Amr Misbah

Deep Learning-based Auto Accident Detection and Alert System for Vehicles

Amr Misbah, Shanid Malayil, Murshida. K.P, Mohammed Binshad et autres

The increasing number of vehicles, especially in urban areas, has led to a rise in traffic violations and accidents. In India, accidents are a leading cause of death, with over 75% of fatalities resulting from the inability to provide prompt assistance. To …

Inversion-based multistage seismic data processing with physics-driven priors

Rajiv Kumar, Y.I. Kamil, Phillip Bilsby, Anu Narayan et autres

Abstract Various aspects of survey design have a profound impact on how noise appears on the coherent signal of interest, thus impacting conventional inversion methods in complex environments. We propose a multistage physics-driven prior-based processing technique that is versatile and can be …

Seismic Image Improvements after Correction for Errors in Obn Acquisition Parameters

E. Muijzert, Claudio Bagaini, Amr Misbah, Nigel Seymour et autres

Summary Uncertainties in acquisition parameters of Ocean Bottom Node data impact image quality. In this study we consider spatial and temporal variations in water velocity and source positions as well node positions and clock drift. Our method inverts the direct arrival travel …

vg (code pays fourni par la source)

Effects of dimensionality of transform domain on multiple stages source separation with prior

Rajiv Kumar, Yousif Izzeldin Kamil Amin, Araz Mahdad, Phillip Bilsby et autres

We illustrate the advantages of deblending a simultaneous source acquisition with a multiple stages source separation with prior approach using higher dimensional transform domain. With such approach, multiple stages progressively build the coherent signal model while eliminating the associated interference noise in …

vg (code pays fourni par la source)

Robust multistage separation of simultaneous sources using priors: Challenges and strategies

Yousif Izzeldin Kamil Amin, Rajiv Kumar, Araz Mahdad, Phillip Bilsby et autres

We proposed a multistage source separation technique that progressively models the primary signal while eliminating the interference in a signal safe manner (Kamil et al., 2021, Robust multistage separation of simultaneous sources using priors, abstract submitted to EAGE). Different sparsity promoting prior …

vg (code pays fourni par la source)

Machine-Learning-Driven Dispersion Curve Picking for Surface-Wave Analysis, Modelling, and Inversion

Anisha Kaul, Phillip Bilsby, Amr Misbah, Aria Abubakar

Summary The quality of onshore seismic data is strongly affected by the characteristics of the near surface. To compensate for the distortion of travel times of seismic energy, workflows have been formulated to analyse, model, and invert surface waves. This approach requires …

vg (code pays fourni par la source)

Inherent Challenges of Randomized Shooting Strategies on Deblending and a Robust Multistage Prior Based Solution

Rajiv Kumar, Y.I. Kamil Amin, Araz Mahdad, A. Narayan et autres

Summary We show the importance of designing a shooting pattern such as flip-flip, which makes the interference noise appear randomly and well distributed over the coherent signal of interest, thus, complementing the coherency-based source separation framework. We then illustrate the challenges posed …

vg (code pays fourni par la source)

Robust Multistage Separation of Simultaneous Sources Using Priors

Y.I. Kamil, Rajendra Kumar, Araz Mahdad, Ananth Ravi Narayan et autres

Summary We propose a multistage prior-based source-separation technique that progressively models the source-separated signal while eliminating the interference in a signal-safe manner. Different sparsity-promoting prior information are utilised in this framework to distinguish signal from blending noise in the transform domain at …

vg (code pays fourni par la source)

Detecting the fundamental mode of energy for surface wave analysis, modelling, and inversion, using a deep convolutional network

Anisha Kaul, Aria Abubakar, Amr Misbah, Phillip Bilsby

The quality of onshore seismic data is strongly affected by the characteristics of the near surface. To compensate for the distortion of travel times of seismic energy, workflows have been formulated to analyse, model, and invert surface waves. This approach requires human-intensive …

vg (code pays fourni par la source)

Joint estimation of modal attenuation and velocity from multichannel surface wave data

Amr Misbah, Claudio Luciano Strobbia

ABSTRACT We evaluated a method for the simultaneous analysis of velocity and attenuation of multichannel surface wave data. It allowed us to estimate the phase velocity and attenuation curves using an array of receivers, possibly unevenly spaced, and a set of multiple …

vg, us, fr (code pays fourni par la source)