Traditional least-squares full-waveform inversion (FWI) suffers from severe local minima problems in the case of presence strongly dispersive surface waves. In addition, recorded wavefields are often characterized by amplitude errors due to varying source coupling and incorrect 3D-to-2D geometric-spreading correction. Thus, FWI is considered less suitable for near-surface applications. We intro...

Wildfires are a natural phenomenon, which nowadays, due to the synergistic effect of increased human intervention and escalation climate change, displaying an ever-increasing intensity frequency. The underlying mechanisms present complexity, with phenomenon itself being characterized by significant degree stochasticity. For above reasons, machine learning models neural networks implemented. In ...

Full waveform inversion (FWI) requires an accurate estimation of source signatures. Due to the coupling between signatures and subsurface model, small errors in former can translate into large latter. When direct methods are used solve forward problem, classical frequency-domain FWI efficiently processes multiple sources for signature wavefield estimations once a single Lower-Upper (LU) decompo...

A robust misfit function is essential for mitigating cycle-skipping in full-waveform inversion (FWI), leading to stable updates of the velocity model this highly nonlinear optimization process. State-of-the-art functions, including matching filter or optimal transport misfits, are all hand-crafted and developed from first principles. With growth artificial intelligence geoscience, we propose le...

We present a generalized workflow to retrieve high-resolution P-wave velocity ( $V_{ P}$ ) models of complex Earth's subsurface structures from traditional marine near-vertical seismic reflection experiments. These records have typically offsets too short map refraction phas...

Abstract The density structure of firn has implications for hydrological and climate modelling ice shelf stability. can be evaluated from depth models seismic velocity, widely obtained with Herglotz-Wiechert inversion (HWI), an approach that considers the slowness refracted arrivals. However, HWI is appropriate only steady-state profiles accuracy compromised where contains layers. In these case...

Conventional gradient-based full waveform inversion (FWI) is a local optimization, which highly dependent on the initial model and prone to trapping in minima. Globally optimal FWI that can overcome this limitation particularly attractive, but currently limited by huge amount of calculation. In paper, we propose globally framework based GPU parallel computing, greatly improves efficiency, expec...

Most fire protection agencies throughout the world have developed forest fire risk forecast systems, usually building upon existing fire danger indices and meteorological forecast data. In this context, the daily predictability of wildfires is of utmost importance in order to allow the fire protection agencies to issue timely fire hazard alerts. In this study, we address the predictability of d...