Search Results
Deep Learning Object Detection for Image Analysis of Cherry Fruit Fly (Rhagoletis cerasi L.) on Yellow Sticky Traps
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
Methods for Recognition of Colorado Beetle (Leptinotarsa decemlineata (Say)) with Multispectral and Color Camera-sensors
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.
Improving Deep Learning-based Plant Disease Classification with Attention Mechanism
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.
DATAMAN: A global database of nitrous oxide and ammonia emission factors for excreta deposited by livestock and land-applied manure
Nitrous oxide (N2 O), ammonia (NH3 ), and methane (CH4 ) emissions from the manure management chain of livestock production systems are important contributors to greenhouse gases (GHGs) and NH3 emitted by human activities. Several studies have evaluated manure-related emissions and associated key variables at regional, national, or continental scales. However, there have been few studies focusing on the drivers of these emissions using a global dataset. An international project was created (DATAMAN) to develop a global database on GHG and NH3 emissions from the manure management chain (housing, storage, and field) to identify key variables influencing emissions and ultimately to refine emission factors (EFs) for future national GHG inventories and NH3 emission reporting. This paper describes the "field" database that focuses on N2 O and NH3 EFs from land-applied manure and excreta deposited by grazing livestock. We collated relevant information (EFs, manure characteristics, soil properties, and climatic conditions) from published peer-reviewed research, conference papers, and existing databases. The database, containing 5,632 observations compiled from 184 studies, was relatively evenly split between N2 O and NH3 (56 and 44% of the EF values, respectively). The N2 O data were derived from studies conducted in 21 countries on five continents, with New Zealand, the United Kingdom, Kenya, and Brazil representing 86% of the data. The NH3 data originated from studies conducted in 17 countries on four continents, with the United Kingdom, Denmark, Canada, and The Netherlands representing 79% of the data. Wet temperate climates represented 90% of the total database. The DATAMAN field database is available at http://www.dataman.co.nz.
Establishment of a Laboratory Scale Set-Up with Controlled Temperature and High Humidity to Investigate Dry Matter Losses of Wood Chips from Poplar during Storage
The aim of this work was to improve the understanding of dry matter losses (DML) that occur in wood chips during the initial phase of storage in outdoor piles. For this purpose, a laboratory scale storage chamber was developed and investigated regarding its ability to recreate the conditions that chips undergo during the initial phase of outdoor storage. Three trials with poplar Max-4 (Populus maximowiczii Henry Populus nigra L.) chips were performed for 6–10 weeks in the storage chamber under controlled temperature and assisted humidity. Two different setups were investigated to maintain a high relative humidity (RH) inside the storage chamber; one using water containers, and one assisted with a humidifier. Moisture content (MC) and DML of the chips were measured at different storage times to evaluate their storage behaviour in the chamber. Additionally, microbiological analyses of the culturable fraction of saproxylic microbiota were performed, with a focus on mesophilic fungi, but discriminating also xerophilic fungi, and mesophilic bacteria, with focus on actinobacteria, in two trials, to gain a view on the poplar wood chip-inhabiting microorganisms as a function of storage conditions (moisture, temperature) and time. Results show that DML up to 8.8–13.7% occurred in the chips within 6–10 storage weeks. The maximum DML were reached in the trial using the humidifier, which seemed a suitable technique to keep a high RH in the testing chamber, and thus, to analyse the wood chips in conditions comparable to those in outdoor piles during the initial storage phase.
A Pixel-wise Segmentation Model to Identify Bur Chervil (Anthriscus caucalis M. Bieb.) Within Images from a Cereal Cropping Field
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.
Ammonia and nitrous oxide emission factors for excreta deposited by livestock and land-applied manure
Manure application to land and deposition of urine and dung by grazing animals are major sources of ammonia (NH3 ) and nitrous oxide (N2 O) emissions. Using data on NH3 and N2 O emissions following land-applied manures and excreta deposited during grazing, emission factors (EFs) disaggregated by climate zone were developed, and the effects of mitigation strategies were evaluated. The NH3 data represent emissions from cattle and swine manures in temperate wet climates, and the N2 O data include cattle, sheep, and swine manure emissions in temperate wet/dry and tropical wet/dry climates. The NH3 EFs for broadcast cattle solid manure and slurry were 0.03 and 0.24 kg NH3 -N kg-1 total N (TN), respectively, whereas the NH3 EF of broadcast swine slurry was 0.29. Emissions from both cattle and swine slurry were reduced between 46 and 62% with low-emissions application methods. Land application of cattle and swine manure in wet climates had EFs of 0.005 and 0.011 kg N2 O-N kg-1 TN, respectively, whereas in dry climates the EF for cattle manure was 0.0031. The N2 O EFs for cattle urine and dung in wet climates were 0.0095 and 0.002 kg N2 O-N kg-1 TN, respectively, which were three times greater than for dry climates. The N2 O EFs for sheep urine and dung in wet climates were 0.0043 and 0.0005, respectively. The use of nitrification inhibitors reduced emissions in swine manure, cattle urine/dung, and sheep urine by 45-63%. These enhanced EFs can improve national inventories; however, more data from poorly represented regions (e.g., Asia, Africa, South America) are needed.
Water productivity of poultry production: The influence of different broiler fattening systems
With the expected increase in poultry meat consumption water use will increase as well. The objective of this study is to quantify the effects of fattening systems on the water productivity in broiler chicken production with consideration given to conditions in Germany. Four fattening systems were analyzed in terms of water use for feed production, drinking, cleaning, and the parent stock. The fattening systems differed in intensity, ranging from fast fattening with a fattening period of 30 days and a carcass weight of 1.1 kg to slow fattening with a period up to 46 days and a carcass weight of 2.1 kg. During the fattening period the broiler chicken were fed with performance-linked feed. The water productivity of the feed components varied from 0.4 kg dry mass per m3 water input for soybean meal to 1.8 kg dry mass per m3 water input for maize. In all fattening systems the water input for feed production accounted for 90 to 93% of the total water input. The share for the parent stock was 7 to 10%, while drinking and cleaning water accounted for less than 1%. For all fattening systems the water productivity was 0.3 kg carcass weight per m3 water input, 2.8 MJ food energy per m3 water input and 57 g food protein per m3 water input. The shorter fattening period and lower feed demand in the more intensive fattening systems were juxtaposed to the higher carcass weight and higher water productivity of the feed components in the more extensive systems.