ABSTRACT Frequency-domain thermoreflectance (FDTR) is a popular technique to investigate thermal properties of bulk and thin film materials. The FDTR data analysis involves fitting experimental data to a theoretical model whose accuracy may be affected by improper fitting approach and by convergence to local minima. This work proposes a novel data analysis approach using deep learning techniques. The developed deep learning model for FDTR (DL-FDTR) can accurately predict thermal conductivity, volumetric heat capacity and thermal boundary conductance with mean error below 5% for bulk samples coated with Au. DL-FDTR predictions can serve as an initial guess to the traditional fitting algorithms and can efficiently avoid local minima with regular fitting options, therefore improving the accuracy of data fitting and uncertainty evaluation.

中文翻译：

---

通过深度学习重新考虑频域热反射测量和新数据分析的不确定性

摘要 频域热反射 (FDTR) 是研究大块和薄膜材料热性能的流行技术。FDTR 数据分析涉及将实验数据与理论模型拟合，该理论模型的准确性可能会受到拟合方法不当和收敛到局部最小值的影响。这项工作提出了一种使用深度学习技术的新型数据分析方法。开发的 FDTR 深度学习模型 (DL-FDTR) 可以准确预测热导率、体积热容和热边界电导率，对于涂有 Au 的大块样品，平均误差低于 5%。DL-FDTR 预测可以作为传统拟合算法的初始猜测，并且可以通过常规拟合选项有效地避免局部最小值，从而提高数据拟合和不确定性评估的准确性。