74 results
Search Results
Now showing 1 - 10 of 74
- ItemOptimized Deep Learning Model as a Basis for Fast UAV Mapping of Weed Species in Winter Wheat Crops(Basel : MDPI AG, 2021) de Camargo, Tibor; Schirrmann, Michael; Landwehr, Niels; Dammer, Karl-Heinz; Pflanz, MichaelWeed maps should be available quickly, reliably, and with high detail to be useful for site-specific management in crop protection and to promote more sustainable agriculture by reducing pesticide use. Here, the optimization of a deep residual convolutional neural network (ResNet-18) for the classification of weed and crop plants in UAV imagery is proposed. The target was to reach sufficient performance on an embedded system by maintaining the same features of the ResNet-18 model as a basis for fast UAV mapping. This would enable online recognition and subsequent mapping of weeds during UAV flying operation. Optimization was achieved mainly by avoiding redundant computations that arise when a classification model is applied on overlapping tiles in a larger input image. The model was trained and tested with imagery obtained from a UAV flight campaign at low altitude over a winter wheat field, and classification was performed on species level with the weed species Matricaria chamomilla L., Papaver rhoeas L., Veronica hederifolia L., and Viola arvensis ssp. arvensis observed in that field. The ResNet-18 model with the optimized image-level prediction pipeline reached a performance of 2.2 frames per second with an NVIDIA Jetson AGX Xavier on the full resolution UAV image, which would amount to about 1.78 ha h−1 area output for continuous field mapping. The overall accuracy for determining crop, soil, and weed species was 94%. There were some limitations in the detection of species unknown to the model. When shifting from 16-bit to 32-bit model precision, no improvement in classification accuracy was observed, but a strong decline in speed performance, especially when a higher number of filters was used in the ResNet-18 model. Future work should be directed towards the integration of the mapping process on UAV platforms, guiding UAVs autonomously for mapping purpose, and ensuring the transferability of the models to other crop fields.
- ItemInvestigation on the potential of applying bio-based edible coatings for horticultural products exemplified with cucumbers(Amsterdam : Elsevier, 2022) Rux, G.; Labude, C.; Herppich, W.B.; Geyer, M.Plastic packaging for fresh horticultural produce has many advantages but generates plastic waste and ecological alternatives are required. Edible coatings can retard many processes related to loss of quality. Hydrophobic lipid-based coatings are preferably applied for fresh fruits and vegetables. The approval of such coatings for products with edible peels in EU is increasingly under discussion. However, investigations on the efficiency of various edible coatings on soft-skinned fruit and vegetables are rare and it is currently unclear whether the consumer will accept them. Therefore, this study investigates (1) important characteristics of a lipid-based coating and (2) its ability to maintain the post-harvest quality of fresh cucumbers. This was evaluated by a comparative storage test under common suboptimal retail conditions (20 °C; 65% RH). The study also evaluates (3) the general perception of consumers about and their acceptance of the application of edible coatings on fresh fruit and vegetables with edible peels. The investigated coating was able to drastically reduce water loss (54–68%) and fruit respiration (approx. 33%) of fresh cucumber. The reduction of tissue stiffness was delayed by 2 days, thus, prolonged shelf life. Majority of consumer (77%) endorse the application of edible coatings as an alternative to plastic packaging, but emphasized important requirements for them.
- ItemSensor-based detection of the severity of hyperkeratosis in the teats of dairy cows(Basel : MDPI AG, 2018) Demba, S.; Hoffmann, G.; Ammon, C.; Rose-Meierhöfer, S.The aim of this study was to evaluate whether the severity of hyperkeratosis (HK) in the teats of dairy cows can be assessed by a dielectric measurement. The study focused on surveying the occurrence of hyperkeratosis in a total of 241 teats of lactating dairy cows. A scoring system consisting of four categories was used to macroscopically assess the severity of HK. Additionally, the dielectric constant (DC) of all teats with milkability was measured in a double iteration with the MoistureMeterD (Delfin Technologies, Kuopio, Finland) on four different days. The Spearman rank correlation coefficient revealed a negative correlation between the DC and HK score (rs = −0.55 to −0.36). The results of the regression analysis showed that the DC values differed significantly between healthy teat ends (≤2) and teat ends with HK (≥3). Thus, the non-invasive measurement of DC provides a promising method of objectively assessing the occurrence and severity of HK.
