Preprints

Filtering by Subject: Signal Processing

Model Ensemble with Dropout for Uncertainty Estimation in Binary Sea Ice or Water Segmentation using Sentinel-1 SAR

Rafael Pires de Lima, Morteza Karimzadeh

Published: 2024-01-19
Subjects: Applied Statistics, Environmental Monitoring, Signal Processing

Despite the growing use of deep learning in sea ice mapping with SAR imagery, the study of model uncertainty and segmentation results remains limited. Deep learning models often produce overconfident predictions, a concern in sea ice mapping where misclassification can impact marine navigation safety. We incorporate and compare dropout and model ensemble within a convolutional neural network [...]

Adaptive Finetuning of 3D CNNs with Interpretation Uncertainty for Seismic Fault Prediction

Ahmad Mustafa, Ghassan AlRegib, Reza Rastegar

Published: 2023-06-20
Subjects: Geophysics and Seismology, Signal Processing

3D CNNs can exploit the full extent of spatial information in seismic volumes to predict faults. They require large quantities of training data, but this issue has been mitigated by training such networks with large amounts of synthetic training data to apply afterwards on real datasets. Because of domain shift, pre-trained networks may fail to perform as expected, emphasizing the need to [...]

Range Geolocation Accuracy of C-/L-Band SAR and Its Implications for Operational Stack Coregistration

Zhang Yunjun, Heresh Fattahi, Xiaoqing Pi, et al.

Published: 2022-04-22
Subjects: Geophysics and Seismology, Signal Processing

Time series analysis of synthetic aperture radar (SAR) and interferometric SAR generally starts with coregistration for the precise alignment of the stack of images. Here we introduce a model-adjusted geometrical image coregistration (MAGIC) algorithm for stack coregistration. This algorithm corrects for atmospheric propagation delays and known surface motions using existing models and ensures [...]

Eavesdropping at the speed of light: distributed acoustic sensing of baleen whales in the Arctic

Léa Bouffaut, Kittinat Taweesintananon, Hannah Joy Kriesell, et al.

Published: 2022-03-22
Subjects: Marine Biology, Physical Sciences and Mathematics, Signal Processing

In a post-industrial whaling world, flagship and charismatic baleen whale species are indicators of the health of our oceans. However, traditional monitoring methods provide spatially and temporally undersampled data to evaluate and mitigate the impacts of increasing climatic and anthropogenic pressures for conservation. Here we present the first case of wildlife monitoring using distributed [...]

Evaluating Short-Term Spatio-Temporal Tropospheric Variability in Multi-Temporal SAR Interferograms Using LES Models

Fengming Hu, Ramon Hanssen, Pier Siebesma, et al.

Published: 2021-07-13
Subjects: Aerospace Engineering, Atmospheric Sciences, Computational Engineering, Earth Sciences, Fluid Dynamics, Longitudinal Data Analysis and Time Series, Meteorology, Multivariate Analysis, Signal Processing

Atmospheric delay has a significant impact on synthetic aperture radar (SAR) interferometry, inducing spatial phase errors and decorrelation in extreme weather condition. For Low Earth Orbit (LEO) SAR missions, the atmosphere can be considered as being spatio-temporally frozen due to the short integration time. Geosynchronous (GEO) SAR missions, however, have short revisit times and extensive [...]

Distributed Acoustic Sensing for Near Surface Imaging from Submarine Telecommunication Cable: Case Study in the Trondheim Fjord

Kittinat Taweesintananon, Martin Landrø, Jan Kristoffer Brenne, et al.

Published: 2021-05-13
Subjects: Geophysics and Seismology, Geotechnical Engineering, Signal Processing, Systems and Communications

Distributed acoustic sensing (DAS) transforms submarine telecommunication cables into densely sampled seismic receivers. To demonstrate DAS applications for seismic imaging, we use an optical cable on the seafloor in the Trondheim Fjord, Norway, to record seismic data generated by a controlled seismic source. The data are simultaneously recorded by a towed hydrophone array and the fiber optic [...]

Detecting Ground Deformation in the Built Environment using Sparse Satellite InSAR data with a Convolutional Neural Network

Nantheera Anantrasirichai, Juliet Biggs, Krisztina Kelevitz, et al.

Published: 2020-05-13
Subjects: Earth Sciences, Electrical and Computer Engineering, Engineering, Other Earth Sciences, Physical Sciences and Mathematics, Signal Processing

The large volumes of Sentinel-1 data produced over Europe are being used to develop pan-national ground motion services. However, simple analysis techniques like thresholding cannot detect and classify complex deformation signals reliably making providing usable information to a broad range of non-expert stakeholders a challenge. Here we explore the applicability of deep learning approaches by [...]

Measuring Azimuth Deformation With L-Band ALOS-2 ScanSAR Interferometry

Cunren Liang, Eric Jameson Fielding

Published: 2020-04-06
Subjects: Aerospace Engineering, Civil and Environmental Engineering, Computational Engineering, Computer Engineering, Earth Sciences, Electrical and Computer Engineering, Engineering, Geology, Geomorphology, Geophysics and Seismology, Glaciology, Hydrology, Mining Engineering, Other Earth Sciences, Physical Sciences and Mathematics, Signal Processing, Tectonics and Structure, Volcanology

We analyze the methods for measuring azimuth deformation with the L-band Advanced Land Observing Satellite-2 (ALOS-2) scanning synthetic aperture radar (ScanSAR) interferometry. To implement the methods, we extract focused bursts from the ALOS-2 full-aperture product, which is the only product available for ScanSAR interferometry at present. The extracted bursts are properly processed to measure [...]

Redshift of Earthquakes via Focused Blind Deconvolution of Teleseisms

Pawan Bharadwaj, Chunfang Meng, Aimé Fournier, et al.

Published: 2019-10-13
Subjects: Applied Mathematics, Earth Sciences, Electrical and Computer Engineering, Engineering, Geophysics and Seismology, Physical Sciences and Mathematics, Signal Processing

We present a robust factorization of the teleseismic waveforms resulting from an earthquake source into signals that originate from the source and signals that characterize the path effects. The extracted source signals represent the earthquake spectrum and its variation with azimuth. Unlike most prior work on source extraction, our method is data-driven, and it does not depend on any [...]

  • 1 
search

You can search by:

  • Title
  • Keywords
  • Author Name
  • Author Affiliation