Position Overview:
Mohammed VI Polytechnic University (UM6P) invites applications for a highly qualified Postdoctoral Researcher to join our research initiative focusing on the integration of Artificial Intelligence (AI) in Chemical Process Systems Engineering (CPSE). The position addresses key challenges in process intensification, sustainability, and advanced process control, aiming to develop AI-driven frameworks for multi-scale modeling, multi-objective optimization, and predictive control of complex chemical and biochemical processes.
The research will contribute to next-generation smart manufacturing systems, aligned with Industry 4.0 paradigms, and target applications in sustainable energy production, green chemistry, circular economy, and carbon capture, utilization and storage (CCUS).
Scientific Challenges Addressed in the Position:
- Non-linear and dynamic system modeling of chemical processes involving complex thermodynamics and transport phenomena.
- Optimization under uncertainty and robust decision-making for process design and operational strategies.
- Integration of first-principles (mechanistic) models with data-driven models (hybrid modeling) for improved accuracy and generalization.
- Development of real-time optimization algorithms and model predictive control (MPC) strategies for adaptive process management.
- Addressing data sparsity and data quality issues in industrial process data streams for reliable AI model training.
- Design of digital twins for process monitoring, fault diagnosis, and predictive maintenance in chemical plants.
Key Responsibilities:
- Create and implement hybrid AI models that merge machine learning techniques with mechanistic frameworks (like physics-informed neural networks and grey-box modeling) to enable predictive simulations of chemical and biochemical processes.
- Construct multi-objective optimization frameworks (Pareto optimization) to evaluate trade-offs among economic, energy efficiency, and environmental performance metrics.
- Utilize reinforcement learning (RL) and deep reinforcement learning (DRL) for autonomous process management, dynamic resource distribution, and real-time decision-making.
- Design and deploy digital twins for integrated chemical processes for virtual commissioning and optimization.
- Examine extensive heterogeneous data sets (including historical process data, sensor data, and laboratory findings) using advanced AI approaches such as unsupervised learning, transfer learning, and anomaly detection.
- Collaborate with process engineers and experimentalists to validate models, demonstrate them at pilot scales, and transfer technology to industry partners.
- Share research results through peer-reviewed publications, conference talks, and patent filings when relevant.
- Oversee graduate students and support capacity building in AI for CPSE at UM6P.
Required Qualifications:
- Ph.D. in Chemical Engineering, Process Systems Engineering, Artificial Intelligence, Data Science, or a related discipline.
- Proven experience in process modeling (steady-state and dynamic) using simulation software such as Aspen Plus, gPROMS, or COMSOL Multiphysics.
- Solid understanding of process control strategies, including model predictive control (MPC), nonlinear control, and optimal control theory.
- Proficiency in programming languages (Python, MATLAB) and experience with AI/ML frameworks (TensorFlow, PyTorch, Scikit-learn).
- Experience in data-driven modeling, deep learning, and reinforcement learning algorithms applied to chemical processes.
- Track record of scientific publications in peer-reviewed journals in AI, chemical engineering, or process systems engineering.
- Excellent communication skills and ability to collaborate in multidisciplinary and international teams.
Application Process:
Candidates are invited to submit the following documents (compiled in a single PDF):
- A cover letter outlining their research vision, motivation, and relevant experiences.
- A comprehensive Curriculum Vitae (CV) including a list of publications and any patents.
- Contact details of two academic referees.
