Die chronologische Liste zeigt aktuelle Veröffentlichungen aus dem Forschungsbetrieb der Hochschule Weihenstephan-Triesdorf. Zuständig ist das Zentrum für Forschung und Wissenstransfer (ZFW).
8 Ergebnisse
Josef Eiglsperger,
Prof. Dr. Florian Haselbeck,
Viola Stiele,
Claudia Guadarrama Serrano,
Kelly Lim-Trinh,
Prof. Dr. Klaus Menrad,
Prof. Dr. Thomas Hannus,
Prof. Dr. Dominik Grimm
Accurately forecasting demand is a potential competitive advantage, especially when dealing with perishable products. The multi-billion dollar horticultural industry is highly affected by perishability, but has received limited attention in forecasting research. In this paper, we analyze the applicability of general compared to dataset-specific predictors, as well as the influence of external information and online model update schemes. We employ a heterogeneous set of horticultural data, three classical, and twelve machine learning-based forecasting approaches. Our results show a superiority of multivariate machine learning methods, in particular the ensemble learner XGBoost. These advantages highlight the importance of external factors, with the feature set containing statistical, calendrical, and weather-related features leading to the most robust performance. We further observe that a general model is unable to capture the heterogeneity of the data and is outperformed by dataset-specific predictors. Moreover, frequent model updates have a negligible impact on forecasting quality, allowing long-term forecasting without significant performance degradation.
Mehr
Francesco Cosenza,
Asis Shrestha,
Delphine van Inghelandt,
Federico A Casale,
Po-Ya Wu,
Marius Weisweiler,
Jinquan Li,
Prof.Dr. Franziska Wespel,
Benjamin Stich
Um die Klimaziele zu erreichen, sollen bis 2035 zwei Prozent der Fläche Deutschlands für Windräder zur Verfügung stehen. Eine Gefahr für viele Vogelarten, warnen Tierschützer. Kann Technik das Kollisionsrisiko senken?
Study regionRaised bog “Königsdorfer-Weidfilz”, Bavaria, GermanyStudy focusThis study investigates effects of different rewetting scenarios on water levels in raised bog peat under varying climatic conditions. We apply physically-based models with high temporal and spatial resolutions to compare seasonal and annual water levels. The results were evaluated to determine the significance of these water level changes. Based on these water levels, a qualitative assessment was conducted to determine the percentage of areas that are more or less likely contributing to climate change through greenhouse gas emissions.New hydrological insightsOur study demonstrates the potential for investigating the rewetting of small peatland areas using high-resolution three-dimensional hydrological models. By utilizing a partially rewetted raised bog as a case study, we successfully modeled areas with different drainage states. Our results indicate that the areas rewetted in the respective scenarios behave similarly to the areas that have already been rewetted on site. Our study highlights that additional rewetting measures have a positive impact on reducing climate-active areas with low water levels in raised bogs. When combined with natural vegetation succession and changes in soil properties resulting from the formation of a new functional acrotelm layer after rewetting, these changes further enhance the effectiveness of the rewetting process. Although the influence of relevant dry periods after rewetting remains significant, our results suggest that the resilience of the peatland increases.
Wir verwenden Cookies. Einige sind notwendig für die Funktion der Webseite, andere helfen uns, die Webseite zu verbessern. Um unseren eigenen Ansprüchen beim Datenschutz gerecht zu werden, erfassen wir lediglich anonymisierte Nutzerdaten mit „Matomo“. Um unser Internetangebot für Sie ansprechender zu gestalten, binden wir außerdem externe Inhalte unserer Social-Media-Kanäle ein.