Norah Alsunaidi
Petroleum Engineering Systems Analyst
Saudi Aramco
Norah Alsunaidi is a Petroleum Engineering Systems Analyst at Saudi Aramco’s Upstream Digital Center, with over seven years of experience supporting digital transformation for Unconventional Resources. In her current role, she bridges business needs with digital technologies to enhance decision-making and operational efficiency.
She holds a Bachelor’s degree in Computer Science and is pursuing a Master of Science at King Fahd University of Petroleum & Minerals, where her research explores leveraging deep learning techniques to advance renewable energy forecasting applications. Alsunaidi has authored and presented several
technical works at leading industry conferences and journals. Her research interests center on applying artificial intelligence to address real-world challenges in the energy sector.
Beyond her technical contributions, Alsunaidi is eager to empower othersthrough sharing knowledge and experiences. She is actively involved in talent and capability development, mentoring undergraduate students at Imam Abdulrahman Bin Faisal University through the Saudi Aramco Student Career
Mentorship program in which she provides her mentees with personalized guidance to support their professional development. In addition, she is the founder and author of Kafu Leaders, an Arabic weekly newsletter dedicated to leadership development and demystifying artificial intelligence for the wider
audience.
Participates in
TECHNICAL PROGRAMME | Energy Technologies
Despite the efforts directed toward adopting machine learning algorithms to address upstream challenges, the prospect of leveraging quantum machine learning (QML) to address these challenges has not been widely investigated. Based on the predictions, the advancement of the current computational powers will reach a plateau. As the hardware capacity determines the limit of what a machine can learn, this work highlights the potential of maximizing the exploitation of machine learning by adopting QML in various upstream cases.
Novelty
Quantum machine learning is an evolving field that utilizes quantum computing to perform machine learning algorithms. Employing quantum computing as a processing platform adds an advantage to machine learning due to the nature of quantum computing that employs subatomic particles for computation. This permits capitalizing on the properties of quantum mechanics phenomena such as superposition, entanglement, and quantum interference.
Methodology
This work sheds light on the feasibility of adapting QML technologies in various oil and gas cases that require computational complexity based on the current status of art. Through a comprehensive analysis of the theoretical concept of quantum computing, we provide an overview focusing on quantum machine learning and its various types and implementation. In addition, we highlight the key difference between the proposed approach to utilize quantum analogs with the current machine learning applications employed in the oil and gas industry, analyzing the gained advantage and the burden of adoption.
Results
Many of the proposed quantum algorithms remain a theoretical concept due to the unavailability of a stable large-scale quantum computer capable of accommodating the execution cost. Although the challenge of producing a stable quantum computer persists at the present time, researchers have discovered that several quantum algorithms, including quantum machine learning algorithms, are compatible with noisy intermediate-scale quantum computers (NISQ), which will be available in the near future. The potential for quantum machine learning is not limited to an extended speedup, but it also includes enhancing the generalization of machine learning algorithms, so that a machine is more likely to operate effectively with the new inputs of a given environment. These advanced capabilities can be harnessed to elevate the challenges and complexity of hydrocarbon plays; therefore, we encourage more exploration in this field tailored to the special requirements of the oil and gas industry since the development in the field of quantum machine learning can set forth a new generation of solutions. This will help with resolving long-standing issues beyond the limitation of existing processing power to advance upstream processes toward optimal operational excellence.
