Software
Software and examples
Title of Dataset: WabInSAR source code and example.
The WabInSAR incorporates GMTSAR, GAMMA and advanced InSAR processing algorithms using MATLAB. The source code for processing ALOS data acquired in Path 172 over Timpson area is provided. The link above also includes all generated interferograms as well as intermediate results obtained from applying various filtering steps to this data set. The raw data can be obtained from Alaska Satellite Facilities.
The current version of WabInSAR used for handling Timpson data set is adapted to use GAMMA for performing SLC co-registration and interferogram generation. To acquire the version compatible with GMTSAR as well as any other questions contact the author at shirzaei@vt..edu.
Read through these guidelines before processing. This is not a set of instructions to generate perfect deformation signals or times series. The user must adjust parameters and code as needed to obtain usable results. This guide is meant to aid the user with reasonable knowledge of InSAR and MATLAB programming and it not comprehensive.
If end up using WabInSAR code and subroutines cite the following publications;
Shirzaei, M. and T. R. Walter (2011). "Estimating the Effect of Satellite Orbital Error Using Wavelet-Based Robust Regression Applied to InSAR Deformation Data." Ieee Transactions on Geoscience and Remote Sensing 49(11): 4600-4605.
Shirzaei, M. and R. Bürgmann (2012). "Topography correlated atmospheric delay correction in radar interferometry using wavelet transforms." Geophysical Research Letters 39(1): doi: 10.1029/2011GL049971.
Shirzaei, M. and R. Bürgmann (2013). "Time-dependent model of creep on Hayward fault inferred from joint inversion of 18 years InSAR time series and surface creep data." J. Geophys. Res. Solid Earth 118( 1733–1746): doi:10.1002/jgrb.50149.
Shirzaei, M. (2013). "A Wavelet-Based Multitemporal DInSAR Algorithm for Monitoring Ground Surface Motion." Ieee Geoscience and Remote Sensing Letters 10(3): 456-460.
Title of Dataset: AI source code and example for unsupervised deformation hotspot extraction.
The set of programs can be used for post-processing InSAR deformation maps obtained from multi-temporal InSAR processing.
Input: Time series deformation matrix in .mat format (exported from WabInSAR software developed by Manoochehr Shirzaei). WabInSAR software is open access and can be downloaded from the following link: https://sites.google.com/vt.edu/eadar-lab/software
Output: Cluster maps based on time series k-means, dbscan, followed by codes to remove unwanted clusters and merge clusters.
If you end up using this code, cite the following publication;
Tiwari, A. and Shirzaei, M., 2024. A novel machine learning and deep learning semi-supervised approach for automatic detection of InSAR-based deformation hotspots. International Journal of Applied Earth Observation and Geoinformation, 126, p.103611.