Xin Li
Texas A&M University-College Station, TX·Engineering
Coastal storms erode beaches and raise flood risk. Predicting that damage requires knowing the bathymetry, the shape of the seafloor, just offshore.
- Fields
Engineering
Earth & Environmental Science
Computer Science
- Topics
nearshore processes
bathymetry
surf zone
- Grants
- 1 known grant, through Sep 2029
What they work on
- Develop physics-informed neural networks, AI models constrained by wave mechanics, that estimate nearshore bathymetry, waves and currents simultaneously from optical and lidar images of the surf zone.
- Estimate subsurface flows, including wave orbital velocities and undertow, from surface observations alone using the PRAM modeling system.
- Validate the PRAM system at multiple coastal field sites and use it to study wave breaking, wave asymmetry in the inner surf zone, and how wave forcing drives seafloor change.
More about the research
That shape is hard and expensive to measure, especially during storms, when boats and divers cannot safely enter the surf. This collaborative project develops artificial intelligence (AI) tools that estimate the underwater beach shape, the waves and the currents directly from remotely sensed images of the sea surface.
Why it matters
Accurate, affordable estimates of nearshore seafloor shape, waves and currents could help federal agencies, coastal engineers and local planners predict beach erosion during storms. They could also support the design of coastal defenses. This would benefit vulnerable shoreline communities, infrastructure and ecosystems, and avoids sending crews into hazardous surf.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Jonghyun Lee
University of Hawaii at Manoa, HI·Earth & Environmental Science
Build hybrid surrogate models from neural operators, networks that imitate expensive simulations, coupled through an open-source framework so groundwater–ocean exchange is simulated quickly while conserving mass at the land–sea boundary.
George Bebis
University of Nevada-Reno, NV·Computer Science
Develop a physics-informed conditional generative deep learning framework that infers underground fracture network geometry and hydraulic properties from hydraulic and tracer tomography data.
Roummel Marcia
University of California-Merced, CA·Mathematics & Statistics
Extend deep unrolling networks for signal recovery and image reconstruction by training them with quasi-Newton optimization methods that exploit previous iterates and gradients.
The school
Texas A&M University-College Station: 23 labs on PI Pages, $1.4B a year on research, 768 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.