of Noisy Controlled Source Audio Magnetotelluric (CSAMT) Data

• Main Author: Fridlund, Julia
• Format: Bachelor Thesis
• Language: English
• Published: Uppsala universitet, Geofysik 2019
• Subjects: CSAMT; noise; magnetotelluric transfer functions; robust processing; transients; bias; brus; magnetotelluriska överföringsfunktioner; robust processering; transienter; Geophysics; Geofysik; Brus; Kiruna
• Online Access: http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-396255

Controlled Source Audio Magnetotellurics (CSAMT) is a geophysical method for characterizing the resistivity of the subsurface with the help of electromagnetic waves. The method is used for various purposes, such as geothermal- and hydrocarbon exploration, mineral prospecting and for investigation of groundwater resources. Electromagnetic fields are created by running an alternating current in a grounded electric dipole and by varying the frequency, different depths can be targeted. Orthogonal components of the electromagnetic fields are measured at receiver stations a few kilometers away from the source. From these field components, so called magnetotellurics transfer functions are estimated, which can be used to invert for the resistivity of the subsurface. The data used in this project is from a survey conducted in 2014 and 2016 in Kiruna by Uppsala University and the mining company LKAB. Measurements were made at 31 stations along two orthogonal profiles. The data have been processed earlier, but due to noise, especially in the lower frequencies, a significant part of the data set could not be inverted. The aim of this project was to improve the results by analyzing the data and testing different methods to remove noise. First, robust regression was used to account for possible non-Gaussian noise in the estimation of the magnetotelluric transfer functions. Except for one station on profile 1, the robust method did not improve the results, which suggests that the noise is mostly Gaussian. Then modified versions of least squares, each affected by a different bias, were used to estimate the transfer functions. Where there is more noise, the estimates should differ more due to their different biases. The estimates differed most for low frequencies and especially on the part of profile 2 that was measured in 2014. It was investigated whether the railway network could explain part of the low frequency noise. Measures were taken to reduce spectral leakage from the railway signal at 16 ⅔ Hz to the closest transmitter ...