Keywords: Pest and Disease Detection Management
Abstract: Greenhouse whitefly (Trialeurodes vaporariorum) is a major insect pest of greenhouse crops. To prevent the damage caused by whiteflies, farmers control the population of whiteflies by spraying pesticides in a regular basis. However, pesticides are costly and may affect the environment and health of farmers. To provide a more efficient way for applying pesticides, this research aims to develop a model for predicting the possible increase in whitefly population in greenhouses using autoregressive integrated moving average (ARIMA) and ARIMA with exogenous variables (ARIMAX). The data used in this work were collected using wireless imaging devices that can monitor the number of whiteflies trapped on sticky paper traps using an automatic insect counting algorithm. The wireless imaging devices were installed in a greenhouse that grew tomato seedlings, which is one of the host plants of whiteflies. The ARIMA and ARIMAX models were compared by setting different combinations of input data. Particularly, ARIMA includes only the whitefly count while ARIMAX includes the whitefly count and environmental data. Based on preliminary testing, the minimum number of input data was found to be at around 60 days to 90 days. ARIMAX was found to be the best model with input data including the increase in whitefly counts, temperature and humidity. In average, the RMSE for 7-day forecasting of the proposed method was found to be around 1.30. To assist farmers in decision-making for pesticide application scheduling, four levels of increase in whitefly count were defined such as Normal, Moderate, High, and Critical, which were determined using K-means clustering algorithm, and testing results on a testing dataset show an F1-scores of 0.86 and 0.42 for Normal and Moderate levels of daily increase in whitefly count.

Keywords: Pest and Disease Detection Management, Sensing, Automation and Robotics in Plant Factory, Protected Cultivation and Greenhouses, Automation and Robotics in Agriculture
Abstract: Potato blackleg is a tuber-borne bacterial disease caused by species within the genera Dickeya and Pectobacterium that can cause decay of plant tissue and wilting through the action of cell wall degrading enzymes released by the pathogen. In case of serious infections, tubers may rot before emergence. Management is largely based on the use of pathogen-free seed potato tubers. For this, fields are visually monitored both for certification and also to take out diseased plants to avoid spread to neighboring plants. Imaging potentially offers a quick and non-destructive way to inspect the health of potato plants in a field. Early detection of blackleg diseased plants with modern vision techniques can significantly reduce costs. In this paper, we studied the use of deep learning for detecting blackleg diseased potato plants. Two deep convolutional neural networks were trained on RGB images with healthy and diseased plants. One of these networks (ResNet18) was experimentally found to produce a precision of 95 % and recall of 91 % for the disease class. These results show that convolutional neural networks can be used to detect blackleg diseased potato plants.

Keywords: Pest and Disease Detection Management, Automation and Robotics in Agriculture, Crop Monitoring
Abstract: Tulip crop production in the Netherlands suffers from severe economic losses caused by virus diseases such as the Tulip Breaking Virus (TBV). Infected plants which can spread the disease by aphids must be removed from the field as soon as possible. As the availability of human experts for visual inspection in the field is limited, there is an urgent need for a rapid, automated and objective method of screening. From 2009-2012, we developed an automatic machine-vision based system, using classical machine-learning algorithms. In 2012, the experiment conducted a tulip field planted at production density of 100 and 125 plants per square meter, resulting in images with overlapping plants. Experiments based on multispectral images resulted in scores that approached results obtained by experienced crop experts. The method, however, needed to be tuned specifically for each of the data trails, and a NIR band was needed for background segmentation. Recent developments in artificial intelligence and specifically in the area of convolutional neural networks, allow the development of more generic solutions for the detection of TBV. In this study, a Faster R-CNN network is applied on part of the data from the 2012 experiment. The outcomes show that the results are almost the same compared to the previous method using only RGB data.

Keywords: Pest and Disease Detection Management, Machine Vision and Robotics for Crop Harvesting, Automation and Robotics in Agriculture
Abstract: Pest bird detection, classification, and recognition in vineyard environment are challenging because of their varying shapes, small size, movement, and outdoor environment. Motion is often used to detect flying birds in outdoor environment from video sequences. However, motion detection is sensitive to noise as well as background movement of leaves and give rise to false detection. The high-quality image resolution is desired for performance improvement in pattern recognition and analysis. This work presents the integration of superresolution technology to enhance quality of small moving objects which were later on classified as birds or false positives using deep learning. Implementation of the super-resolution enhanced the image resolution which offers high pixel density and more details about the scene. With the implementation of super-resolution, the CNN-based classifier received enhanced feature information to perform more informed decision in classifying birds. The classification accuracy shows a significant rise from 70% to more than 90% after resolution enhancement. Results also show that the model trained with combined varying spatial resolution for the same set of images performs almost equally over any spatial resolution.

