Filters

2017 - 201932020 - 20236

More filters

2022 - 20239
Reset filters

Settings

DDC: 580 × DDC: 630 × Has files: Yes ×

Search Results

Now showing 1 - 9 of 9
  • Thumbnail Image
    Item
    Identification of representative dairy cattle and fodder crop production typologies at regional scale in Europe
    (Berlin ; Heidelberg : Springer, 2022) Díaz de Otálora, Xabier; Dragoni, Federico; Del Prado, Agustín; Estellés, Fernándo; Wilfart, Aurélie; Krol, Dominika; Balaine, Lorraine; Anestis, Vasileios; Amon, Barbara
    European dairy production faces significant economic, environmental, and social sustainability challenges. Given the great diversity of dairy cattle production systems in Europe, region-specific concepts to improve environmental and socioeconomic sustainability are needed. Regionally integrated dairy cattle-crop systems emerge as a more resilient and sustainable alternative to highly specialized farming systems. Identifying different dairy cattle production typologies and their potential interactions with fodder crop production is presented as a step in transitioning to optimized agricultural systems. Currently existing typologies of integrated systems are often insufficient when characterizing structural, socioeconomic, and environmental components of farms. We fill this gap in the literature by identifying, describing, and comparing representative dairy cattle production system typologies and their interrelation with regional fodder crop production at the European regional scale. This is a necessary step to assess the scope for adapted mitigation and sustainability measures in the future. For this purpose, a multivariate statistical approach is applied. We show how different land-use practices, farm structure characteristics, socio-economic attributes, and emission intensities condition dairy production. Furthermore, the diversity of regional fodder crop production systems is demonstrated by analyzing their distribution in Europe. Together with identified typologies, varying degrees of regional specialization in milk production allow for identifying future strategies associated with the application of integrated systems in key European dairy regions. This study contributes to a better understanding of the existing milk production diversity in Europe and their relationship with regional fodder crop production. In addition, we discuss the benefits of integrated systems as a clear, viable, and resilient alternative to ongoing livestock intensification in the European context. Identifying interactions between components of integrated systems will facilitate decision-making, the design and implementation of measures to mitigate climate change, and the promotion of positive socio-economic and environmental interactions.
  • Thumbnail Image
    Item
    Milk fatty acids estimated by mid-infrared spectroscopy and milk yield can predict methane emissions in dairy cows
    (Berlin ; Heidelberg : Springer, 2018-5-2) Engelke, Stefanie W.; Daş, Gürbüz; Derno, Michael; Tuchscherer, Armin; Berg, Werner; Kuhla, Björn; Metges, Cornelia C.
    Ruminant enteric methane emission contributes to global warming. Although breeding low methane-emitting cows appears to be possible through genetic selection, doing so requires methane emission quantification by using elaborate instrumentation (respiration chambers, SF6 technique, GreenFeed) not feasible on a large scale. It has been suggested that milk fatty acids are promising markers of methane production. We hypothesized that methane emission can be predicted from the milk fatty acid concentrations determined by mid-infrared spectroscopy, and the integration of energy-corrected milk yield would improve the prediction. Therefore, we examined relationships between methane emission of cows measured in respiration chambers and milk fatty acids, predicted by mid-infrared spectroscopy, to derive diet-specific and general prediction equations based on milk fatty acid concentrations alone and with the additional consideration of energy-corrected milk yield. Cows were fed diets differing in forage type and linseed supplementation to generate a large variation in both CH4 emission and milk fatty acids. Depending on the diet, equations derived from regression analysis explained 61 to 96% of variation of methane emission, implying the potential of milk fatty acid data predicted by mid-infrared spectroscopy as novel proxy for direct methane emission measurements. When data from all diets were analyzed collectively, the equation with energy-corrected milk yield (CH4 (L/day) = − 1364 + 9.58 × energy-corrected milk yield + 18.5 × saturated fatty acids + 32.4 × C18:0) showed an improved coefficient of determination of cross-validation R2 CV = 0.72 compared to an equation without energy-corrected milk yield (R2 CV = 0.61). Equations developed for diets supplemented by linseed showed a lower R2 CV as compared to diets without linseed (0.39 to 0.58 vs. 0.50 to 0.91). We demonstrate for the first time that milk fatty acid concentrations predicted by mid-infrared spectroscopy together with energy-corrected milk yield can be used to estimate enteric methane emission in dairy cows. © 2018, The Author(s).
  • Thumbnail Image
    Item
    Biochar research activities and their relation to development and environmental quality. A meta-analysis
    (Berlin ; Heidelberg : Springer, 2017-6-6) Mehmood, Khalid; Chávez Garcia, Elizabeth; Schirrmann, Michael; Ladd, Brenton; Kammann, Claudia; Wrage-Mönnig, Nicole; Siebe, Christina; Estavillo, Jose M.; Fuertes-Mendizabal, Teresa; Cayuela, Mariluz; Sigua, Gilbert; Spokas, Kurt; Cowie, Annette L.; Novak, Jeff; Ippolito, James A.; Borchard, Nils
