ONE DIMENSIONAL MAGNETOTELLURIC DATA INVERSION MODELING USING CONVOLUTIONAL NEURAL NETWORK
The magnetotelluric method is a geophysical method commonly used to map subsurface resistivity. The subsurface’s true resistivity is generated by inversion of the magnetotelluric data. This study tries to invert one-dimensional magnetotelluric data using one of the machine learning methods, the c...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/65673 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| id |
id-itb.:65673 |
|---|---|
| spelling |
id-itb.:656732022-06-24T11:16:50ZONE DIMENSIONAL MAGNETOTELLURIC DATA INVERSION MODELING USING CONVOLUTIONAL NEURAL NETWORK Iqbal Khatami, Muhammad Indonesia Final Project convolutional neural network, inversion, magnetotelluric INSTITUT TEKNOLOGI BANDUNG https://digilib.itb.ac.id/gdl/view/65673 The magnetotelluric method is a geophysical method commonly used to map subsurface resistivity. The subsurface’s true resistivity is generated by inversion of the magnetotelluric data. This study tries to invert one-dimensional magnetotelluric data using one of the machine learning methods, the convolutional neural network, which is heavily inspired by the human nervous system. This method has been tested on synthetic data with curves of type A, H, K, and Q contaminated with noise. The inversion results show that the convolutional neural network model could approach the actual resistivity values and patterns with a fairly small error and exceptionally fast computation time without initial model guess and iteration. text |
| institution |
Institut Teknologi Bandung |
| building |
Institut Teknologi Bandung Library |
| continent |
Asia |
| country |
Indonesia Indonesia |
| content_provider |
Institut Teknologi Bandung |
| collection |
Digital ITB |
| language |
Indonesia |
| description |
The magnetotelluric method is a geophysical method commonly used to map
subsurface resistivity. The subsurface’s true resistivity is generated by inversion of
the magnetotelluric data. This study tries to invert one-dimensional magnetotelluric
data using one of the machine learning methods, the convolutional neural network,
which is heavily inspired by the human nervous system. This method has been tested
on synthetic data with curves of type A, H, K, and Q contaminated with noise. The
inversion results show that the convolutional neural network model could approach
the actual resistivity values and patterns with a fairly small error and exceptionally
fast computation time without initial model guess and iteration. |
| format |
Final Project |
| author |
Iqbal Khatami, Muhammad |
| spellingShingle |
Iqbal Khatami, Muhammad ONE DIMENSIONAL MAGNETOTELLURIC DATA INVERSION MODELING USING CONVOLUTIONAL NEURAL NETWORK |
| author_facet |
Iqbal Khatami, Muhammad |
| author_sort |
Iqbal Khatami, Muhammad |
| title |
ONE DIMENSIONAL MAGNETOTELLURIC DATA INVERSION MODELING USING CONVOLUTIONAL NEURAL NETWORK |
| title_short |
ONE DIMENSIONAL MAGNETOTELLURIC DATA INVERSION MODELING USING CONVOLUTIONAL NEURAL NETWORK |
| title_full |
ONE DIMENSIONAL MAGNETOTELLURIC DATA INVERSION MODELING USING CONVOLUTIONAL NEURAL NETWORK |
| title_fullStr |
ONE DIMENSIONAL MAGNETOTELLURIC DATA INVERSION MODELING USING CONVOLUTIONAL NEURAL NETWORK |
| title_full_unstemmed |
ONE DIMENSIONAL MAGNETOTELLURIC DATA INVERSION MODELING USING CONVOLUTIONAL NEURAL NETWORK |
| title_sort |
one dimensional magnetotelluric data inversion modeling using convolutional neural network |
| url |
https://digilib.itb.ac.id/gdl/view/65673 |
| _version_ |
1822004922486358016 |