Dokument-ID Dokumenttyp Verfasser/Autoren Herausgeber Haupttitel Abstract Auflage Verlagsort Verlag Erscheinungsjahr Seitenzahl Schriftenreihe Titel Schriftenreihe Bandzahl ISBN Quelle der Hochschulschrift Konferenzname Quelle:Titel Quelle:Jahrgang Quelle:Heftnummer Quelle:Erste Seite Quelle:Letzte Seite URN DOI Abteilungen OPUS4-62694 Wissenschaftlicher Artikel Lischeid, Gunnar; Webber, Heidi; Sommer, Michael; Nendel, Claas; Ewert, Frank Machine learning in crop yield modelling Provisioning a sufficient stable source of food requires sound knowledge about current and upcoming threats to agricultural production. To that end machine learning approaches were used to identify the prevailing climatic and soil hydrological drivers of spatial and temporal yield variability of four crops, comprising 40 years yield data each from 351 counties in Germany. Effects of progress in agricultural management and breeding were subtracted from the data prior the machine learning modelling by fitting smooth non-linear trends to the 95th percentiles of observed yield data. An extensive feature selection approach was followed then to identify the most relevant predictors out of a large set of candidate predictors, comprising various soil and meteorological data. Particular emphasis was placed on studying the uniqueness of identified key predictors. Random Forest and Support Vector Machine models yielded similar although not identical results, capturing between 50% and 70% of the spatial and temporal variance of silage maize, winter barley, winter rapeseed and winter wheat yield. Equally good performance could be achieved with different sets of predictors. Thus identification of the most reliable models could not be based on the outcome of the model study only but required expert's judgement. Relationships between drivers and response often exhibited optimum curves, especially for summer air temperature and precipitation. In contrast, soil moisture clearly proved less relevant compared to meteorological drivers. In view of the expected climate change both excess precipitation and the excess heat effect deserve more attention in breeding as well as in crop modelling. Amsterdam Elsevier 2022 23 Agricultural and forest meteorology 312 10.1016/j.agrformet.2021.108698 Institut für Biochemie und Biologie OPUS4-36179 Wissenschaftlicher Artikel Lopez-Tarazon, Jose Andres; Batalla Villanueva, Ramon J.; Vericat, Damia; Francke, Till The sediment budget of a highly dynamic mesoscale catchment the River Isabena The paper presents the sediment budget of the Isabena basin, a highly dynamic 445-km(2) catchment located in the Central Pyrenees that is patched by highly erodible areas (i.e., badlands). The budget for the period 2007-2009 is constructed following a methodology that allows the interpolation of intermittent measurements of suspended sediment concentrations and enables a subsequent calculation of sediment loads. Data allow specification of the contribution of each subbasin to the water and sediment yield in the catchment outlet. Mean annual sediment load was 235,000 t y(-1). Specific sediment yield reached 2000 t km(-2) y(-1), a value that indicates very high sedimentary activity, especially in the case of Villacarli and Lascuarre subcatchments, were most badlands are located. The specific sediment yield obtained for the entire Isabena is 527 t km(-2) y(-1), a high value for such a mesoscale basin. Results show that a small part of the area (i.e., 1%) controls most of the catchment's gross sediment contribution. Sediment delivery ratio (ratio between sediment input from primary sources and basin export) has been estimated at around 90%, while in-channel storage represents the 5% of the annual load on average. The high connectivity between sediment sources (i.e., badlands) and transfer paths (i.e., streamcourses) exacerbates the influence of the local sediment production on the catchment's sediment yield, a quite unusual fact for a basin of this scale. Amsterdam Elsevier 2012 14 Geomorphology : an international journal on pure and applied geomorphology 138 1 15 28 10.1016/j.geomorph.2011.08.020 Institut für Geowissenschaften OPUS4-35758 Wissenschaftlicher Artikel Vorpahl, Peter; Elsenbeer, Helmut; Märker, Michael; Schröder-Esselbach, Boris How can statistical models help to determine driving factors of landslides? Landslides are a hazard for humans and artificial structures. From an ecological point of view, they represent an important ecosystem disturbance, especially in tropical montane forests. Here, shallow translational landslides are a frequent natural phenomenon and one local determinant of high levels of biodiversity. In this paper, we apply weighted ensembles of advanced phenomenological models from statistics and machine learning to analyze the driving factors of natural landslides in a tropical montane forest in South Ecuador. We exclusively interpret terrain attributes, derived from a digital elevation model, as proxies to several driving factors of landslides and use them as predictors in our models which are trained on a set of five historical landslide inventories. We check the model generality by transferring them in time and use three common performance criteria (i.e. AUC, explained deviance and slope of model calibration curve) to, on the one hand, compare several state-of-the-art model approaches and on the other hand, to create weighted model ensembles. Our results suggest that it is important to consider more than one single performance criterion. Approaching our main question, we compare responses of weighted model ensembles that were trained on distinct functional units of landslides (i.e. initiation, transport and deposition zones). This way, we are able to show that it is quite possible to deduce driving factors of landslides, if the consistency between the training data and the processes is maintained. Opening the 'black box' of statistical models by interpreting univariate model response curves and relative importance of single predictors regarding their plausibility, we provide a means to verify this consistency. With the exception of classification tree analysis, all techniques performed comparably well in our case study while being outperformed by weighted model ensembles. Univariate response curves of models trained on distinct functional units of landslides exposed different shapes following our expectations. Our results indicate the occurrence of landslides to be mainly controlled by factors related to the general position along a slope (i.e. ridge, open slope or valley) while landslide initiation seems to be favored by small scale convexities on otherwise plain open slopes. Amsterdam Elsevier 2012 13 Ecological modelling : international journal on ecological modelling and engineering and systems ecolog 239 7 27 39 10.1016/j.ecolmodel.2011.12.007 Institut für Geowissenschaften