首页|Study Findings from Lawrence Berkeley National Laboratory Advance Knowledge in M achine Learning (Prediction of the Cu oxidation state from EELS and XAS spectra using supervised machine learning)
Study Findings from Lawrence Berkeley National Laboratory Advance Knowledge in M achine Learning (Prediction of the Cu oxidation state from EELS and XAS spectra using supervised machine learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
A new study on artificial intelligence is now available. According to news reporting from the Lawrence Berkeley Nation al Laboratory by NewsRx journalists, research stated, "Electron energy loss spec troscopy (EELS) and X-ray absorption spectroscopy (XAS) provide detailed informa tion about bonding, distributions and locations of atoms, and their coordination numbers and oxidation states." Financial supporters for this research include U.S. Department of Energy. The news journalists obtained a quote from the research from Lawrence Berkeley N ational Laboratory: "However, analysis of XAS/EELS data often relies on matching an unknown experimental sample to a series of simulated or experimental standar d samples. This limits analysis throughput and the ability to extract quantitati ve information from a sample. In this work, we have trained a random forest mode l capable of predicting the oxidation state of copper based on its L-edge spectr um. Our model attains an R 2 score of 0.85 and a root mean square error of 0.24 on simulated data. It has also successfully predicted experimental L-edge EELS s pectra taken in this work and XAS spectra extracted from the literature. We furt her demonstrate the utility of this model by predicting simulated and experiment al spectra of mixed valence samples generated by this work."
Lawrence Berkeley National LaboratoryC yborgsEmerging TechnologiesMachine Learning
NETL
NSTL
