Tanaka Kenya, Hachiya Kengo, Zhang Wenjin, Matsuda Kazunari, Miyauchi Yuhei
Institute of Advanced Energy , Kyoto University , Gokasho, Uji, Kyoto 611-0011 , Japan.
ACS Nano. 2019 Nov 26;13(11):12687-12693. doi: 10.1021/acsnano.9b04220. Epub 2019 Oct 14.
We demonstrate the applicability of employing machine-learning-based analysis to predict the low-temperature exciton valley polarization landscape of monolayer tungsten diselenide (1L-WSe) using position-dependent information extracted from its photoluminescence (PL) spectra at room temperature. We performed low- and room-temperature polarization-resolved PL mapping and used the obtained experimental data to create regression models for the prediction using the Random Forest machine-learning algorithm. The local information extracted from the room-temperature PL spectra and the low-temperature exciton valley polarization was used as the input and output data for the machine-learning process, respectively. The spatial distribution of the exciton valley polarization in a 1L-WSe sample that was not used for the learning of the decision trees was successfully predicted. Furthermore, we numerically obtained the degree of importance for each input variable and demonstrated that this parameter provides helpful information for examining the physics that shape the spatially heterogeneous valley polarization landscape of 1L-WSe.
我们展示了利用基于机器学习的分析方法，通过从室温下的单层二硒化钨（1L-WSe）光致发光（PL）光谱中提取的位置相关信息，来预测其低温激子谷极化态势的适用性。我们进行了低温和室温下的偏振分辨PL映射，并使用获得的实验数据，通过随机森林机器学习算法创建用于预测的回归模型。从室温PL光谱中提取的局部信息和低温激子谷极化分别用作机器学习过程的输入和输出数据。成功预测了未用于决策树学习的1L-WSe样品中激子谷极化的空间分布。此外，我们通过数值方法获得了每个输入变量的重要程度，并证明该参数为研究塑造1L-WSe空间异质谷极化态势的物理过程提供了有用信息。