Keywords: Automation and Robotics in Agriculture, Machine Vision and Robotics for Crop Harvesting, Sensing, Automation and Robotics for Post-Harvest/Processing
Abstract: Carrot grading is a labor-intensive and time-consuming task. In order to improve the efficiency and effect of carrot grading, algorithms were proposed to extract the key parameters of surface defects such as green-shoulder, bending, fibrous root, surface cracked and broken based on machine vision. The detection algorithm of green-shoulder is obtained by binarizing the H component. The recognition of bending carrots is realized by extracting the skeleton of the carrot on the H component and the shape of the skeleton. The detection of fibrous root is realized by the slope of carrot edges on S component. And the algorithm of surface cracked detection is gotten by binarization on G subtract B component. Broken carrots is detected by calculating the slope of carrot ends’ edges on H component. On these bases, five quantitative indicators, i.e. green shoulder ratio, bending degree, fibrous root number, surface cracked degree and broken degree, are defined. 720 carrot images selected randomly were tested. The experimental results show that the correct rate is 97.4%, 85.4%, 92.6%, 80.8% and 93.2% respectively, and the overall recognition rate is 90.9%. The algorithm proposed in this paper has positive significance for the following carrot surface defect detection and on-line classification.

Keywords: Sensing, Automation and Robotics for Post-Harvest/Processing, Automation and Robotics in Agriculture, Machine Vision and Robotics for Crop Harvesting
Abstract: Carrot grading is a crucial part in the carrot processing and marketing. At present, the grading of carrots mainly depends on manual grading, which is labor intensive and low efficient In this paper, six shape parameters of carrot, including length, maximum diameter, average diameter, area, perimeter and aspect ratio, and six color parameters on R, G, B, H, S and V components were extracted by machine vision. Taking these 12 parameters as input feature parameters, the grading recognition models of back propagation neural network (BPNN), support vector machine (SVM) and extreme learning machine (ELM) are constructed, and compared by the recognition effects. The results show that the image acquisition system constructed in this paper can extract the feature parameters of carrot accurately. As a simple and easy to solve algorithm, the ELM model based on shape and color parameters has the best recognition effect and the recognition accuracy reaches 96.67%. It provides a reference classification method of carrots by digital.

Keywords: Automation and Robotics in Agriculture, Soil, Plant and Environment Sensing, Precision Agriculture and Variable Rate Technologies
Abstract: Abstract: The measurement of soil conductivity is generally based on the theory of current-voltage four-terminal method. On the basis of the above-mentioned principle, field experiments and laboratory experiments were carried out with a soil conductivity meter developed based on ARM and a portable oscilloscope conductivity meter. The soil conductivity meter based on ARM is mainly composed of ARM, GPS, signal generating circuit and signal conditioning circuit. The differential circuit is introduced to improve the measurement accuracy by enhancing the feedback signal and suppressing the input of noise signal. Portable oscilloscope conductivity meter is composed of portable oscilloscope, signal generating circuit, signal conditioning circuit and computer display software. The main oscilloscope uses DSCope C20P, a digital oscilloscope based on USB developed by DreamSourceLab, which has excellent performance in waveform processing and data prefetching. The experimental data of the two instruments are compared with the laboratory measurements. The EC values obtained by portable oscilloscope soil conductivity meter were scattered with laboratory EC values after removing the points seriously affected by noise and experimental errors, and R2=0.6299 was obtained. The EC value obtained by ARM soil conductivity meter was used to get the scatter plot after removing the points seriously affected by noise and experimental errors, and R2 = 0.5057 was obtained. The experimental results show that the accuracy of the portable oscilloscope conductivity meter is significantly higher than that of the soil conductivity meter based on ARM.

