Poster
in
Workshop: AI for Accelerated Materials Design (AI4Mat-2023)
Rapid Fitting of Band-Excitation Piezoresponse Force Microscopy Using Physics Constrained Unsupervised Neural Networks
Alibek T Kaliyev · Shuyu Qin · Yichen Guo · Seda Memik · Michael Mahoney · Amir Gholami · Nhan Tran · Martin Takac · Joshua Agar
Keywords: [ machine learning ] [ ferroelectric switching ] [ simple harmonic oscillator ] [ real-time analysis ] [ robust fitting ] [ scanning probe spectroscopy ] [ Unsupervised Learning ] [ Deep Learning ]
Scanning probe spectroscopy generates high-dimensional data that is difficult to analyze in real time, hindering researcher creativity. Machine learning techniques like PCA accelerate analysis but are inefficient, sensitive to noise, and lack interpretability. We developed an unsupervised deep neural network constrained by a known empirical equation to enable real-time, robust fitting. Demonstrated on band-excitation piezoresponse force microscopy, our model fits cantilever response to a simple harmonic oscillators more than 4 orders of magnitude faster than least squares while enhancing robustness. It performs well on noisy data where conventional methods fail. Quantization-aware training enables sub-millisecond streaming inference on an FPGA, orders of magnitude faster than data acquisition. This methodology broadly applies to spectroscopic fitting and provides a pathway for real-time control and interpretation.