Refine
Has Fulltext
- no (4)
Document Type
- Article (4)
Language
- English (4) (remove)
Is part of the Bibliography
- yes (4)
Keywords
- Carbon (1)
- Crop modelling (1)
- Ecosystem services (1)
- Edge effects (1)
- Environmental gradients (1)
- Equivocality (1)
- Feature selection (1)
- Fragmentation (1)
- Germany (1)
- Machine learning (1)
Institute
- Institut für Umweltwissenschaften und Geographie (4) (remove)
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.
Human-driven fragmentation of landscapes leads to the formation of transition zones between ecosystems that are characterised by fluxes of matter, energy and information. These transition zones may offer rather inhospitable habitats that could jeopardise biodiversity. On the other hand, transition zones are also reported to be hotspots for biodiversity and even evolutionary processes. The general mechanisms and influence of processes in transition zones are poorly understood. Although heterogeneity and diversity of land use of fragments and the transition zones between them play an important role, most studies only refer to forested transition zones. Often, only an extrapolation of measurements in the different fragments themselves is reported to determine gradients in transition zones. This paper contributes to a quantitative understanding of agricultural landscapes beyond individual ecotopes, and towards connected ecosystem mosaics that may be beneficial for the provision of ecosystem services.
In crop modeling and yield predictions, the heterogeneity of agricultural landscapes is usually not accounted for. This heterogeneity often arises from landscape elements like forests, hedges, or single trees and shrubs that cast shadows. Shading from forested areas or shrubs has effects on transpiration, temperature, and soil moisture, all of which affect the crop yield in the adjacent arable land. Transitional gradients of solar irradiance can be described as a function of the distance to the zero line (edge), the cardinal direction, and the height of trees. The magnitude of yield reduction in transition zones is highly influenced by solar irradiance-a factor that is not yet implemented in crop growth models on a landscape level. We present a spatially explicit model for shading caused by forested areas, in agricultural landscapes. With increasing distance to forest, solar irradiance and yield increase. Our model predicts that the shading effect from the forested areas occurs up to 15 m from the forest edge, for the simulated wheat yields, and up to 30 m, for simulated maize. Moreover, we estimated the spatial extent of transition zones, to calculate the regional yield reduction caused by shading of the forest edges, which amounted to 5% to 8% in an exemplary region.
Large-scale crop yield failures are increasingly associated with food price spikes and food insecurity and are a large source of income risk for farmers. While the evidence linking extreme weather to yield failures is clear, consensus on the broader set of weather drivers and conditions responsible for recent yield failures is lacking. We investigate this for the case of four major crops in Germany over the past 20 years using a combination of machine learning and process-based modelling. Our results confirm that years associated with widespread yield failures across crops were generally associated with severe drought, such as in 2018 and to a lesser extent 2003. However, for years with more localized yield failures and large differences in spatial patterns of yield failures between crops, no single driver or combination of drivers was identified. Relatively large residuals of unexplained variation likely indicate the importance of non-weather related factors, such as management (pest, weed and nutrient management and possible interactions with weather) explaining yield failures. Models to inform adaptation planning at farm, market or policy levels are here suggested to require consideration of cumulative resource capture and use, as well as effects of extreme events, the latter largely missing in process-based models. However, increasingly novel combinations of weather events under climate change may limit the extent to which data driven methods can replace process-based models in risk assessments.