KAUST Ph.D. student Zhaolun Liu won the best student presentation at the 2017 Society of Exploration Geophysicists (SEG) Full-Waveform Inversion (FWI) and Beyond Workshop in Beijing. Liu's presentation was on "3D Wave-Equation Dispersion Inversion of Surface Waves," based on a paper co-authored with Jing Li and Professor Gerard Schuster. The paper describes a new method called wave equation dispersion inversion (WD) for inverting surface waves. Why it matters: This award recognizes KAUST's contributions to geophysics and seismic imaging, highlighting the university's research capabilities and access to high-performance computing.
KAUST researchers have developed a detailed 3D dynamic model using data from the February 2023 Turkiye earthquake to improve earthquake simulations. The model incorporates 3D fault geometry and Earth structure for realistic simulations of ground shaking. It explains complex ground shaking patterns and the impact of supershear ruptures, which can amplify damage far from the epicenter. Why it matters: This research provides a more accurate understanding of earthquake rupture processes, crucial for seismic hazard assessment and infrastructure planning in seismically active regions like the Middle East.
KAUST and Cerebras Systems collaborated on multi-dimensional seismic processing using the Condor Galaxy AI supercomputer, achieving record sustained memory bandwidth of 92.58 petabytes per second. They developed a Tile Low-Rank Matrix-Vector Multiplication (TLR-MVM) kernel to exploit the architecture of Cerebras CS-2 systems. This work was recognized as a finalist for the 2023 Gordon Bell Prize. Why it matters: This demonstrates the potential of AI-customized architectures for seismic processing, with broader implications for climate modeling and other scientific domains in the region and globally.
KAUST researchers from statistics and earth science collaborated to improve earthquake source modeling. They developed a statistical ranking tool to classify 2D fields, applicable to geoscience models like temperature or precipitation. The tool helps compare different 2D fields describing the earthquake source process and quantify inter-event variability. Why it matters: This cross-disciplinary approach enhances the reliability of earthquake rupture models, contributing to better hazard assessment and risk management in seismically active regions.
KAUST Professor Wolfgang Heidrich is researching computational imaging systems that jointly design optics and image reconstruction algorithms. He focuses on hardware-software co-design for imaging systems with applications in HDR, compact cameras, and hyperspectral imaging. Heidrich's work on HDR displays was the basis for Brightside Technologies, acquired by Dolby in 2007. Why it matters: This research aims to advance imaging technology through AI-driven design, potentially impacting various fields from consumer electronics to scientific research within the region and globally.
KAUST researchers have developed an AI system for the Saudi Geological Survey (SGS) to improve the scientific understanding of seismic activity in Saudi Arabia. The AI system helps the SGS analyze swarm earthquakes, which are common in volcanic regions and difficult to decipher using conventional methods. The system allows for a more reliable survey of seismic regions, better infrastructure planning, and improved building codes. Why it matters: The AI system enhances Saudi Arabia's ability to monitor and respond to seismic events, contributing to public safety and infrastructure resilience.
KAUST held the Imaging and Active Tectonics of the Red Sea Region workshop, gathering over 20 international and 30 local researchers. The workshop aimed to improve understanding of seismicity, volcanism, and Earth structure in Saudi Arabia and the Red Sea region. Participants came from countries surrounding the Red Sea, as well as the US, UK, France, Brazil, and South Korea. Why it matters: The event fosters international collaboration and data exchange to better monitor and model seismic and volcanic activity in a geologically active region.
Pascal Fua from EPFL presented an approach to implementing convolutional neural nets that output complex 3D surface meshes. The method overcomes limitations in converting implicit representations to explicit surface representations. Applications include single view reconstruction, physically-driven shape optimization, and bio-medical image segmentation. Why it matters: This research advances geometric deep learning by enabling end-to-end trainable models for 3D surface mesh generation, with potential impact on various applications in computer vision and biomedical imaging in the region.