摘要
Synchrotron tomography experiments are transitioning into multifunctional,cross-scale,and dynamic characterizations,enabled by new-generation synchrotron light sources and fast developments in beamline instrumentation.However,with the spatial and temporal resolving power entering a new era,this transition generates vast amounts of data,which imposes a significant burden on the data processing end.Today,as a highly accurate and efficient data processing method,deep learning shows great potential to address the big data challenge being encountered at future synchrotron beamlines.In this review,we discuss recent advances employing deep learning at different stages of the synchrotron tomography data processing pipeline.We also highlight how applications in other data-intensive fields,such as medical imaging and electron tomography,can be migrated to synchrotron tomography.Finally,we provide our thoughts on possible challenges and opportunities as well as the outlook,envisioning selected deep learning methods,curated big models,and customized learning strategies,all through an intelligent scheduling solution.
基金
This work was funded by the National Science Foundation for Young Scientists of China(grant 12005253)
the Strategic Priority Research Program of the Chinese Academy of Sciences(XDB 37000000)
the Innovation Program of the Institute of High Energy Physics,CAS(E25455U210)
the Hefei Science Center,Chinese Academy of Sciences(award 2019HSC-KPRD003).All authors gratefully acknowledge support from the BL13HB and BL16U2 beamlines of the Shanghai Synchrotron Radiation Facility(SSRF)and BL07W beamline of the National Synchrotron Radiation Laboratory(NSRL)。
