Geoscience and Remote Sensing

Remote sensing of environment research has explored the benefits of using synthetic aperture radar imagery systems for a wide range of land and marine applications since these systems are not affected by weather conditions and therefore are operable both daytime and nighttime. The design of image processing techniques for  synthetic aperture radar applications requires tests and validation on real and synthetic images. The GRSS benchmark database supports the desing and analysis of algorithms to deal with SAR and PolSAR data.

Last Updated On: 
Tue, 02/08/2022 - 17:46
Citation Author(s): 
Nobre, R. H.; Rodrigues, F. A. A.; Rosa, R.; Medeiros, F.N.; Feitosa, R., Estevão, A.A., Barros, A.S.

Radial basis function (RBF) is a basis function suitable for scattered data interpolation and high dimensional function interpolation, wherein the independent shape parameters have a direct impact on the accuracy of calculation results. Research in this field is mostly concerned with the shape parameter selection strategy based on the premise of global distribution or block regional distribution. In this paper, a shape parameter selection strategy is proposed, which is used for the local RBF collocation method (LRBF) for solving partial differential equations.


This dataset contains 6 raw ground-penetrating radar (GPR) profiles (#9, #10, #11, #14, #25, #30) collected at 4 locations in the Wahiba Sands dune field of Oman in May of 2014. The survey was performed to assess the detectability of the water table within the first 100 meters in hyper-arid sandy formations by VHF sounding radar. Profiles #9-10-11 are three parts of the same track ascending a ~36-m tall dune, and used to assess the maximum GPR penetration depth at which the water table is still detectable.


We propose a coupled physics-driven and data-driven algorithm to improve standard deep learning workflow. In order to evaluate the proposed method, a 2.5D geological model including dip, fault and anisotropic formation is considered.  Comparing the inversion imaging performance of the proposed physics-driven method with the traditional classical residual network (Resnet), it shows a significant improvement in resistivity accuracy.


Algorithm for automating conceptual urban planning work


Contains latitude and longitude, attributes and ID.


Development of the Complex-Valued (CV) deep learning architectures has enabled us to exploit the amplitude and phase components of the CV Synthetic Aperture Radar (SAR) data. However, most of the available annotated SAR datasets provide only the amplitude information (Only detected SAR data) and disregard the phase information. The lack of high-quality and large-scale annotated CV-SAR datasets is a significant challenge for developing CV deep learning algorithms in remote sensing.


Radio Frequency (RF) signals transmitted by Global Navigation Satellite Systems (GNSS) are exploited as signals of opportunity in many scientific activities, ranging from sensing waterways and humidity of the terrain to the monitoring of  the ionosphere. The latter can be pursued by processing the GNSS signals through dedicated ground-based monitoring equipment, such as the GNSS Ionospheric Scintillation and Total Electron Content Monitoring (GISTM) receivers.


The theoretical data  sets are used in the synthetic tests in the manuscript and supplementary materials calculated by the models.


Thermal infrared (IR) environmental satellite data assimilation and remote sensing of the surface and lower troposphere depend on accurate specification of the spectral surface emissivity within clear-sky forward calculations. Over ocean surfaces, accurate modeling of surface-leaving radiances over the sensor scanning swaths is complicated by a quasi-specular bidirectional reflectance distribution function (BRDF).