Djamel Ouzzane
Papers
2
Total Citations
36
H-Index
2
About
Djamel Ouzzane is a pioneering researcher at the intersection of machine learning, geophysics, and planetary science, whose work redefines how we quantify and understand fluid dynamics in complex natural systems. His primary research areas include computational geodynamics, porous media physics, and AI-driven 3D vision for planetary surveillance. Ouzzane’s major contributions center on two groundbreaking studies: his "Morphology Decoder" (2021, 19 citations) introduces a machine learning-guided 3D vision framework that revolutionizes the quantification of heterogeneous rock permeability, replacing computationally expensive Lattice Boltzmann simulators with a faster, more accurate approach for nano- and micropore networks. This work has profound implications for robotic functions and planetary exploration. In parallel, his "Understanding of Intertwined Physics" (2021, 17 citations) resolves a long-standing challenge by demonstrating the co-determination of capillary pressure and permeability, revealing that knowing one property directly yields the other—a breakthrough that transforms our grasp of fluid distribution in nature. Ouzzane’s research not only advances fundamental geodynamics but also equips autonomous systems with the tools to analyze subsurface environments on Earth and other planets, marking him as a visionary in AI-driven Earth and planetary sciences.
Research Focus
Key Achievements
Top Papers
- 1
- 2