- ItemApplication of Absorption and Scattering Properties Obtained through Image Pre-Classification Method Using a Laser Backscattering Imaging System to Detect Kiwifruit Chilling Injury(Basel : MDPI AG, 2021) Yang, Zhuo; Li, Mo; East, Andrew R.; Zude-Sasse, ManuelaKiwifruit chilling injury (CI) damage occurs after long-term exposure to low temperature. A non-destructive approach to detect CI injury was tested in the present study, using a laser backscattering image (LBI) technique calibrated with 56 liquid phantoms for providing absorption coefficient (µa) and reduced scattering coefficient (µs’). Calibration of LBI resulted in a true-positive (TP) classification of 91.5% and 65.6% of predicted µs’ and µa, respectively. The optical properties of ‘SunGold™’and ‘Hayward’ kiwifruit were analysed at 520 nm with a two-step protocol capturing pre-classification according to the LBI parameters used in the calibration and estimation with the Farrell equation. Severely injured kiwifruit showed white corky tissue and water soaking, reduced soluble solids content and firmness measured destructively. Non-destructive classification results for ‘SunGold™’ showed a high percentage of TP for severe CI of 92% and 75% using LBI parameters directly and predicted µa and µs’ after pre-classification, respectively. The classification accuracy for severe CI ‘Hayward’ kiwifruit with LBI parameter was low (58%) and with µa and µs’ decreased further (35%), which was assumed to be due to interference caused by the long trichomes on the fruit surface.
- ItemAn extended hybrid input-output model applied to fossil- and bio-based plastics(Amsterdam [u.a.] : Elsevier, 2021) Jander, WiebkeMatrix augmentation method is developed further and described transparently for enabling more specific input-output analyses of bio- vs. fossil-based sectors. A number of economic and environmental effects of substitution can be estimated, compared, and managed. While the model was applied for the first time to the German plastics industry, it can be well integrated into existing bioeconomy monitorings to represent substitution in sectors and countries. • Original matrix augmentation method is described in much detail for the first time considering available data for bio- and fossil-based industries. • Particular attention is paid to balancing cost and benefit in model building so that indicators can be integrated in a continuous monitoring of the bioeconomy. Hence, industry data is prefered to process data whenever possible. • Input structures of bio-based imports are considered in single-region input-output analysis.
- ItemInfluence of Processing Parameters on Fibre Properties during Twin-Screw Extrusion of Poplar Wood Chips(Basel : MDPI, 2022) Dittrich, Christian; Pecenka, Ralf; Selge, Benjamin; Ammon, Christian; Kruggel-Emden, HaraldFor sustainable agriculture, the contentious input of peat in growing media needs to be replaced by a substitute with the best possible water-holding capacity (WHC). Wood from fast growing poplar trees, cultivated in short rotation coppices (SRC), is a suitable alternative if it is processed correctly in a twin-screw extruder. The processing parameters, such as the aperture setting of the extruder, moisture content, and specific energy demand (SED), during twin-screw extrusion, as well as their influence on fibre properties such as WHC and particle size distribution, are investigated. SRC-poplar wood chips from clone Max3 are the raw material used for this research. As a result, the best volume-based WHC (75%) at −1 kPa suction tension was achieved for dry extruded wood chip fibre at an aperture setting of 15 mm and an SED of 340 kWh*t−1. The smallest SED of 140 kWh*t−1 was measured at apertures of 35 mm and 40 mm, which resulted in a volume-based WHC of approximately 30% and a dry matter mass flow during processing of 0.289 t*h−1 (40 mm). The particle size distribution of semi-dry wood chips has the highest fine fraction as well as the smallest coarse fraction. Conclusively, poplar wood can be processed fresh and dry into fibre at an acceptable SED, which results in an acceptable WHC.
- ItemEffects of the COVID-19 Pandemic on Food Security and Agriculture in Iran: A Survey(Basel : MDPI AG, 2021) Rad, Abdullah Kaviani; Shamshiri, Redmond R.; Azarm, Hassan; Balasundram, Siva K.; Sultan, MuhammadThe consequences of COVID-19 on the economy and agriculture have raised many concerns about global food security, especially in developing countries. Given that food security is a critical component that is affected by global crises, beside the limited studies carried out on the macro-impacts of COVID-19 on food security in Iran, this paper is an attempt to address the dynamic impacts of COVID-19 on food security along with economic and environmental challenges in Iran. For this purpose, a survey was conducted with the hypothesis that COVID-19 has not affected food security in Iran. To address this fundamental hypothesis, we applied the systematic review method to obtain the evidence. Various evidences, including indices and statistics, were collected from national databases, scientific reports, field observations, and interviews. Preliminary results revealed that COVID-19 exerts its effects on the economy, agriculture, and food security of Iran through six major mechanisms, corresponding to a 30% decrease in the purchasing power parity in 2020 beside a significant increase in food prices compared to 2019. On the other hand, the expanding environmental constraints in Iran reduce the capacity of the agricultural sector to play a crucial role in the economy and ensure food security, and in this regard, COVID-19 forces the national programs and budget to combat rising ecological limitations. Accordingly, our study rejects the hypothesis that COVID-19 has not affected food security in Iran.