Keywords: Precision Agriculture and Variable Rate Technologies, Wireless Sensor Network
Abstract: In this article, a variable rate liquid fertilizer applicator for deep-fertilization based on ZigBee technology was elaborated. A host computer with remote control software and a STM32F103RET6 microcontroller were combined to measure and control the liquid fertilizer output: monitoring the liquid fertilizer level and collection the liquid flow information by the flow meter, and an incremental PID control algorithm was used to dynamically adjust the converter frequency for reaching the set liquid fertilizer flow accurately. Through the field test, the influence of parameters, such as fertilization depth, frequency of inverter, pressure of fertilizer injection, and the valve opening for water return of liquid fertilizer pump, on precise flow control is analyzed, and the mathematical model is established by using experimental data. The results showed that, the applicator accuracy is able to reach 99.52% and the liquid fertilizer consumption in each fertilization process is within 0.2L.min-1, with the fertilizer application depth changing, the maximum flow output difference is within 0.2L.min-1 and the inverter frequency difference is within 1Hz. When the valve opening for back water is 40%, the system works most stable and the flow output error is the smallest.

Keywords: Robust Control Systems for Agriculture
Abstract: Rice seed soaking and germination is a crucial process before sowing in the cold area where rice is widely cultivated. Temperature controller of rice seed soaking and germination device requires a high performance in precision and stability, for the quality of soaking and germination has a great influence on the cereal yield. In this paper, grey-box model combined with sliding mode control (SMC) method was designed for rice seed soaking and germination device. The grey-box based sliding mode controller was simulated in Matlab based on a nonlinear auto regressive external (ARX) model of the device, performance of different control parameters were compared. Comparative study of a SMC controller, a proportional-integral-derivative (PID) controller, and the proposed scheme was carried out. The results showed that the grey-boxed based sliding mode controller had a superior performance, due to its faster convergence and stability. The experimental results showed that the proposed method achieved an expected soaking and germination quality.

Keywords: Sensing and Automation for Precision Irrigation, Robust Control Systems for Agriculture, Decision Support Systems
Abstract: The productivity and financial success of large-scale arable farming operations depends highly on how effectively resources are distributed among fields. Therefore, it is of interest to develop methods to determine (near optimal) resource inputs. In this paper we focus on computing the optimal irrigation policy for large-scale arable farming operations, where the number of irrigation machinery is much smaller than the number of fields that require irrigation inputs. We propose a model predictive control (MPC) framework that simultaneously computes the optimal division of irrigation over the fields and which irrigation machines should be allocated to which fields, such that the profit at the end of the season is maximized. The fact that the optimization of irrigation and allocation of irrigation machinery is done simultaneously makes our approach vastly different from strategies available in the literature. Another important novelty of our work is that we link short-term effects of crop growth to long-term effects on profit. The proposed framework has reasonable computation times when optimizing on a daily basis over many fields and irrigation machines and guarantees a feasible solution. The main principles of our approach are more widely applicable. Using simulations we demonstrate the robustness of the scheme with respect to changes in weather and benchmark it with respect to a heuristic approach.

Keywords: Sensing and Automation for Precision Irrigation, Soil, Plant and Environment Sensing, Sensing and Automation with UAVs
Abstract: Water management is an important aspect in modern agriculture. Irrigation systems are becoming more and more complex, trying to minimize the water consumption while ensuring the necessities of the plants. A fundamental requirement to define efficient irrigation policies is to be able to estimate the water status of the plants and of the soil. In this context, precision agriculture addresses this problem by using the latest technological advancements. In particular, most of the works in the literature aim to develop highly accurate estimations under the assumption of the availability of a dense network of sensors. Although, this assumption may be adequate for intensive farming (e.g. greenhouses), it becomes quite unrealistic in the context of large-scale scenarios. In this work, we propose a novel observer-based architecture for the water management of large-scale (hazelnut) orchards which relies on a network of sparsely deployed soil moisture sensors along with a weather station and on remote sensing measurements carried out by drones with a pre-defined periodicity. The contribution is twofold: i) First a novel model of the water dynamics in an hazelnut orchard is proposed, which includes the water dynamics in the soil and in the plants, and ii) then, on the basis of this model and of the available measurements, the use of a Kalman filter with intermittent observations is proposed, taking also into account the availability of the weather station measurements. The effectiveness of the proposed solution is validated through simulation.

Keywords: Automation and Robotics in Agriculture, Machine Vision and Robotics for Crop Harvesting, Crop Yield Estimation/Monitoring/Mapping
Abstract: The objective of this work is to detect individual fruits and obtain pixel-wise mask for each detected fruit in an image. To this end, we presents a deep learning approach, named Deep Orange, to detection and pixel-wise segmentation of fruits based on the state-of-the-art instance segmentation framework, Mask R-CNN. The presented approach uses multi-modal input data comprising of RGB and HSV images of the scene. The developed framework is evaluated using images obtained from an orange grove in Citra, Florida under natural lighting conditions. The performance of the algorithm is compared using RGB and RGB+HSV images. Our preliminary findings indicate that inclusion of HSV data improves the precision to 0.9753 from 0.8947, when using RGB data alone. The overall F1 score obtained using RGB+HSV is close to 0.89.

