Image segmentation remains the most critical step in Digital Rock Physics (DRP) workflows, affecting the analysis of physical rock properties. Conventional segmentation techniques struggle with numerous image artifacts and user bias, which lead to considerable uncertainty. This study evaluates the advantages of using the random forest (RF) algorithm for the segmentation of fractured rocks. The segmentation quality is discussed and compared with two conventional image processing methods (thresholding-based and watershed algorithm) and an encoder–decoder network in the form of convolutional neural networks (CNNs). The segmented images of the RF method were used as the ground truth for CNN training. The images of two fractured rock samples are acquired by X-ray computed tomography scanning (XCT). The skeletonized 3D images are calculated, providing information about the mean mechanical aperture and roughness. The porosity, permeability, flow fields, and preferred flow paths of segmented images are analyzed by the DRP approach. Moreover, the breakthrough curves obtained from tracer injection experiments are used as ground truth to evaluate the segmentation quality of each method. The results show that the conventional methods overestimate the fracture aperture. Both machine learning approaches show promising segmentation results and handle all artifacts and complexities without any prior CT-image filtering. However, the RF implementation has superior inherent advantages over CNN. This method is resource-saving (e.g., quickly trained), does not need an extensive training dataset, and can provide the segmentation uncertainty as a measure for evaluating the segmentation quality. The considerable variation in computed rock properties highlights the importance of choosing an appropriate segmentation method.

Calcite is a highly abundant mineral in the Earth’s crust and occurs as a cement phase in numerous siliciclastic sediments, where it often represents the most reactive component when a fluid percolates through the rock. Hence, the objective of this study is to derive calcite dissolution rates on different scales in a reservoir sandstone using mineral surface experiments combined with vertical scanning interferometry (VSI) and two types of core plug experiments. The 3D geometry of the calcite cement phase inside the rock cores was characterized by X-ray micro-computed tomography (µXCT) and was used to attempt dissolution rate upscaling from the mineral surface to the core scale. Initially (without upscaling), our comparison of the far-from-equilibrium dissolution rates at the mineral surface (µm-mm-scale, low fluid residence time) and the surface normalized dissolution rates obtained from the core experiments (cm-scale, high fluid residence time) revealed differences of 0.5–2 orders of magnitude. The µXCT geometric surface area connected to the open pore space $$\left( {GSA_{{Cc,{\text{open}}}} } \right)$$G S A C c , open considers the fluid accessibility of the heterogeneously distributed calcite cement that can largely vary between individual samples, but greatly affects the effective dissolution rates. Using this parameter to upscale the rates from the µm- to the cm-scale, the deviation of the upscaled total dissolution rates from the measured total dissolution rates was less than one order of magnitude for all investigated rock cores. Thus, $$GSA_{{Cc,{\text{open}}}}$$G S A C c , open showed to be reasonably suitable for upscaling the mineral surface rates to the core scale.

The unique vegetation in riparian zones is fundamental for various ecological and socio-economic functions in these transitional areas. Sustainable management requires detailed spatial information about the occurring flora. Here, we present a Deep Learning (DL)-based approach for processing multimodal high-resolution remote sensing data (aerial RGB and near-infrared (NIR) images and elevation maps) to generate a classification map of the tidal Elbe and a section of the Rhine River (Germany). The ground truth was based on existing mappings of vegetation and biotope types. The results showed that (I) despite a large class imbalance, for the tidal Elbe, a high mean Intersection over Union (IoU) of about 78% was reached. (II) At the Rhine River, a lower mean IoU was reached due to the limited amount of training data and labelling errors. Applying transfer learning methods and labelling error correction increased the mean IoU to about 60%. (III) Early fusion of the modalities was beneficial. (IV) The performance benefits from using elevation maps and the NIR channel in addition to RGB images. (V) Model uncertainty was successfully calibrated by using temperature scaling. The generalization ability of the trained model can be improved by adding more data from future aerial surveys.