查看更多>>摘要：? 2022As there are many links in the cold chain logistics process, which takes a long time, the processed aquatic products are easily damaged and deteriorated. And the growth and reproduction of microorganisms in aquatic products can be inhibited by MA (Modified Atmosphere) preservation, thus extending the shelf life of aquatic products. In this context, we have developed an automatic gas dynamic volumetric system for aquatic products' MA preservation. It can control the operation platform by a 4G network cell phone client and realize remote monitoring function. Particularly, there are the main contents and conclusions of the study: 1) Combined with MA preservation, intelligent control and network communication technologies, we overcame the difficulties of remote monitoring for gas dynamic volumetric. Then, according to MA preservation and automatic gas dynamic volumetric, we designed a logical structure of the system, including the specific distribution of the sensing layer, network transmission layer and application layer. 2) We established the mathematical model for the system based on the step response method, and designed the analog acquisition, control and gas dynamic volumetric system; In addition, in this system, we realized the gas dynamic volumetric based on the embedded PID control algorithm and mass flow controller; Then, we used 4G network for remote data transmission and 4G DTU as network data transceiver, and realized remote monitoring function of mobile client through cell phone terminal applet software. 3) The results were shown by testing the stability, accuracy and communication of the system: the gas concentration error of the system floated at ± 0.25% when the gas dynamic volumetric system was stable, which was 12 times more accurate than before, and the gas dynamic volumetric speed based on embedded PID control algorithm was increasing by approximately about 50%, which greatly improved the working conditions and production efficiency.
查看更多>>摘要：? 2022Pests and diseases are the two primary reasons for poor crop yields. Farmers have traditionally relied on manual methods to identify pests and diseases, which is time-consuming and costly. The Internet and pervasiveness of camera-enabled mobile devices, however, have made image acquisition more convenient and cheaper than ever before, and have launched a wave of research into how to use deep learning models to recognize pests and diseases in field. However, the datasets used in these studies were customized for only one or a few crop types. ImageNet pre-trained models were usually adopted to obtain high accuracy, regardless of the attributes of the target image datasets. A more comprehensive image dataset of crop pests and diseases was created. Transfer learning based on this disease and pest image dataset (TLDP) was compared with ImageNet pre-training. From experiments, we observed that TLDP has a similar effect to ImageNet pre-training. In addition, the performance of transfer learning largely depended on model performance on the source image dataset. To further improve the accuracy of TLDP, a novel convolutional neural network backbone called Decoupling-and-Attention network (DANet) was developed. DANet trained with the TLDP method achieved the highest classification accuracy on a strawberry pests and diseases image dataset (96.79%), followed by ImageNet pre-trained ResNet-50 (96.56%). In terms of computational cost, DANet was only a quarter of ResNet-50. The pre-trained DANet was also tested on other open pests and diseases image datasets. It still shows comparable performance to ImageNet pre-trained models.
查看更多>>摘要：? 2022 Elsevier B.V.Estimating site-specific crop yield response to changes to input (e.g., seed, fertilizer) management is a critical step in making economically optimal site-specific input management recommendations. Past studies have attempted to estimate yield response functions using various Machine Learning (ML) methods, including the Random Forest (RF), Boosted Random Forest (BRF), and Convolutional Neural Network (CNN) methods. This study proposes use of the Causal Forest (CF) model, which is one of the emerging ML methods that comprise “Causal Machine Learning.” Unlike previous yield-prediction-oriented ML methods, CF focuses strictly on estimating heterogeneous treatment effects (changes in yields that result from changes in input application rates) of inputs. We report results of using Monte Carlo simulations assuming various production scenarios to test the effectiveness of CF in estimating site-specific economically optimal nitrogen rates (EONRs), comparing CF with the yield-prediction-oriented ML methods RF, BRF, and CNN. CF's estimations of site-specific EONRs were superior under all scenarios considered. We also show that the model's yield prediction accuracy need not imply EONR prediction accuracy.
