KUNLING · Intelligent Numerical Geoscience

AI for a connected Earth.

We connect intelligent agents, physical simulation, global marine data, and scientific visualization to study our planet across space and deep time.

Explore our research Meet the team

06Research directions

AI × PhysicsOne connected workflow

OUCQingdao · China

Scroll to explore

Our research position

AI should reason with the Earth—not just fit its data.

KUNLING develops AI-native methods for Earth science and ocean geology. We connect scientific agents, physical simulation, domain knowledge, data processing, visualization, and evaluation so that AI can support rigorous research workflows—not only fit models to geoscience data.

01ReasonAgents and knowledge

02SimulatePhysics and computation

03RevealData and visualization

From scientific question → physical evidence → reproducible insight

Research Together✦Create Together✦Share Together✦Research Together✦Create Together✦Share Together✦

Research constellation

Six directions. One connected Earth.

Each project begins with a scientific question and connects algorithms to physical evidence, numerical systems, and interpretable output.

Explore all research →

01AI Co-Scientist Environment for Geodynamics

TectonOS

A harness for AI-assisted geodynamic research.

Harness EngineeringScientific AgentsASPECT · LaMEM · goSPL

02Global Lithosphere Inversion

GLTitan

Reconstructing global lithospheric thickness through deep time.

Neural operatorsTransformersGeophysical inversion

03Deep Earth–Climate Feedback

Ridge–Climate Coupling

Tracing links between sea level, mid-ocean ridges, and climate.

DSDP · ODP · IODPMultimodal learningTime-series analysis

04Life–Earth Representation

Eco-Transformer

Learning ecological change across the last 21,000 years.

TransformersSelf-supervised learningBiogeography

05Accelerated Geodynamics

Physics-guided AI Earth Simulator

A next-generation simulator for geodynamic evolution.

Neural operatorsJEPA · TransformersDiffusion models · PINNs

06Scientific Visual Intelligence

AI-native Geoscience Visualization

From raw Earth data to publication-quality scientific figures.

GMT · PyGMT · ParaViewPython · C++CUDA · OpenGL · Vulkan

Principal investigator

Scientific questions first.

PIOUC · MOE Key Lab

Principal Investigator · Associate Professor

Ze Liu

Ocean University of China · Key Lab of Submarine Geosciences and Prospecting Techniques, MOE

Dr. Ze Liu develops intelligent numerical methods for marine geology and deep-time Earth system science. His work combines multiscale numerical modeling, machine learning, and data assimilation to reconstruct paleogeomorphology and paleoenvironmental change.

Multiscale numerical modelingCross-sphere Earth system interactionsIntelligent data assimilationDeep-time reconstruction

Official profile ↗liuze@ouc.edu.cn

Open research