Nader Shakibay Senobari
Nader Shakibay Senobari
Research Scientist (AI, Time Series & Earthquake Physics)
Research Scientist (AI, Time Series & Earthquake Physics)
Embedded Files
Hello!
Hello!
I am an interdisciplinary researcher and educator working at the intersection of artificial intelligence, computer science, and earth sciences. My core expertise — and greatest passion — lies in algorithm design and creative problem solving, which I apply to both fundamental research and real-world challenges such as earthquake detection, stress monitoring, and hazard forecasting.
I am an interdisciplinary researcher and educator working at the intersection of artificial intelligence, computer science, and earth sciences. My core expertise — and greatest passion — lies in algorithm design and creative problem solving, which I apply to both fundamental research and real-world challenges such as earthquake detection, stress monitoring, and hazard forecasting.
Most recently, I taught Introduction to Artificial Intelligence at UC Riverside, gaining hands-on experience with a broad range of AI methods, including machine learning, deep learning, and data-driven modeling. Combined with my research background, this has given me a strong command of both the theoretical foundations and practical applications of AI.
Most recently, I taught Introduction to Artificial Intelligence at UC Riverside, gaining hands-on experience with a broad range of AI methods, including machine learning, deep learning, and data-driven modeling. Combined with my research background, this has given me a strong command of both the theoretical foundations and practical applications of AI.
I hold a Ph.D. in Geophysics from UC Riverside, where I focused on earthquake physics and seismic time-series analysis, and a B.S. in Physics, which gave me a rigorous foundation in mathematics, computational thinking, and problem solving. Throughout my career, I have built interdisciplinary collaborations across computer science, engineering, and earth science — developing novel approaches for time-series clustering, anomaly discovery, inverse modeling, and interpretable machine learning.
I hold a Ph.D. in Geophysics from UC Riverside, where I focused on earthquake physics and seismic time-series analysis, and a B.S. in Physics, which gave me a rigorous foundation in mathematics, computational thinking, and problem solving. Throughout my career, I have built interdisciplinary collaborations across computer science, engineering, and earth science — developing novel approaches for time-series clustering, anomaly discovery, inverse modeling, and interpretable machine learning.
I am currently in transition and open to opportunities where I can contribute my expertise in AI, algorithms, and data science while continuing to build bridges between disciplines.
I am currently in transition and open to opportunities where I can contribute my expertise in AI, algorithms, and data science while continuing to build bridges between disciplines.
🚨 New Research Highlight
I am excited to share our latest work, “Remotely sensing stress evolution in solids: a passive approach to earthquake monitoring,” now available on arXiv:2509.00268.
In this study, we introduce a stress-sensitive transformation of seismic noise that reveals systematic pre-earthquake signatures not captured by existing methods. If validated across broader datasets and settings, this approach could represent a game-changing advance in earthquake physics and geophysics, opening a new pathway for passively tracking stress evolution in the Earth’s crust.
I encourage researchers in seismology, geophysics, acoustics, and related fields to read, test, challenge, and build upon this work.
Tracking Cascadia slow-slip events with the Shakibay-Senobari stress-sensitive frequency-domain transform.
The top panel shows GPS motion and seismic tremor during episodic tremor and slip (ETS) events beneath southern Vancouver Island (2010–2013), highlighting the timing of slow-slip initiation and termination.
The lower panels show the Shakibay-Senobari stress-sensitive frequency-domain transform (SS_f) computed from continuous seismic noise. Between ETS events, SS_f evolves smoothly as stress accumulates along the fault, followed by a rapid drop and recovery during slow slip. This behavior captures the full loading–release–relaxation cycle and complements GPS and tremor observations.
For methodological details and additional case studies, see Shakibay-Senobari (2025), “Remotely sensing stress evolution in solids: a passive approach to earthquake monitoring,” arXiv:2509.00268.
curriculum vitae:
curriculum vitae:
CV_NSS_2026.pdfPage updated
Google Sites
Report abuse