查看更多>>摘要：? 2022 The Author(s)Symbiotic di-nitrogen fixation of grain legumes has a substantial impact on crop performance, harvest product quality, and nitrogen (N) balance of crop rotations, particularly under organic management regimes. In soybean breeding, selection for increased nitrogen fixation is desirable for improving seed protein content and N balance of cropping systems. However, the lack of high-throughput screening methods for direct measurement of N2 fixation rates prohibits practical breeding efforts. Therefore, hyperspectral canopy reflectance measurement as a field-based phenotyping method was evaluated in three environments for indirect estimation of N fixation and uptake of soil nitrogen in a set of early maturity soybean genotypes exhibiting a wide range in seed protein content. Reflectance spectra were collected in repeated measurements during flowering and early seed filling stages. Subsequently, various spectral reflectance indices (SRIs) were calculated for characterizing nitrogen accumulation of individual genotypes. Moreover, prediction models for seed protein content as an end-of-season target trait were developed utilizing full spectral information in partial-least-square regression (PLSR) models. A number of N-related SRIs calculated from spectral reflectance data recorded at the beginning of the seed filling stage were significantly correlated to seed protein content. The best prediction of seed protein content, however, was achieved in PLSR models (validation R2 = 0.805 across all three environments). Environments lower in initial soil mineral N content appeared as more favorable selection sites in terms of prediction accuracy, because N fixation is not masked by soil N uptake in such environments. Hyperspectral reflectance data proved to be a valuable method for determining genetic variation in crop N accumulation, which might be implemented in high-throughput screening protocols for N fixation in plant breeding programs.
查看更多>>摘要：? 2022 Elsevier B.V.The paddy field blade is a key component in the machinery of transplanting rice cultivation. The mud splashing efficiency and power consumption are closely related to the number of blades. Therefore, optimizing the number of paddy field blades is helpful to improve the efficiency of this transplanter and reduce its power consumption. However, this research faces great challenges due to the specific geometry of the blade, unfamiliar mud properties, and few references. In this paper, a method was proposed to calculate the dynamic splashed mud quantity based on kinematics and the motion path of the blade. Mechanics analysis, the Bingham fluid property, and the law of conservation of energy were applied to resolve the power consumption of the rice sprout transplanter machinery related to the splashed mud. With the proposed method, the number of paddy field blades, the efficiency, and the power consumption were all researched during the mud throwing period. An experiment investigating the efficiency and power consumption of mud splashing with the control variables method was designed to verify and modify the theoretical model. Then, the proposed method, CFD simulation, and experimental methods were applied to calculate the volume of splashed mud and power consumption. The results of the research show that the modified theoretical model is accurate and reveals the law between the number of paddy field blades, the efficiency of mud splashing, and power consumption for the transplanting machinery.
查看更多>>摘要：? 2022It has been estimated that up to a third of all rams have little to no sexual interest in ewes. Despite the prevalence of this issue, it is challenging to monitor the reproductive behaviour of individual sheep in an extensive farming environment. In this study, we developed a single-feature algorithm to detect in-paddock mounting activity from the accelerometer records of rams and androgenised wethers. Tri-axial accelerometers were first deployed on the necks and withers of the rams (n = 15) in a controlled pen test to determine the optimal attachment point for detecting mounting events. A Moving Average Convergence Divergence (MACD) algorithm was applied to accelerometer data with a threshold of 0.3 g. Validation and performance evaluation of the algorithm was based on observed video footage. The MACD was more sensitive and precise when applied to data collected from the withers than the neck (100% vs 89%; 98% vs 86%; respectively). Following the pen test, the MACD was applied to data collected in-paddock from accelerometers attached to the withers of rams (n = 6) and androgenised wethers (n = 8). A MACD + was simultaneously evaluated, which included additional conditions that must be satisfied for the detected peak to be deemed a mounting event. For both algorithms, a series of thresholds were tested. The threshold that returned the highest F1 score (the harmonic mean of precision and sensitivity) for the respective algorithm and male type was selected as the optimal threshold. At their respective optimal thresholds, the MACD + was marginally more precise than the MACD in-paddock for both wethers (91% vs 84%, respectively) and rams (94% vs 84%, respectively). The sensitivity of the MACD in detecting in-paddock mounting behaviour was 91% in rams and 86% in wethers. The MACD + was similarly sensitive at 91% for both rams and wethers. This research demonstrates the success of this algorithm, particularly the MACD+, in detecting mounting activity. Following integration into a commercial sensor and further validation, this algorithm would allow producers to identify rams with low libido and improve reproduction and productivity.
查看更多>>摘要：? 2022 Elsevier B.V.Agricultural environments with tree plantations usually present a regular structure that can be used by SLAM systems to improve self-location, and therefore, facilitate the autonomous navigation. In this context, tree trunks are natural landmarks that can be used to incorporate the environment structure into the problem modeling. This article presents a trunk detector solely based on RGB-D data obtained from a frontal-view stereo camera, and a SLAM system that incorporates the regular tree distribution of these crops. The trunk detector can be adapted to similar agricultural environments because its parameters have specific geometric meanings, which differentiates it from black box-type procedures. The structure-based SLAM system has theoretical and practical advantages over the well-known SLAM procedures in the mentioned context. This proposal can be executed on-line and is experimentally tested with databases obtained from a challenging agricultural environment. Results show a good performance and robustness when the database is spatially or temporally subsampled, even under adverse lighting conditions.