    Biochar is the solid product that results from pyrolysis of organic materials. Its addition to highly weathered soils changes physico-chemical soil properties, improves soil functions and enhances crop yields. Highly weathered soils are typical of humid tropics where agricultural productivity is low and needs to be raised to reduce human hunger and poverty. However, impact of biochar research on scientists, politicians and end-users in poor tropical countries remains unknown; assessing needs and interests on biochar is essential to develop reliable knowledge transfer/translation mechanisms. The aim of this publication is to present results of a meta-analysis conducted to (1) survey global biochar research published between 2010 and 2014 to assess its relation to human development and environmental quality, and (2) deduce, based on the results of this analysis, priorities required to assess and promote the role of biochar in the development of adapted and sustainable agronomic methods. Our main findings reveal for the very first time that: (1) biochar research associated with less developed countries focused on biochar production technologies (26.5 ± 0.7%), then on biochars’ impact on chemical soil properties (18.7 ± 1.2%), and on plant productivity (17.1 ± 2.6%); (2) China dominated biochar research activities among the medium developed countries focusing on biochar production technologies (26.8 ± 0.5%) and on use of biochar as sorbent for organic and inorganic compounds (29.1 ± 0.4%); and (3) the majority of biochar research (69.0±2.9%) was associated with highly developed countries that are able to address a higher diversity of questions. Evidently, less developed countries are eager to improve soil fertility and agricultural productivity, which requires transfer and/or translation of biochar knowledge acquired in highly developed countries. Yet, improving local research capacities and encouraging synergies across scientific disciplines and countries are crucial to foster development of sustainable agronomy in less developed countries. © 2017, The Author(s).
  • Thumbnail Image
    Item
    Deep Learning Object Detection for Image Analysis of Cherry Fruit Fly (Rhagoletis cerasi L.) on Yellow Sticky Traps
    (Berlin ; Heidelberg : Springer, 2022) Salamut, Christian; Kohnert, Iris; Landwehr, Niels; Pflanz, Michael; Schirrmann, Michael; Zare, Mohammad
    Insect populations appear with a high spatial, temporal and type-specific diversity in orchards. One of the many monitoring tools for pest management is the manual assessment of sticky traps. However, this type of assessment is laborious and time-consuming so that only a few locations can be controlled in an orchard. The aim of this study is to test state-of-the art object detection algorithms from deep learning to automatically detect cherry fruit flies (Rhagoletis cerasi), a common insect pest in cherry plantations, within images from yellow sticky traps. An image annotation database was built with images taken from yellow sticky traps with more than 1600 annotated cherry fruit flies. For better handling in the computational algorithms, the images were augmented to smaller ones by the known image preparation methods “flipping” and “cropping” before performing the deep learning. Five deep learning image recognition models were tested including Faster Region-based Convolutional Neural Network (R-CNN) with two different methods of pretraining, Single Shot Detector (SSD), RetinaNet, and You Only Look Once version 5 (YOLOv5). R‑CNN and RetinaNet models outperformed other ones with a detection average precision of 0.9. The results indicate that deep learning can act as an integral component of an automated system for high-throughput assessment of pest insects in orchards. Therefore, this can reduce the time for repetitive and laborious trap assessment but also increase the observed amount of sticky traps
  • Thumbnail Image
    Item
  • Thumbnail Image
    Item
    Improving Deep Learning-based Plant Disease Classification with Attention Mechanism
    (Berlin ; Heidelberg : Springer, 2022) Alirezazadeh, Pendar; Schirrmann, Michael; Stolzenburg, Frieder
    In recent years, deep learning-based plant disease classification has been widely developed. However, it is challenging to collect sufficient annotated image data to effectively train deep learning models for plant disease recognition. The attention mechanism in deep learning assists the model to focus on the informative data segments and extract the discriminative features of inputs to enhance training performance. This paper investigates the Convolutional Block Attention Module (CBAM) to improve classification with CNNs, which is a lightweight attention module that can be plugged into any CNN architecture with negligible overhead. Specifically, CBAM is applied to the output feature map of CNNs to highlight important local regions and extract more discriminative features. Well-known CNN models (i.e. EfficientNetB0, MobileNetV2, ResNet50, InceptionV3, and VGG19) were applied to do transfer learning for plant disease classification and then fine-tuned by a publicly available plant disease dataset of foliar diseases in pear trees called DiaMOS Plant. Amongst others, this dataset contains 3006 images of leaves affected by different stress symptoms. Among the tested CNNs, EfficientNetB0 has shown the best performance. EfficientNetB0+CBAM has outperformed EfficientNetB0 and obtained 86.89% classification accuracy. Experimental results show the effectiveness of the attention mechanism to improve the recognition accuracy of pre-trained CNNs when there are few training data.