Keywords: Internet of Things, Crop Systems/Canopy Architectures, Breeding and Genetics for Precision and Automated Agriculture
Abstract: Kiwifruit is widely planted in Shaanxi, China, accounting for approximately 70% of the local production, and 33% of the global. Harvesting kiwifruits in China relies mainly on manual picking, and it is labor-intensive. To develop a machine vision system for harvesting robot which can work all day, kiwifruit images were captured in an orchard at different timing, morning, afternoon, and night, with or without flash, respectively. Kiwifruit images of 2400 were divided into training (1440) and testing (960) groups. A Faster R-CNN model implemented by VGG16 were constructed and trained. The average precision of VGG16 model was 87.61%, and the kiwifruit images collected under different timing and lighting conditions were detected well. In the end, the performance of the proposed method was compared with ZFNet in the same image dataset. It suggested that the proposed method achieved higher detection average precision than ZFNet (72.50%). This system is able to detect different categories of fruit in the field effectively and provides strong support for the harvesting robot, which can work all day round during the busy season.

Keywords: Automation and Robotics in Agriculture
Abstract: Green shoot thinning operation in vineyards helps to reduce the crop load in favor of optimal quality wines. Mechanical green shoot thinning exists, but it causes cluster removal efficiencies to vary widely between 10-85 % because of difficulty in controlling the thinning end-effector position precisely to cordon trajectories. Automatically positioning the thinning end-effector to cordon trajectories will help to precisely remove the green shoots and to increase the efficiency and performance of the mechanical green shoot thinning operation. However, heavy occlusion of cordons due to shoots/leaves during thinning season makes it challenging to accurately determine the trajectories of cordons. Successfully detecting the visible parts of the cordons during the thinning season will help to estimate the trajectories of cordons for automated/robotics operation. In this study, a total of 390 wine grape vines were selected, and color images of these wine grapes were captured from a fixed distance and height for three weeks during the thinning season in real-time field conditions. Faster R-CNN (Faster regions-convolutional neural network) was deployed through transfer learning and fine tuning using the pre-trained networks (AlexNet, VGG16, VGG19 and ResNet18) to detect the visible parts of the cordons. Results showed that, Faster-RCNN model trained with ResNet18 networks provides higher accuracy in detecting visible parts of cordons compared to other tested networks with faster detection speed. Moreover, the detection accuracy with week 2 dataset was higher compared to that with week 3 and week4 datasets because of the higher visibility of cordons. These results show the potential of Faster-RCNN model in detecting the visible parts of cordons, which will be used in the future to estimate the trajectories of the cordons for the automated green shoot thinning operation in vineyards.

Keywords: Design and Control of Agricultural Implements, Agricultural Machinery Guidance and Control
Abstract: In order to find out an effective way for separating the seed and peel of camellia oleifera fruit, the physical characteristic of seed and peel was studied. A separating machine of the seed and peel was designed according to the principle of friction and air separation, and the separating experimental was carried out. Experiment results shows that compared with belt speed and airflow speed, belt inclination has more significant effect on separation of seed and peel. The optimum combination of separation of seed and peel are as follows: belt inclination angle is 22°, the belt speed is 0.7m/s, the airflow speed is 1m/s, and the separation rate of seed is more than 98% and the separation rate of peel is more than 93%.

Keywords: Design and Control of Agricultural Implements, Agricultural Machinery Guidance and Control, Precision Agriculture and Variable Rate Technologies
Abstract: In order to improve the efficiency of vegetable seedling transplantation and realize its high quality transplanting, this paper developed a multi-functional vegetable pot seedling transplanting machine. The machine was mainly composed of duckbill type planter, fertilization mechanism, power transmission system, soil covering device, watering device, film covering and pipe laying mechanism, etc. It could perform drip irrigation tape laying and film covering, transplanting, fertilizing, soil covering, watering and other working procedures at one time. In order to evaluate the work performance of the machine, field tests were conducted with 35 day-old pepper and tomato seedlings as testable subjects. The results showed that when the planting frequency were 57, 72 and 88 seedlings/min, the seedling-standing ratio decreased slightly with the increase of planting frequency, the average values were 96.4%~98.6%. The coefficient of variation of seedling spacing and the mechanical damage degree of plastic film increased with average values of 1.6%~6% and 3.8~7.9 mm/m2, respectively. The average values of the qualified rate of planting depth were 97.2%~99.0%. Seedling-standing ratio and mechanical damage degree of plastic film of diamond duckbill type planter were better than flat duckbill type planter. The test results met the requirements of mechanical industry standards. The field test results were basically consistent with the ADAMS simulation results. The structure of the transplanter was reasonable and the performance was stable. The watering device, covering device, film covering and pipe laying mechanism of the transplanter were coordinated, which could carried out the functions of each part accurately and met the agronomic requirements of vegetable seedling transplantation.

