Geologic cores are rock samples that are extracted from deep under the ground during the well drilling process. They are used for petroleum reservoirs' performance characterization. Traditionally, physical studies of cores are carried out by the means of manual time-consuming experiments. With the development of deep learning, scientists actively started working on developing machine-learning-based approaches to identify physical properties without any manual experiments. Several previous works used machine learning to determine the porosity and permeability of the rocks, but either method was inaccurate or computationally expensive. We are proposing to use self-supervised pretraining of the very small CNN-transformer-based model to predict the physical properties of the rocks with high accuracy in a time-efficient manner. We show that this technique prevents overfitting even for extremely small datasets.
翻译:地质岩心是钻井过程中从地下深处提取的岩石样品,用于石油储油层的性能特征鉴定,传统上,岩心的物理研究是通过人工费时实验进行的。随着深层学习的发展,科学家积极着手开发基于机械学习的方法,在没有人工实验的情况下查明物理特性。以前的一些工程利用机器学习来确定岩石的孔隙性和渗透性,但方法不准确或计算成本昂贵。我们提议使用非常小的CNN变异模型进行自我监督的预培训,以高精度和高时间效率的方式预测岩石的物理特性。我们表明,即使极小的数据集,这种技术也无法过度使用。