Lee Mark, Piper Robert T, Bhandari Bishal, Hsu Julia W P
Department of Physics, University of Texas at Dallas, Richardson, Texas 75080, United States.
Department of Materials Science and Engineering, University of Texas at Dallas, Richardson, Texas 75080, United States.
ACS Appl Nano Mater. 2023 Oct 2;6(19):17364-17368. doi: 10.1021/acsanm.3c03599. eCollection 2023 Oct 13.
Optimizing the spin coating of silver nanowires to form transparent conducting electrodes (TCE) is guided by machine learning (ML). A good TCE has two competing characteristics: high transmittance and high conductance. Optimization using a scalar figure of merit, as often done in the field, cannot satisfy the independent requirements for transmittance and conductance imposed by specific applications. By performing a Pareto front analysis based on ML models, we show that the desired outcomes of transmittance ≥ 75% and sheet resistance ≤ 15 Ω/sq are challenging but can be achieved using processing parameters identified by ML analysis.
利用机器学习指导银纳米线旋涂工艺以形成透明导电电极（TCE）。一个性能良好的TCE具有两个相互矛盾的特性：高透射率和高电导率。该领域通常采用标量品质因数进行优化，但无法满足特定应用对透射率和电导率的独立要求。通过基于机器学习模型进行帕累托前沿分析，我们表明，透射率≥75%且方阻≤15Ω/sq的理想结果具有挑战性，但可以使用机器学习分析确定的工艺参数来实现。