Keywords: Design and Control of Agricultural Implements, Automation and Robotics in Agriculture, Robust Control Systems for Agriculture
Abstract: This paper proposes a bionic electric spraying rod to perform the crop watering and spraying in the farm. The design concept of multiple vertebrae structures of snake is used to realize a reproducible snake bone arm and muscles of snake, which can be regarded as multiple sets of thin wires and be pulled and released through driver module. It results in different attitudes of the snake bone arm. A water pipe is installed in the snake arm connected to the spray nozzle for spraying. The mobile application interface (APP) is designed to provide the user to control the arm remotely. The maximum bending angle of the arm, which can reach to 115.7 degrees, and the jetting distance is up to 60 cm. Some spraying tests were performed to evaluate and verify the effectiveness of proposed bionic arm. The proposed snake bone-armed robot has high degree of freedom and low cost, which is more feasible than the rigid robotic arm. The robotic arm can be installed in the unmanned field mobile robot to perform spraying operation, reducing the burden of labor and the damage of on-site pesticide spraying to farmers.

Keywords: Automation and Robotics in Agriculture
Abstract: For robotic technology to be adopted within the agricultural domain, there is a need for low-cost systems that can be flexibly deployed across a wide variety of crop types, environmental conditions, and planting methods, without extensive re-engineering. Here we present an approach for predicting steering angles for an autonomous, crop row-following, agri-robot using only RGB image input. Our approach employs a deep convolutional neural network (DCNN) and an end-to-end learning strategy. We pre-train our network using existing open datasets containing natural features and show that this approach can help to preserve performance across diverse agricultural settings. We also present preliminary results from open-loop field tests that demonstrate the feasibility and some of the limitations of this approach for agri-robot guidance.

Keywords: Machine Vision and Robotics for Crop Harvesting, Big Data and Cloud Computing, Automation and Robotics in Agriculture
Abstract: Labor shortage is a critical issue in most of industries, especially in agricultural production. In recent year, riding-type tea plucking machine was imported to provide a relatively high-efficient solution for tea harvesting. However, high-level driving skill is essential. Improper operation may cause damage on tea trees and also lead to mechanical failure. A real-time image-based navigation system may provide an automatic choice to mitigate the difficulties. In this study, deep neural network architectures were applied to semantic segmentation to derive the contours of the tea rows and identify the obstacles in the field scene. Performance of four models including 8s-, 16s-, 32s- of the fully convolutional networks (FCN) and ENet were compared. Considering the overall performance, ENet outperformed other models with the mean intersection over unit (mean IU) of 0.734, the mean accuracy of 0.941, and the inference time of 0.176 s. Furthermore, Hough transform was introduced to obtain the guidelines based on the classification. The average bias of angles and distance were 6.2° and 13.9 pixels, respectively. The preliminary result showed the feasibility of using the developed navigation system for field application. To achieve a higher precision, images that cover a diverse scenario in field were be collected and trained in the future work.

Keywords: Automation and Robotics in Agriculture, Robust Control Systems for Agriculture
Abstract: To improve commercial feasibility of robotic harvesters, it is utmost important to reduce and be able to guarantee harvesting times. A significant portion of this responsibility is on the control system. Current visual servo control methods can at best achieve exponential regulation of a robot (i.e., theoretically infinite convergence time), making it impossible to predict harvest time. The aim of this paper is to introduce a new finite-time visual servo control approach that guarantees finite (i.e., bounded) and computable harvest times. To this end, a continuous terminal sliding mode visual servo controller is developed, and Lyapunov-based stability analysis is presented to guarantee finite-time regulation of the robot to a target fruit. Further, we derive expressions for the bound on the harvesting time, which can aid post-harvest operations management. The developed controller is validated through numerical simulations.

