Salem Alzaabi
Papers
2
Total Citations
12
H-Index
2
About
Salem Alzaabi is a researcher at the forefront of planetary exploration and high-performance computing, specializing in 3D image analysis and machine learning. His major contribution is the development of the **3D Adapted Random Forest Vision (3DARFV)** framework, a novel approach that challenges the dominance of deep learning in semantic segmentation. Alzaabi’s work directly addresses the computational bottlenecks of processing massive 3D datasets from planetary missions, where lengthy processing times and high energy consumption are critical constraints. By demonstrating that a carefully optimized random forest can exceed deep learning efficiency and accuracy, his research offers a more sustainable and practical solution for untangling heterogeneous rock fabrics in extraterrestrial environments. His most-cited paper on this topic has garnered 8 citations, with a related work receiving 4, signaling growing interest in his alternative methodology. Alzaabi’s contributions are particularly notable for their potential to accelerate real-time analysis on rovers and orbiters, reducing reliance on power-hungry neural networks. His work represents a significant step toward making autonomous planetary exploration both faster and more energy-efficient.
Research Focus
Key Achievements
Top Papers
- 1
- 2