MLReal：弥合机器学习中合成数据训练和真实数据应用之间的差距
MLReal: Bridging the gap between training on synthetic data and real data applications in machine learning
摘要：
我们在利用波形数据训练的神经网络时面临的最大挑战之一（即，地震、电磁或超声波）是其对真实数据的应用。对准确标签的要求迫使我们使用合成数据开发解决方案，其中标签很容易获得。然而，合成数据通常无法捕捉现场/真实实验的现实，并且我们最终在推理阶段训练的神经网络（NN）的性能很差。我们描述了一种新的方法来增强对具有真实数据特征（域自适应）的合成数据的监督训练。具体来说，对于输入数据的垂直轴（时间或深度）的绝对值并不重要的任务，如分类，或者可以在之后进行校正，如使用测井曲线建立速度模型，我们建议对输入进行一系列线性运算，以便训练和应用数据具有相似的分布。这是通过对NN模型的输入数据应用两个操作来实现的：1）输入数据的互相关（即，炮集、地震图像等）具有来自相同数据集的固定参考轨迹。2)所得数据与来自另一个域的自相关数据的平均值（或随机样本）的卷积。在训练阶段，输入数据来自合成域，自相关数据来自实域，并且在每个训练时期从实数据中抽取随机样本。在推理/应用阶段，输入数据来自实子集域，自相关部分的均值来自合成数据子集域。被动地震资料的微震事件源位置确定和主动地震资料预测低频的示例应用程序被用来证明这种方法的力量，在提高训练模型的适用性，以真实的数据。
英文摘要：
Among the biggest challenges we face in utilizing neural networks trained on waveform data (i.e., seismic, electromagnetic, or ultrasound) is its application to real data. The requirement for accurate labels forces us to develop solutions using synthetic data, where labels are readily available. However, synthetic data often do not capture the reality of the field/real experiment, and we end up with poor performance of the trained neural network (NN) at the inference stage. We describe a novel approach to enhance supervised training on synthetic data with real data features (domain adaptation). Specifically, for tasks in which the absolute values of the vertical axis (time or depth) of the input data are not crucial, like classification, or can be corrected afterward, like velocity model building using a well-log, we suggest a series of linear operations on the input so the training and application data have similar distributions. This is accomplished by applying two operations on the input data to the NN model: 1) The crosscorrelation of the input data (i.e., shot gather, seismic image, etc.) with a fixed reference trace from the same dataset. 2) The convolution of the resulting data with the mean (or a random sample) of the autocorrelated data from another domain. In the training stage, the input data are from the synthetic domain and the auto-correlated data are from the real domain, and random samples from real data are drawn at every training epoch. In the inference/application stage, the input data are from the real subset domain and the mean of the autocorrelated sections are from the synthetic data subset domain. Example applications on passive seismic data for microseismic event source location determination and active seismic data for predicting low frequencies are used to demonstrate the power of this approach in improving the applicability of trained models to real data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