查看更多>>摘要：? 2022 Elsevier B.V.Accurate estimation of fingerlings quantity is one of the most challenging aspects of aquaculture, relevant simple and efficient solutions, however, are still lacking. To address this problem, an accurate and practical on-line counting method for 2–8 cm fingerlings, which was simple to implement, computational inexpensively (without huge pre-training like that in deep learning), and suitable for five different kinds of fingerlings, based on fish kinematics characteristics was proposed in this study. First, the kinematic model of the fingerlings for motion prediction was constructed based on the analysis of their kinematics characteristics; secondly, adaptive threshold segmentation (ATS) algorithm was used to segment and detect the fingerlings; and then, the fingerlings in previous and current frames were associated and tracked by using the kinematic model and the probability density function (PDF). Following this, the new fingerlings were identified and counted in real-time. Finally, through the exhaustive test on 102 datasets (acquired with a low frame rate (10 fps)), the present method showed the average counting accuracy rate (ACAR) and standard deviation (SD) of more than 98.78% and less than 0.95%, respectively. Specifically, the ACAR of Pseudosciaena Crocea (2–3 cm) and Ctenopharyngodon idellus (3–5 cm, 6–8 cm) exceeded 99.19%, and the corresponding SD was less than 0.59%.
查看更多>>摘要：? 2022 The Author(s)Digital Twins can be considered as a new phase in smart and data-driven greenhouse horticulture. A Digital Twin is a digital equivalent to a real-life object of which it mirrors its behaviour and states over its lifetime in a virtual space. Research indicates that they can substantially enhance productivity and sustainability, and are able to deal with the increasing scarcity of green labour in greenhouse horticulture. This paper presents the results of a systematic literature review on Digital Twin applications in greenhouse horticulture. The review identifies 8 articles that explicitly address Digital Twins in greenhouse horticulture and 115 studies that implicitly apply the Digital Twin concept in smart IoT-based systems. Findings indicate that the concept of the Digital Twin is in a seminal phase in greenhouse horticulture, but there are existing applications that are not yet framed as Digital Twins. In the reviewed papers, there is a dominant focus on the cultivation process at the greenhouse level, among others for climate control, energy management and lighting. About 9% of the articles are virtualizing plants themselves, which indicates that the granularity level addressed is still rather limited. Only 7 % of the articles look beyond plants or single greenhouses. None of the reviewed articles consider the company level. Furthermore, most applications address monitoring and control of the state and behaviour of real-life objects. More advanced applications, including predictive and prescriptive capabilities across the complete lifecycle, are still in an early stage of development, although predictive Digital Twins are gaining prominence.
查看更多>>摘要：? 2022 Elsevier B.V.The measurement of tree diameter at breast height (DBH) is the basis for estimating forest timber volume, biomass, and carbon fluxes. The traditional contact methods of measuring DBH are time-consuming and labor-intensive. Thus, it is important to realize a low-cost and rapid method for measuring DBH. In this paper, a non-contact method was proposed by integrating passive (a smartphone) and active optical sensors (a laser ranger). With this device, the horizontal distance from the sensor to the tree trunk acquired by the laser ranger and the image of the target tree acquired by the smartphone were collected simultaneously. An autodetection algorithm was employed to identify the tree trunk within the image, and the diameter of the tree was then measured in combination with the horizontal distance based on the photogrammetry principle. The performance of the proposed method was validated using measuring tapes across 371 trees, the main species of which were Italian Poplar (Populus euramevicana) and Pine (Pinus tabuliformis) with diameters ranging from 6 to 51 cm. To investigate the factors that might affect the method, the results were further analyzed under four different conditions, i.e., varied illumination conditions, urban and natural forest conditions and different tree species with varied surface texture features. The results suggested that the measurements using the proposed device were in good agreement with those of the traditional contact method, with an absolute mean error (MAE) of 1.12 cm and RMSE of 1.55 cm. The attraction of the proposed method is that it is low-cost, portable, easy to use and sufficiently accurate. It is also expected that the proposed method can facilitate the measurement of DBH-related canopy structure parameters, such as tree volume, and other parameters, such as tree height, with little adaptation to the current version.
NSTL
Elsevier