Appl Opt. 2023 May 1;62(13):3370-3379. doi: 10.1364/AO.487185.
Atmospheric turbulence ( 2) modeling has been proposed by physics-based models, but they are unable to capture the many cases. Recently, machine learning surrogate models have been used to learn the relationship between local meteorological conditions and turbulence strength. These models predict 2 at time from weather at time . This work expands modeling capabilities by proposing a technique to forecast 3 h of future turbulence conditions at 30 min intervals from prior environmental parameters using artificial neural networks. First, local weather and turbulence measurements are formatted to pairs of the input sequence and output forecast. Next, a grid search is used to find the best combination of model architecture, input variables, and training parameters. The architectures investigated are the multilayer perceptron and three variants of the recurrent neural network (RNN): the simple RNN, the long short-term memory RNN (LSTM-RNN), and the gated recurrent unit RNN (GRU-RNN). A GRU-RNN architecture that uses 12 h of prior inputs is found to have the best performance. Finally, this model is applied to the test dataset and analyzed. It is shown that the model has generally learned the relationship between prior environmental and future turbulence conditions.
大气湍流（2）建模已经被物理模型提出，但是它们无法捕捉到很多情况。最近，机器学习代理模型已被用于学习局部气象条件和湍流强度之间的关系。这些模型可以从当时的天气预测到当时的 2 。这项工作通过提出一种使用人工神经网络从先前的环境参数每隔 30 分钟预测未来 3 小时的湍流条件的技术来扩展建模能力。首先，将局部天气和湍流测量值格式化为输入序列和输出预测的对。接下来，进行网格搜索以找到最佳模型架构、输入变量和训练参数组合。研究的架构是多层感知器和三种递归神经网络（RNN）变体：简单 RNN、长短期记忆 RNN（LSTM-RNN）和门控递归单元 RNN（GRU-RNN）。发现使用 12 小时先前输入的 GRU-RNN 架构具有最佳性能。最后，将该模型应用于测试数据集并进行分析。结果表明，该模型已经学习了先前环境与未来湍流条件之间的关系。
