zhoulab

Dr. Yi-Qiao Song Visit WIPM

time:   2017-08-31 00:00    hits:6428

In August 31, 2017, Doctor Yi-Qiao Song visited Wuhan Institute of Physics and Mathematics (WIPM), Chinese Academy of Sciences at the invitation of Professor Xin Zhou and gave us an academic report entitled "Porous Media, Magnetic Resonance and Machine Learning" in the 22nd Tianjuan Spectrum Forum of WIPM. Prof. Xin Zhou, vice director of WIPM presided over the forum. Director Maili Liu presented Dr. Song with the letter of appointment and nameplate of "Tianjuan Spectrum Forum Chair Professor".

Dr. Song graduated from Peking University and got the Ph.D. at Northwestern University. After that, he worked as a postdoctoral fellow at the University of California, Berkeley. He is a scientific advisor at Schlumberger-Doll Research in Cambridge MA and also works part-time at Martinos Center of Biomedical Imaging of Massachusetts General Hospital. He is also a fellow of American Physical Society, and a member of the Editorial Board of Journal of Magnetic Resonance.Dr. Song has published nearly a hundred papers in established journals, such as Nature, Science, PRL, JMR, etc.His research involves development of nuclear magnetic resonance and imaging techniques and instrumentation to understand complex materials and fluids. His interest focuses on the physics of diffusion dynamics in porous media and biological tissues and the development of multi-dimensional experimental methods and numerical inversion algorithms. These multi-dimensional experiments have been broadly used in research and industrial applications. One of his current areas of interest is the Bayesian theory, uncertainty, and machine learning as a means to optimize NMR/MRI data acquisition in real time in order to enhance the speed and quality of the experiments and for robust/automated applications.

Porous media is widely found in nature. Wood, soil, rocks are porous media. Exploring the nature of these mediais of great significanceon life and environmental science research area. Dr. Song first introduced the porous media. Then he introduced the process of oil extraction, how to use multi-dimensional experiments to distinguish between oil and water, the relationship between the diffusion coefficient of the same substance and the molecular weight, the non-Gaussian diffusion of porous mediacombined with NMR method. Subsequently, Dr. Song introduced a miniaturized low field NMR spectrometer used in oil exploration. The magnet of the spectrometer is permanent magnet, and the signal transmission, reception and processing circuits are all integrated in a chip. In the experimental algorithm, Dr. Song introduced the machine learning. For multi-parameter experiments such as NMR, an algorithm was designed to predict the parameters required for the next experiment by analyzing the results of the previous experiment, and the exact data fitting results can be obtained after several iterations.

The participants show great interest in Dr. Song's report, and they had warm discussions with Dr. Song on some academic topics.