Abstract: Due to its single molecule sensitivity, high-resolution Atomic Force Microscopy (HR-AFM) has proved to be a valuable and uniquely advantageous tool to study complex mixtures, such as petroleum, biofuels/chemicals, and environmental samples. However, significant challenges remain in order to achieve the full potential of the challenging and time-consuming experiments. Automated HR-AFM, in conjunction with machine learning and artificial intelligence, will be the key to overcoming many bottlenecks today, and crucial for research on solutions for the energy transition and environmental sustainability. We showcase first “autonomously acquired” results on petroleum-based mixtures with potential for novel carbon-based composite materials for applications in infrastructures. These are the early steps towards fully autonomous HR-AFM imaging along with a master plan to expand our AI and computer vision based approach further to include all essential steps starting from sample approach, exploration, tip functionalization to molecule selecting and imaging in HR-AFM mode. Our AI steered image “appearance” optimization fine adjusts the sample probe distance. The process we have implemented is using a state machine, computer vision and AI (CNN) for decision making.
Biography: Dr. Percy Zahl is currently leading the Low Temperature (LT) STM and NC-AFM/HR-AFM facility at CFN and providing world-class expertise for HR-AFM imaging together with all related experimental services and operating the microscope. He is always open to new ideas and establishing new collaborations. For over 20 years he has been project manager and lead programmer of GXSM, an open source SPM (and more) control software. GXSM provides a DSP + FPGA hardware based data acquisitions and instrument control platform, and is a widely-used SPM control solution with easily accessible and commercial available hardware running non-proprietary and user-accessible software. Dr. Zahl also provides online support and help with custom projects.
