On 14 May 2025, three juvenile grass snakes, Natrix natrix (Linnaeus, 1758), were dissected from the stomach of a single rainbow trout, Oncorhynchus mykiss (Walbaum, 1792), caught in the Ammer River, Bavaria, Germany. That record completes the scarce evidence of reptiles as prey in salmonid diets and highlights the trophic plasticity of the introduced O. mykiss.
This paper presents agronomic and economic challenges of herbicide reduction strategies in German arable farming, based on a workshop-discussion on the ‘Reduction of herbicide use—economic and structural challenges and effects on agricultural farming in Germany’, held at the German Conference on Weed Biology and Weed Control in February 2024. The strategies discussed and compiled comprise (1) indirect and preventive measures like diverse cropping systems, cultivar choice, intercropping or mulching and (2) direct non-chemical measures, such as mechanical weed control or biological control. Direct non-chemical measures with optimization potential for arable farming (3), like thermal weed control or electro weeding and (4) measures for optimising herbicide application such as site-specific herbicide application or computer-aided forecast models were also discussed. The discussed strategies are associated with advantages like positive co-benefits in terms of soil health and biodiversity, a reduced selection of herbicide-resistant biotypes or in specific cases with positive yield effects. Disadvantages are in many cases linked to economic parameters such as higher workload, higher costs or/and to a reduction of yield potential. Disadvantages and economic challenges contribute to a reluctance of farmers towards the adoption of herbicide reduction strategies, which in Germy is still limited. To overcome these shortcomings and support the reduction of pesticides alongside environmental benefits, targeted funding and compensation, combined with an expanded independent advisory service, should be considered and reinforced. Furthermore, increased research and knowledge on economic challenges is expected to help farmers better judge the benefits, risks and obstacles of reducing herbicide use.
Weeds significantly impact agricultural production, and traditional weed control methods often harm soil health and environment. This study aimed to develop deep learning-based segmentation models in identifying weeds in potato fields captured by Unmanned Aerial Vehicle (UAV) orthophotos and to explore the effects of weeds on potato yield. Previous studies predominantly employed U-Net for weed segmentation, but its performance often declines under complex field environments and low-image resolution conditions. Some studies attempted to overcome this limitation by reducing flight altitude or using high-cost cameras, but these approaches are not always practical. To address these challenges, this study uniquely integrated Real-ESRGAN Super-Resolution (SR) for UAV image enhancement and the Segment Anything Model (SAM) for semi-automatic annotation. Subsequently, we trained the YOLOv8 and Mask R-CNN models for segmentation. Results showed that the detection accuracy mAP50 scores were 0.902 and 0.920 for YOLOv8 and Mask R-CNN, respectively. Real-ESRGAN reconstruction slightly improved accuracy. When multiple weed types were present, accuracy generally decreased. The YOLOv8 model characterized plant and weed coverage areas could explained 41.2 % of potato yield variations (R2 = 0.412, p-value = 0.01), underscoring the practical utility of UAV-based segmentation for yield estimation. Both YOLOv8 and Mask R-CNN achieved high accuracy, with YOLOv8 converging faster. While different nitrogen fertilizer treatments had no significant effect on yield, weed control treatments significantly impacted yield, highlighting the importance of precise weed mapping for spot-specific weed management. This study provides insights into weed segmentation using Deep Leaning and contributes to environmentally friendly precision weed control.
Perennial crops, such as Silphium perfoliatum L. (cup plant), offer significant benefits for soil and groundwater conservation, owing to their nearly continuous soil cover and extensive root systems. To effectively plan and manage the establishment of cup plant in areas with high erosion risk, it is crucial to quantify its preventive impact on rainfall‐induced soil erosion, expressed as the C factor. This study determined the C factor using a subfactor approach, which incorporated measurements of root mass development, soil cover by mulch and vegetation, and plant height across multiple experimental and practitioner sites with cup plant stands of varying ages. The findings indicate that, over a cultivation period of at least 10 years, soil erosion because of intense rainfall is reduced under cup plant to less than a quarter of the erosion typically observed in conventional arable farming and one eighth of the erosion in maize. While erosion under cup plants is significantly lower than in pure cereal cultivation, it does not achieve the minimal levels observed in grasslands, primarily because of higher erosion risks during the initial years following establishment. This applies equally to stands established through direct sowing and those established with maize as a nurse crop in the first year. A substantial portion of the erosion reduction can be attributed to soil consolidation and intensive rooting in the topsoil. Additionally, the absence of soil displacement because of tillage post‐establishment further contributes to reduced erosion by additionally eliminating tillage erosion.
Accurate estimates of the location, timing, and severity of soil-erosion events on arable land have eluded erosionprediction technology for decades. Here, for the first time, we demonstrate how a machine learning model parameterised with spatiotemporal covariates within a back-end infrastructure of data cubes can nowcast the occurrence and relatively rank the severity of erosion events on arable field parcels at the regional scale with high accuracy and interpretable outputs. Our findings pave the way for dynamic erosion-monitoring systems to achieve healthy soils and improve food security.
