Haifa Alyazeedi
Papers
2
Total Citations
12
H-Index
2
About
Haifa Alyazeedi is a researcher at the forefront of applying high-performance computing and machine learning to planetary science and geospatial image analysis. Her work centers on developing novel computer vision techniques to process and interpret complex 3D image data—critical for autonomous planetary exploration and remote sensing. Alyazeedi’s major contribution is the creation of the **3D Adapted Random Forest Vision (3DARFV)** framework, which challenges the prevailing dominance of deep learning in semantic segmentation. Her research demonstrates that a carefully optimized random forest approach can not only match but exceed the accuracy of deep neural networks while dramatically reducing computational cost and energy consumption. This breakthrough addresses a key bottleneck in space exploration: the need for efficient, real-time analysis of heterogeneous rock fabrics and terrain from orbiters or rovers. Her most-cited paper on this method has accumulated over a dozen citations, signaling growing interest in her resource-efficient alternative to deep learning. By bridging high-performance computing with machine learning, Alyazeedi is paving the way for faster, more sustainable analysis of planetary surfaces—a vital step toward enabling autonomous decision-making in future missions to the Moon, Mars, and beyond.
Research Focus
Key Achievements
Top Papers
- 1
- 2