Scholar
Ahmad Mustafa
Google Scholar ID: x10e8yQAAAAJ
Machine Learning and Analytics Engineer at Occidental Petroleum
Citations & Impact
Citations
281
H-index
8
i10-index
7
Publications
19
Co-authors
13
list available
Publications
Resume (English only)
Academic Achievements
- Publications: 'Visual Attention-Guided Learning With Incomplete Labels for Seismic Fault Interpretation' accepted for publication in IEEE Transactions on Geoscience and Remote Sensing (TGRS); 'A unified framework for evaluating robustness of Machine Learning Interpretability for Prospect Risking' accepted for publication in Geophysics; 'Explainable Machine Learning for Hydrocarbon prospect Risking' featured in the machine learning special section of the January-February edition of Geophysics. Talks and Courses: Delivered an invited talk titled 'Theory to Practice: AI and ML in Subsurface Exploration' at the SPE Seminar Series at the University of Engineering and Technology, Lahore; Invited to deliver a 2-day short course titled 'Artificial Intelligence for Accelerating Subsurface Characterization: From Theory to Practice' to a team of OGDCL geophysicists at the Oil and Gas Training Institute, Islamabad; Abstract 'Interactive Seismic Facies Segmentation using Multi-Attribute Seismic Data' accepted for a poster presentation at IMAGE 25 Exhibition and Conference.
Research Experience
- Focused on the automatic analysis and interpretation of high-dimensional spatiotemporal image signals, such as those present in migrated 3D seismic volumes (for geophysics exploration) and medical imaging data (for predictive analytics in healthcare). Developed deep learning algorithms for solving multimodal inverse problems in geophysics, accurate segmentation of spatiotemporal image data for subsurface characterization and automatic tumour detection, and addressing domain shift for real-world application of deep models pretrained on synthetic training data. Additionally, researched weakly supervised learning and active learning for accurate semantic segmentation of 2D/3D image signals in sparse label settings.
Education
- PhD in Electrical and Computer Engineering from the Georgia Institute of Technology, supervised by Professor Ghassan AlRegib at the OLIVES lab.
Background
- Machine Learning Researcher with a background in neural networks, joint optimization, uncertainty quantification, domain adaptation, and spatiotemporal image analysis.
Miscellany
- In addition to research engagements, delivered numerous talks and short courses across industry and academic settings and has been involved with numerous research initiatives involving industry and academia. Served as a mentor and advisor to students and early-career researchers, fostering knowledge exchange through technical workshops and industry partnerships. Welcomes collaborations that push the boundaries of AI-driven signal processing, particularly in domains where high-dimensional data and complex physics-based constraints pose unique challenges.
