Fundamental research in ML & Optimization
Developing novel ML algorithms with embedded statistical constraints for AI guardrails and contextualization.
Scale Lab — Systems, Computing & Analytics Lab for Engineering
How can we design safe and domain-consistent AI systems that accelerate the transition to net‑zero, sustainable industries, and resilient societies?
Based at the intersection of chemical engineering, AI, and optimization, Scale Lab develops systems-level methods to embed domain knowledge and statistical guarantees in machine learning and decision-making pipelines. We focus on net‑zero power and process systems, digital manufacturing, and data-centric sustainability applications.
Led by Dr Waqar Muhammad Ashraf, we combine machine learning, optimization, and domain-consistent modelling to build robust analytics and decision architectures for energy, environment, and climate action. Our work spans algorithm design, real industrial deployments, and human-in-the-loop AI for trustworthy engineering systems.
You can explore a subset of our activities on the following pages: Projects, Publications, Softwares, and the Team.
Featured
Research Areas
Generative Design & autonomous Control
Foundation models and multi-agent systems with autonomous control and experimental workflows for energy, health and environmental applications.
Digital Manufacturing
Cyber physical digital manufacturing systems with digital twin functionalities for smart factories.
AI for sustainability and Climate action
AI for environmental forecasting, early warning systems and climate resilience to contribute to UN sustainable development goals.