TY - CHAP A1 - Kleber, Arno A1 - Terhorst, Birgit A1 - Hülle, Daniela A1 - Leopold, Matthias A1 - Müller, S. A1 - Raab, Thomas A1 - Sauer, Daniela A1 - Scholten, Thomas A1 - Dietze, Michael A1 - Felix-Henningsen, Peter A1 - Heinrich, J. A1 - Spies, E. D. A1 - Thiemeyer, H. ED - Kleber, Arno ED - Terhorst, Birgit T1 - Subdued Mountains of Central Europe T2 - Mid-Latitude Slope Deposits (Cover Beds) N2 - Slope deposits, which veil entire slopes or large parts of them in a rather uniform manner (cover beds), are ubiquitous in the subdued mountains of Central Europe. Here we provide an overview of the current state of knowledge on these deposits. The Central European cover beds are divided into (1) the upper layer that is ubiquitously distributed and displays a relatively constant thickness; (2) the intermediate layer the distribution of which is mainly restricted to flat relief, to slope depressions, and to lee-ward facing slopes; and (3) the basal layer, which is rather widespread again. Both the upper and intermediate layer contain intermixed loess, whereas the basal layer is free of loess and typically has a high bulk density. Aside from the loess content, the composition of the layers differs, reflecting varying portions of crushed and chemically weathered rock allocated from up-slope. This causes notable diversity depending on bedrock and, thus, induces remarkable regional differences. Cover beds were mainly formed by periglacial gelifluction. The upper layer formed in the Late Glacial possibly during several short episodes of activity. In contrast, the underlying layers may be diachronous; nevertheless, they display recurring vertical sequences. This is probably due to the fact that loess-free layers usually could not deposit as long as there was loess in the environs, which may have been inherited from older deposits. Thus, the last phase of surface wash, during which older loess was removed, determines the age of the lower layers. Y1 - 2013 SN - 978-0-444-53118-6 U6 - https://doi.org/10.1016/B978-0-444-53118-6.00002-7 SP - 9 EP - 93 PB - Elsevier CY - Oxford ER - TY - GEN A1 - Kakhani, Nafiseh A1 - Taghizadeh‐Mehrjardi, Ruhollah A1 - Omarzadeh, Davoud A1 - Ryo, Masahiro A1 - Heiden, Uta A1 - Scholten, Thomas T1 - Towards explainable AI : interpreting soil organic carbon prediction models using a learning‐based explanation method T2 - European Journal of Soil Science N2 - An understanding of the key factors and processes influencing the variability of soil organic carbon (SOC) is essential for the development of effective policies aimed at enhancing carbon storage in soils to mitigate climate change. In recent years, complex computational approaches from the field of machine learning (ML) have been developed for modelling and mapping SOC in various ecosystems and over large areas. However, in order to understand the processes that account for SOC variability from ML models and to serve as a basis for new scientific discoveries, the predictions made by these data‐driven models must be accurately explained and interpreted. In this research, we introduce a novel explanation approach applicable to any ML model and investigate the significance of environmental features to explain SOC variability across Germany. The methodology employed in this study involves training multiple ML models using SOC content measurements from the LUCAS dataset and incorporating environmental features derived from Google Earth Engine (GEE) as explanatory variables. Thereafter, an explanation model is applied to elucidate what the ML models have learned about the relationship between environmental features and SOC content in a supervised manner. In our approach, a post hoc model is trained to estimate the contribution of specific inputs to the outputs of the trained ML models. The results of this study indicate that different classes of ML models rely on interpretable but distinct environmental features to explain SOC variability. Decision tree‐based models, such as random forest (RF) and gradient boosting, highlight the importance of topographic features. Conversely, soil chemical information, particularly pH, is crucial for the performance of neural networks and linear regression models. Therefore, interpreting data‐driven studies requires a carefully structured approach, guided by expert knowledge and a deep understanding of the models being analysed. KW - Explainable AI KW - Germany KW - Google Earth Engine KW - HLS product KW - Remote sensing KW - Soil organic carbon Y1 - 2025 U6 - https://doi.org/10.1111/ejss.70071 SN - 1351-0754 VL - 76 IS - 2 SP - 1 EP - 18 PB - Wiley ER -