- ItemDevelopment of Biorefineries in the Bioeconomy: A Fuzzy-Set Qualitative Comparative Analysis among European Countries(Basel : MDPI, 2021) Ding, Zhengqiu; Grundmann, PhilippThis study aims to identify the configurational conditions that characterize the establish-ment of biorefineries in 20 European countries. After determining the conditions which support a bioeconomy transition, secondary data from national sources are used to represent their existing conditions within respective countries. Then, a fuzzy-set qualitative comparative analysis is em-ployed to compare and contrast the effect of varying combinations of the selected conditions on the development of biorefineries. The conditions chosen include coherent bioeconomy strategies, network intensity of regional bioclusters, intellectual capital, and natural resource availability. Our results reveal that the configuration of a coherent bioeconomy strategy, sizable public spending on R&D, abundant biomass supply, and a high level of network intensity is sufficient to explain the pro-nounced biorefineries development among some European countries. We recommend that countries with fragmented approaches review and redesign the policy and regulatory framework to create a holistic and consistent bioeconomy strategy, taking into account the configurations of conditions as an important prerequisite. In particular, factors such as the lack of best practice examples, the low level of public spending on research and development, the economic capacities for a skilled workforce in addition to the sustainable supply of raw materials should be addressed as focal points.
- ItemCan Green Plants Mitigate Ammonia Concentration in Piglet Barns?(Basel : MDPI, 2021) Menardo, Simona; Berg, Werner; Grüneberg, Heiner; Jakob, MartinaFor animal welfare and for farmers’ health, the concentration of ammonia (NH3 ) in animal houses should be as low as possible. Plants can remove various atmospheric contaminants through the leaf stomata. This study examined the effect of ornamental plants installed inside a piglet barn on the NH3 concentration in the air. Gas measurements of the air in the ‘greened’ compartment (P) and a control compartment (CTR) took place over two measuring periods (summer–autumn and winter). Differences between the NH3 emissions were calculated based on the ventilation rates according to the CO2 balance. Fairly low mean NH3 concentrations between 2 and 4 ppm were measured. The NH3 emissions were about 20% lower (p < 0.01) in P than in CTR, in summer–autumn and in winter period. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
- ItemEstimation of Vegetative Growth in Strawberry Plants Using Mobile LiDAR Laser Scanner(Basel : MDPI, 2022) Saha, Kowshik Kumar; Tsoulias, Nikos; Weltzien, Cornelia; Zude-Sasse, ManuelaMonitoring of plant vegetative growth can provide the basis for precise crop manage-ment. In this study, a 2D light detection and ranging (LiDAR) laser scanner, mounted on a linear conveyor, was used to acquire multi-temporal three-dimensional (3D) data from strawberry plants (‘Honeoye’ and ‘Malling Centenary’) 14–77 days after planting (DAP). Canopy geometrical variables, i.e., points per plant, height, ground projected area, and canopy volume profile, were extracted from 3D point cloud. The manually measured leaf area exhibited a linear relationship with LiDAR-derived parameters (R2 = 0.98, 0.90, 0.93, and 0.96 with number of points per plant, volume, height, and projected canopy area, respectively). However, the measuring uncertainty was high in the dense canopies. Particularly, the canopy volume estimation was adapted to the plant habitus to remove gaps and empty spaces in the canopy point cloud. The parametric values for maximum point to point distance (Dmax) = 0.15 cm and slice height (S) = 0.10 cm resulted in R2 = 0.80 and RMSPE = 26.93% for strawberry plant volume estimation considering actual volume measured by water displacement. The vertical volume profiling provided growth data for cultivars ‘Honeoye’ and ‘Malling Centenary’ being 51.36 cm3 at 77 DAP and 42.18 cm3 at 70 DAP, respectively. The results contribute an approach for estimating plant geometrical features and particularly strawberry canopy volume profile based on LiDAR point cloud for tracking plant growth.