Dan Sui

Dan Sui is a Professor in the Department of Energy and Petroleum Engineering at the University of Stavanger, within the Faculty of Science and Technology. His research is centered on drilling automation, digitalization, artificial intelligence, machine learning, data analytics, modeling, optimization, and control systems in petroleum and geothermal energy contexts.

His research interests span drilling automation, AI, machine learning, data processing, modeling, optimization, simulation, control system design (including model predictive control, PID, Kalman filters), advanced drilling technologies, drilling event detection, geothermal drilling, and digital twin development. He actively contributes to the development of smart drilling systems and data-driven models for real-time decision support.

The recent publications (2020–2025) highlight a strong trend in applying reinforcement learning, deep learning, and data-driven modeling to drilling optimization, ROP prediction, well path design, and subsea control. These works are published in high-impact journals such as SPE Journal, Journal of Petroleum Science and Engineering, and Applied Sciences, as well as in proceedings from ASME and IADC/SPE conferences, indicating a strong presence in both petroleum and mechanical engineering domains.

• Automatic calibration of directional drilling control
• Multi-agent reinforcement learning for waterflooding
• PI controller tuning using Deep Q-Learning
• Safe operating envelope for directional drilling
• Neural network optimization for ROP prediction
• Real-time ROP trend analysis
• Well path optimization with Bezier curves
• Anti-collision trajectory design
• Automated drilling algorithms on lab rigs
• Subsea shuttle tanker depth control

While no specific scientific awards are listed, his extensive publication record and involvement in AI and digital twin projects reflect significant recognition in the field. He advises students and collaborates on research involving laboratory-scale drilling automation systems, hybrid test environments, and smart drilling robots, contributing to both theoretical and applied advancements. His work includes development of algorithms for autonomous drilling agents, feature selection for kick detection, and experimental studies on drillstring dynamics.

Dan Sui is a key contributor to the OpenLab project, a modern drilling digitalization infrastructure, and leads research in data quality improvement, downhole data correction, and sensor data reconstruction using recurrent neural networks. His lab-based work includes designing autonomous small-scale drilling rigs and testing machine learning algorithms for incident detection, showcasing a strong integration of experimental and computational research.