- Datasets (source)

Sentinel-1 IW SAFE files: from ASF Vertex, https://search.asf.alaska.edu/

- Software

CSLC-S1 processing: COMPASS https://github.com/opera-adt/COMPASS

Offset-tracking: PyCuAmpcor https://github.com/lijun99/cuAmpcor

Deep learning: TensorFlow's Keras (version 2.13.1; recommended installation with 'pip install tensorflow[and-cuda]==2.13.1')

- Description of Contents (in CC-ResSiamNet_dataset.zip)

select_CSLC-S1_bursts.ipynb: processed OPERA burst IDs in Alaska and plotting

note_download.txt: downloading training/validation/test sets from Box cloud storage

utils.py: necessary python functions

read_dataset.ipynb: jupyter notebook to read datasets for deep learning

- Youtube clip

AI-generated conversations about the findings in the published article to help the public understand (created by NotebookLM).

https://youtu.be/sfOGJBBOrCU

The shapefile represents bottomfast sea ice (BSI) extent in lagoons along the Alaska Beaufort Sea coast during winter and spring, 2017-2021. It was created by digitizing extents from interferograms from the Alaska Satellite Facility Vertex portal. The result is used to identify BSI lateral extent in Arctic lagoons during the growth cycle seasonally. Comparing to future interferograms will identify the trend of BSI within Arctic lagoons. Each feature is attributed with applicable date range and area. Accurate data for the initial growth and maximum extent of BSI could only be collected for the winter and spring months. After the last collection in the spring, there is likely still BSI; however, the surface processes that take place after this point prevent further readings. For early winter time periods, if there are interferograms available (2017 and 2018 data had gaps in interferogram collection as Sentinel-1 was still new), the first date collected can be considered the onset of BSI formation.

Ice cores are collected using a Snow, Ice, and Permafrost Research Establishment (SIPRE) corer and measured for salinity. The data is logged in Excel format following Seasonal Ice Zone Observing Network (SIZONet) practices, making it compatible with the PySIC Python toolkit for analysis.

The auger data identifies key measurements collected from in-situ observations. Data are collected along five surveys and saved as a single CSV file. The data represent a 1-D representation of each auger hole. The data are used to verify satellite interpretations of BSI extent.

The apparent conductivity data includes values at three frequencies (1000 Hz, 4000 Hz, 16000 Hz) recorded during the spring of 2021 in Western Elson Lagoon. Data are saved as an EMI file, which is a CSV format with specific column names and header information. MATLAB scripts to read and interpret data are included in this data package. The apparent conductivity values are used to identify the boundary between floating and bottomfast sea ice. This is an additional survey method used to validate BSI extent interpreted from satellite data.

This is a supporting dataset for Tang et al. (2023), "Oblique blind faulting underneath the Luzon volcanic arc during the 2022 Mw 7.0 Abra earthquake, the Philippines". The original and downsampled line-of-sight displacements for modeling are presented in this repository. The coseismic interferogram using the synthetic aperture radar images from Copernicus Sentinel-1A descending track 32 on 21 July and 2 August, 2022 (6 days before and after the mainshock). The flight direction is ~N190° with a westward look angle ranging from 36° to 45°. Details of processing and downsampling schemes can be found in the paper. The Sentinel-1 images were processed by European Space Agency (ESA) and downloaded from Alaska Satellite Facility (ASF) Data Search Vertex (https://search.asf.alaska.edu/).

This dataset provides seven Sentinel-1 Synthetic Aperture Radar (SAR) scenes covering a portion of the Madeira River in Brazil from Porto Velho to Abuna. Each scene has been pre-processed for the use of detecting artisanal and small-scale mining (ASM) riverine dredges. The scenes were collected from the ASF search vertex (https://search.asf.alaska.edu/#/) as L1 Detected High-Res Dual-Pol (GRD-HD) products. They were acquired using a C-band SAR with the Interferometric Wide Swath (IW) mode, VV and VH polarizations, and a temporal resolution of 6 days. Each SAR acquisition covers a 250 km swath; however, these have been clipped to the study area. They have a 20 m x 22 m (ground range x azimuth) resolution, a 10 m x 10 m pixel spacing, and an Equivalent Number of Looks (ENL) of 4.4. The data is collected in ascending and descending passes; although, only descending passes were available in the study area. Four of the dates (20190604, 20190616, 20190628, and 20190710) required two sce ...

- Datasets (source)

OPERA CSLC-S1: from ASF Vertex, https://search.asf.alaska.edu/

- Software

Deep learning: TensorFlow's Keras (version 2.13.1; recommended installation with 'pip install tensorflow[and-cuda]==2.13.1')

- Description of Contents

dataset_handle.ipynb: jupyter notebook to handle datasets for deep learning

• Includes ~50K training, validation, and test sets.
• ~70GB separate binary files can be downloaded via Box.
• The downloaded files can be reassembled to a single HDF5 file.
• Each set consists of 256×256 reference (non-displaced) and secondary (displaced) amplitude image chips along with x- and y-direction displacements.