  • Thumbnail Image
    Item
    A Pixel-wise Segmentation Model to Identify Bur Chervil (Anthriscus caucalis M. Bieb.) Within Images from a Cereal Cropping Field
    (Berlin ; Heidelberg : Springer, 2022) Karimi, Hadi; Navid, Hossein; Dammer, Karl-Heinz
    Because of insufficient effectiveness after herbicide application in autumn, bur chervil (Anthriscus caucalis M. Bieb.) is often present in cereal fields in spring. A second reason for spreading is the warm winter in Europe due to climate change. This weed continues to germinate from autumn to spring. To prevent further spreading, a site-specific control in spring is reasonable. Color imagery would offer cheap and complete monitoring of entire fields. In this study, an end-to-end fully convolutional network approach is presented to detect bur chervil within color images. The dataset consisted of images taken at three sampling dates in spring 2018 in winter wheat and at one date in 2019 in winter rye from the same field. Pixels representing bur chervil were manually annotated in all images. After a random image augmentation was done, a Unet-based convolutional neural network model was trained using 560 (80%) of the sub-images from 2018 (training images). The power of the trained model at the three different sampling dates in 2018 was evaluated at 141 (20%) of the manually annotated sub-images from 2018 and all (100%) sub-images from 2019 (test images). Comparing the estimated and the manually annotated weed plants in the test images the Intersection over Union (Jaccard index) showed mean values in the range of 0.9628 to 0.9909 for the three sampling dates in 2018, and a value of 0.9292 for the one date in 2019. The Dice coefficients yielded mean values in the range of 0.9801 to 0.9954 for 2018 and a value of 0.9605 in 2019.
  • Thumbnail Image
    Item
    Methods for Recognition of Colorado Beetle (Leptinotarsa decemlineata (Say)) with Multispectral and Color Camera-sensors
    (Berlin ; Heidelberg : Springer, 2022) Dammer, Karl-Heinz
    At the beginning of an epidemic, the Colorado beetle occur sparsely on few potato plants in the field. A target-orientated crop protection applies insecticides only on infested plants. For this, a complete monitoring of the whole field is required, which can be done by camera-sensors attached to tractors or unmanned aerial vehicles (UAVs). The gathered images have to be analyzed using appropriate classification methods preferably in real-time to recognize the different stages of the beetle in high precision. In the paper, the methodology of the application of one multispectral and three commercially available color cameras (RGB) and the results from field tests for recognizing the development stages of the beetle along the vegetation period of the potato crop are presented. Compared to multispectral cameras color cameras are low-cost. The use of artificial neural network for classification of the larvae within the RGB-images are discussed. At the bottom side of the potato leaves the eggs are deposited. Sensor based monitoring from above the crop canopy cannot detect the eggs and the hatching first instar. The ATB developed a camera equipped vertical sensor for scanning the bottom of the leaves. This provide a time advantage for the spray decision of the farmer (e.g. planning of the machine employment, purchase of insecticides). In this paper, example images and a possible future use of the presented monitoring methods above and below the crop surface are presented and discussed.
  • Thumbnail Image
    Item
    Forest carbon allocation modelling under climate change
    (Victoria, BC : Heron, 2019) Merganičová, Katarína; Merganič, Ján; Lehtonen, Aleksi; Vacchiano, Giorgio; Ostrogović Sever, Maša Zorana; Augustynczik, Andrey L. D.; Grote, Rüdiger; Kyselová, Ina; Mäkelä, Annikki; Yousefpour, Rasoul; Krejza, Jan; Collalti, Alessio; Reyer, Christopher P. O.
    Carbon allocation plays a key role in ecosystem dynamics and plant adaptation to changing environmental conditions. Hence, proper description of this process in vegetation models is crucial for the simulations of the impact of climate change on carbon cycling in forests. Here we review how carbon allocation modelling is currently implemented in 31 contrasting models to identify the main gaps compared with our theoretical and empirical understanding of carbon allocation. A hybrid approach based on combining several principles and/or types of carbon allocation modelling prevailed in the examined models, while physiologically more sophisticated approaches were used less often than empirical ones. The analysis revealed that, although the number of carbon allocation studies over the past 10 years has substantially increased, some background processes are still insufficiently understood and some issues in models are frequently poorly represented, oversimplified or even omitted. Hence, current challenges for carbon allocation modelling in forest ecosystems are (i) to overcome remaining limits in process understanding, particularly regarding the impact of disturbances on carbon allocation, accumulation and utilization of nonstructural carbohydrates, and carbon use by symbionts, and (ii) to implement existing knowledge of carbon allocation into defence, regeneration and improved resource uptake in order to better account for changing environmental conditions. © The Author(s) 2019. Published by Oxford University Press.