Generating land gravity anomalies from satellite gravity observations using PIX2PIX GAN image translation
Generative Adversarial Networks (GANs), specifically the Pix2Pix GAN, are used to effectively map gravity anomalies from satellite to ground, and adapt the Pix2Pix GAN model for large-scale data transformation. The impact of varying patch sizes on model performance is investigated using key metrics...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Applied Computing and Geosciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590197424000521 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850251191704879104 |
|---|---|
| author | Bisrat Teshome Weldemikael Girma Woldetinsae Girma Neshir |
| author_facet | Bisrat Teshome Weldemikael Girma Woldetinsae Girma Neshir |
| author_sort | Bisrat Teshome Weldemikael |
| collection | DOAJ |
| description | Generative Adversarial Networks (GANs), specifically the Pix2Pix GAN, are used to effectively map gravity anomalies from satellite to ground, and adapt the Pix2Pix GAN model for large-scale data transformation. The impact of varying patch sizes on model performance is investigated using key metrics to ensure improved accuracy in gravity anomaly mapping. The model used 2728 satellite, and 2728 ground Bouguer gravity anomaly images from northern and northeast part of Ethiopia. 5456 images were used for training and 552 for testing. The findings indicate that Intermediate patch sizes, particularly 70 x 70 pixels, significantly enhanced model accuracy by capturing global features and contextual information. Additionally, models incorporating L2 loss with LcGAN demonstrated superior performance across qualitative metrics compared to those with L1 loss. The study will contribute to improve geophysical exploration by providing an alternative method that generates more accurate gravity maps, thereby enhancing the precision of geological models and related applications. |
| format | Article |
| id | doaj-art-6741f62fb53a4b96a618d19d4eeb24f0 |
| institution | OA Journals |
| issn | 2590-1974 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Applied Computing and Geosciences |
| spelling | doaj-art-6741f62fb53a4b96a618d19d4eeb24f02025-08-20T01:57:58ZengElsevierApplied Computing and Geosciences2590-19742024-12-012410020510.1016/j.acags.2024.100205Generating land gravity anomalies from satellite gravity observations using PIX2PIX GAN image translationBisrat Teshome Weldemikael0Girma Woldetinsae1Girma Neshir2Addis Ababa Science and Technology University, Department of Software Engineering, EthiopiaAddis Ababa Science and Technology University Department of Mining Engineering, Ethiopia; Corresponding author.Addis Ababa Science and Technology University, Department of Software Engineering, EthiopiaGenerative Adversarial Networks (GANs), specifically the Pix2Pix GAN, are used to effectively map gravity anomalies from satellite to ground, and adapt the Pix2Pix GAN model for large-scale data transformation. The impact of varying patch sizes on model performance is investigated using key metrics to ensure improved accuracy in gravity anomaly mapping. The model used 2728 satellite, and 2728 ground Bouguer gravity anomaly images from northern and northeast part of Ethiopia. 5456 images were used for training and 552 for testing. The findings indicate that Intermediate patch sizes, particularly 70 x 70 pixels, significantly enhanced model accuracy by capturing global features and contextual information. Additionally, models incorporating L2 loss with LcGAN demonstrated superior performance across qualitative metrics compared to those with L1 loss. The study will contribute to improve geophysical exploration by providing an alternative method that generates more accurate gravity maps, thereby enhancing the precision of geological models and related applications.http://www.sciencedirect.com/science/article/pii/S2590197424000521Gravity anomalyPix2Pix GANGAN and image-to-image translation |
| spellingShingle | Bisrat Teshome Weldemikael Girma Woldetinsae Girma Neshir Generating land gravity anomalies from satellite gravity observations using PIX2PIX GAN image translation Applied Computing and Geosciences Gravity anomaly Pix2Pix GAN GAN and image-to-image translation |
| title | Generating land gravity anomalies from satellite gravity observations using PIX2PIX GAN image translation |
| title_full | Generating land gravity anomalies from satellite gravity observations using PIX2PIX GAN image translation |
| title_fullStr | Generating land gravity anomalies from satellite gravity observations using PIX2PIX GAN image translation |
| title_full_unstemmed | Generating land gravity anomalies from satellite gravity observations using PIX2PIX GAN image translation |
| title_short | Generating land gravity anomalies from satellite gravity observations using PIX2PIX GAN image translation |
| title_sort | generating land gravity anomalies from satellite gravity observations using pix2pix gan image translation |
| topic | Gravity anomaly Pix2Pix GAN GAN and image-to-image translation |
| url | http://www.sciencedirect.com/science/article/pii/S2590197424000521 |
| work_keys_str_mv | AT bisratteshomeweldemikael generatinglandgravityanomaliesfromsatellitegravityobservationsusingpix2pixganimagetranslation AT girmawoldetinsae generatinglandgravityanomaliesfromsatellitegravityobservationsusingpix2pixganimagetranslation AT girmaneshir generatinglandgravityanomaliesfromsatellitegravityobservationsusingpix2pixganimagetranslation |