"Please if you use this datasets we appreciated that you reference this repository and cite the works related that made possible the generation of this dataset." This change detection datastet has different events, satellites, resolutions and includes both homogeneous/heterogeneous cases. The main idea of the dataset is to bring a benchmark on semantic change detection in remote sensing field.This dataset is the outcome of the following publications:

@article{ JimenezSierra2022graph,author={Jimenez-Sierra, David Alejandro and Quintero-Olaya, David Alfredo and Alvear-Mu{~n}oz, Juan Carlos and Ben{\'i}tez-Restrepo, Hern{\'a}n Dar{\'i}o and Florez-Ospina, Juan Felipe and Chanussot, Jocelyn},journal={IEEE Transactions on Geoscience and Remote Sensing},title={Graph Learning Based on Signal Smoothness Representation for Homogeneous and Heterogeneous Change Detection},year={2022},volume={60},number={},pages={1-16},doi={10.1109/TGRS.2022.3168126}} @article{ JimenezSierra2020graph,title={Graph-Based Data Fusion Applied to: Change Detection and Biomass Estimation in Rice Crops},author={Jimenez-Sierra, David Alejandro and Ben{\'i}tez-Restrepo, Hern{\'a}n Dar{\'i}o and Vargas-Cardona, Hern{\'a}n Dar{\'i}o and Chanussot, Jocelyn},journal={Remote Sensing},volume={12},number={17},pages={2683},year={2020},publisher={Multidisciplinary Digital Publishing Institute},doi={10.3390/rs12172683}} @inproceedings{jimenez2021blue,title={Blue noise sampling and Nystrom extension for graph based change detection},author={Jimenez-Sierra, David Alejandro and Ben{\'\i}tez-Restrepo, Hern{\'a}n Dar{\'\i}o and Arce, Gonzalo R and Florez-Ospina, Juan F},booktitle={2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS},ages={2895--2898},year={2021},organization={IEEE},doi={10.1109/IGARSS47720.2021.9555107}} @article{florez2023exploiting,title={Exploiting variational inequalities for generalized change detection on graphs},author={Florez-Ospina, Juan F and Jimenez Sierra, David A and Benitez-Restrepo, Hernan D and Arce, Gonzalo},journal={IEEE Transactions on Geoscience and Remote Sensing}, year={2023},volume={61},number={},pages={1-16},doi={10.1109/TGRS.2023.3322377}} @article{florez2023exploitingxiv,title={Exploiting variational inequalities for generalized change detection on graphs},author={Florez-Ospina, Juan F. and Jimenez-Sierra, David A. and Benitez-Restrepo, Hernan D. and Arce, Gonzalo R},year={2023},publisher={TechRxiv},doi={10.36227/techrxiv.23295866.v1}} In the table on the html file (dataset_table.html) are tabulated all the metadata and details related to each case within the dasetet. The cases with a link, were gathered from those sources and authors, therefore you should refer to their work as well. The rest of the cases or events (without a link), were obtained through the use of open sources such as:

Copernicus European Space Agency Alaska Satellite Facility (Vertex) Earth Data In addition, we carried out all the processing of the images by using the SNAP toolbox from the European Space Agency. This proccessing involves the following:

Data co-registration Cropping Apply Orbit (for SAR data) Calibration (for SAR data) Speckle Filter (for SAR data) Terrain Correction (for SAR data) Lastly, the ground truth was obtained from homogeneous images for pre/post events by drawing polygons to highlight the areas where a visible change was present. The images where layout and synchorized to be zoomed over the same are to have a better view of changes. This was an exhaustive work in order to be precise as possible.Feel free to improve and contribute to this dataset.

Resumen EL SATÉLITE ALOS: Lanzado en enero del 2006 por la Agencia Japonesa de Exploración Aeroespacial en enero de 2006 y su nombre japonés es "DAICHI". El satélite ALOS durante su operación (mayo 16 de 2006 a abril 22 de 2011), colectó imágenes de Radar en escenas de 50 km x 70 km de todo el planeta cada 45 días aproximadamente a través de su sensor PALSAR (Phased Array Type L-band Synthetic Aperture Radar). DEM ALOS-PALSAR Uno de los productos ofrecidos por Alaska Satellite Facility en el contexto de las imágenes de ALOS Palsar, es el Modelo Digital de Elevación de 12.5 m por pixel. (Ver en https://vertex.daac.asf.alaska.edu/). Para Chile, la cobertura es total. Cada escena mide 85 x 85 km y es posible descargar orbitas ascendentes como descendentes. Se descargaron las escenas y se confeccionaron mosaicos regionales. Para cambiar la altura Geoidal a Nivel medio del mar, se utilizó un modelo Geoidal EGM2008 mundial, que registra las diferencias entre el geoide y en nivel medio del mar, con pixeles de 1 segundo de arco (30 mt). Las diferencias geoidales se le restaron a los valores de altitud del DEM. Por último se recortó el DEM con el límite Regional ODEPA y se exportaron los resultados (15 regiones) al formato JPG2000 en 16 bit y sin decimales. La escala aproximada, definida por el error vertical y por el tamaño del Pixel, es de 1:25.000 Tipo de archivo: Raster en formato GRID.Palabras claves: medio fisico, topografiaAño del archivo: 2016Coordenadas: - norte: 6.355.841,256000- sur: 6.205.191,256000- oeste: 255.600,000000- este: 428.450,000000Autor: Centro de Información de Recursos Naturales (CIREN)Fuente: IDE Chile https://www.ide.cl/descargas/capas/Imagenes/DEM/RM.rar https://www.ide.cl/descargas/capas/Imagenes/DEM/LGBO.rarhttps://www.ide.cl/descargas/capas/Imagenes/DEM/VALPO.rarRestricciones: Dato abierto