Life Purpose: With a profound understanding of applied sciences, physics, mathematics, and (generative) AI, I am committed to deciphering the complexities of intricate geophysical data. My mission is to forge strategic partnerships across various disciplines, enabling a comprehensive understanding of natural and industrial processes, and delivering actionable insights to clients
Vision and Impact: Innovation in the energy sector exemplifies human ingenuity and collective effort. It involves creating smarter, more eco-responsible extraction methods, requiring multi-energy development globally, aiming to gradually replace conventional fuels, and using AI-assisted processes to optimize production and storage. My current work is reshaping the pre-industrialization era, fostering a sustainable ecosystem where humanity is responsible for both health and technological advancement.
Developing innovative solutions in image processing and Computer Vision, leveraging TotalEnergies’ High Performance Machine Learning (HPML) environment.
• Computer Vision Frameworks: Expertise in object detection and instance segmentation using YOLO-v8, Detectron2, and TFOD. Proficient in image processing with OpenCV scripting for R&D projects like ARGOS (robotics), MicroDeep (microalgae), Biodiversity (phototraps), and SYRACO (nannofossils).
• Workflow Automation: Streamlined and unified Computer Vision components using the Snakemake workflow management library (Python).
Utilized the Microsoft PyTorch-Wildlife collaborative framework for automated biodiversity labeling.
Conducted database correction and validation with the expertise of specialist ecologists.
Performed extraction, data augmentation, and classification of animal images using YOLOv8-cls Contributed to the preservation and census of animal species near TotalEnergies assets.
• Geological Facies Prediction: Applied Gradient Boosting Decision Trees (GBDT) models to predict geological facies using 3D seismic cubes. Evaluated I/O performance across different file systems.
• Seismic Data Analysis/Processing: Enhanced the internal DIVA seismic toolbox for SEG-Y/SEP data analysis and processing on Pangea-3/4 supercomputers.
• Forecasting flooding for TotalEnergies' Papua LNG project using satellite, AI and in-situ data
Detailed Description
Entity: OneTech/Technical Lines/Data Tech/Scientific Computing/Softwares for Scientific Computing
Company Description
Located in Pau, the Jean Féger Scientific and Technical Center (CSTJF) is a first-rate research and expertise center, a source of great pride for Total's Exploration-Production branch. Equipped with state-of-the-art laboratories and a high performance supercomputer (HPC), the CSTJF offers our Group the scientific expertise and the means of study which make it shine in the oil and gas world