Efficient and accurate Technology Computer-Aided Design simulations with machine learning and their application to develop monolithic CMOS sensors for

Complementary Metal-Oxide-Semiconductor (CMOS) is one of the most popular commercial processes to fabricate integrated circuits such as image sensors, memories and microprocessors, which constitute the backbone of everyday devices like smartphones and tablets. CMOS is also an extremely attractive option for producing silicon sensors which are essential for measuring charged particles in physics experiments that create extremely challenging environments.

A key aspect in the R&D phase towards a new CMOS sensor is the ability to anticipate the performance of the device before its expensive and time-consuming fabrication, which is typically achieved with Technology Computer-Aided Design (TCAD) simulations. Unfortunately, TCAD simulations are computationally very expensive. This limits the accuracy and scope of the simulations that can be done to guide the design of a CMOS sensor, and often results in suboptimal devices and longer and more expensive R&D programmes.

In this project we propose to develop machine learning methods for fast and accurate TCAD simulations in a commercial CMOS process, and to apply the developed methods to guide the design of a real CMOS sensor tailored to the demands of physics experiments. The project entails collecting training data from relevant TCAD simulations, exploring various neural-network models, and identifying the most promising one to train and develop a machine learning model.

The student will use the developed machine learning framework to run fast and accurate TCAD simulations to inform the design of a cutting-edge monolithic CMOS sensor with fast-timing, and evaluate the fabricated device in the laboratory and potentially also at test beams with particles at DESY and/or CERN.

The student will work as an integral part of the Liverpool ATLAS group, helping in the development of the operational procedures for, and making the first system-level performance evaluation of, the UK pixel endcap detector. They will contribute to an intense programme of testing that will be needed to ensure that the delivered endcap performs to the stringent specifications.

This testing and evaluation will include the first measurements of the performance of pixel quad modules in their final configurations. Key to this work will be the development of an analysis framework which is tightly coupled with the production