Soil samples from several European countries were scanned using medical computer tomography (CT) device and are now available as CT images. The analysis of these samples was carried out using deep learning methods. For this purpose, a VGG16 network was trained with the CT images (X). For the annotation (y) a new method for automated annotation, ‘surrogate’ learning, was introduced. The generated neural networks (NNs) were subjected to a detailed analysis. Among other things, transfer learning was used to check whether the NN can also be trained to other y-values. Visually, the NN was verified using a gradient-based class activation mapping (grad-CAM) algorithm. These analyses showed that the NN was able to generalize, i.e. to capture the spatial structure of the soil sample. Possible applications of the models are discussed.

使用医用计算机断层扫描 (CT) 设备对来自多个欧洲国家的土壤样本进行扫描，现在可提供 CT 图像。使用深度学习方法对这些样本进行了分析。为此，使用 CT 图像 (X) 训练 VGG16 网络。对于注释（y），引入了一种新的自动注释方法，即“代理”学习。对生成的神经网络（NN）进行了详细分析。除此之外，迁移学习还用于检查神经网络是否也可以训练为其他 y 值。从视觉上看，神经网络是使用基于梯度的类激活映射 (grad-CAM) 算法进行验证的。这些分析表明神经网络能够泛化，即捕获土壤样本的空间结构。讨论了模型的可能应用。