Keywords: Sensing, Automation and Robotics in Plant Factory, Protected Cultivation and Greenhouses, Machine Vision and Robotics for Crop Harvesting, Automation and Robotics in Agriculture
Abstract: 3D Move To See (3DMTS) is a mutli-perspective visual servoing method for unstructured and occluded environments, like that encountered in robotic crop harvesting. This paper presents a deep learning method, Deep-3DMTS for creating a single-perspective approach for 3DMTS through the use of a Convolutional Neural Network (CNN). The novel method is developed and validated via simulation against the standard 3DMTS approach. The Deep-3DMTS approach is shown to have performance equivalent to the standard 3DMTS baseline in guiding the end effector of a robotic arm to improve the view of occluded fruit (sweet peppers): end effector final position within 11.4 mm of the baseline; and an increase in fruit size in the image by a factor of 17.8 compared to the baseline of 16.8 (avg.).

Keywords: Crop Yield Estimation/Monitoring/Mapping
Abstract: Optimization strategies for crop growth have been explored, particularly with a view to maximization of yield and efficient use of irrigation water. Strategic use of agricultural resources requires knowledge of plant growth dynamics. Recent research establishes models describing plant growth. Use of more precise plant models, particularly those related to irrigation control may be useful in automation of irrigation scheduling. In this work, in addition to a system view-based thinking of plant growth, leaf appearance is considered. It is assumed that prediction of leaf appearance in maize plants is useful in forecasting growth stages, which allows planning for growth-stage dependent resource allocation for optimal growth. It can be shown that the appearance of new leaves corresponds to an observable decrease in leaf elongation rate. It is therefore possible to forecast timing of appearance of new leaves from the growth trajectory of older leaves. Based on the growth behavior of individual leaves, a linear approximative modeling approach is applied to maize plants in the vegetative phase. The predicted timing of end of leaf growth is compared to the experimentally observed appearance of new leaves. This novel application of sequenced linear models using different individual leaf models allows the prediction of appearance of leaves 4 and 5 to within 35 and 22 growing degree days respectively.

Keywords: Crop Yield Estimation/Monitoring/Mapping
Abstract: Deficit irrigation strategies have been employed in mitigation of challenges related to efficient water use in crop production. Various models have been developed to represent the behavior of plants under water stress conditions. This work presents a state-machine-based model that defines plant behavior in terms of states and transitions which are determined by both current and historical water status of the plant. The model is employed in prediction of the growth of maize plants under different irrigation treatments during the vegetative stage. The new approach provides an accurate estimation of the growth performance of maize plants during the early vegetative phase, allowing it to be used in evaluation of effects of different irrigation treatments and in design of irrigation-based plant control.

Keywords: Crop Yield Estimation/Monitoring/Mapping, Big Data and Cloud Computing, Crop Monitoring
Abstract: Cover crop is an agriculture operation that is planted during the winter and owns several advantages such as improving water quality and soil quality. However, the large-scale effect of cover crop in relieving environmental burden and improving cash crop yield over a region has not been widely investigated. Due to cost and time limitation, it is not favorable to conduct the conventional field trials. Previous study proposed a Random Forest classifier to predict the pattern of cover crop adoption from the remote sensing data. In this study, we propose a Multilayer Perceptron neural network to further improve the performance and reliability of the classification model and achieve an accuracy of 0.93 and Cohen’s Kappa of 0.76. Moreover, the Multilayer Perceptron model outperforms two baseline classification models. Finally, we predict the cover crop planting status for the Knox County and found a significant increase in cover crop planting on the corn cropland in 2016.

Keywords: Soil, Plant and Environment Sensing, Sensing and Automation for Precision Irrigation
Abstract: In this paper, a drip irrigation emitter with new pit flow channels such as shunt, sharp turn, and confluence was constructed by the pit structure in the water transporting tracheid of bionic plant xylem. In order to study the hydraulic performance and energy dissipation effect of the pit flow channel, the geometric parameters of the pit flow channel were combined by simulation prediction and orthogonal test. The 25 sets of test schemes were carried out to test the hydraulic characteristics, and the Bernoulli equation was used to solve the structural loss coefficient. At the same time, the orthogonal test results were analyzed by the range and variance, and the regression model of geometric parameters and flow index was established. The results showed that the flow index of the emitter was 0.462~0.496, and its hydraulic performance was good. The structural loss coefficient under the pressure head of 5~25 m was 2120~6321, which showed that the energy dissipation effect was obvious. The order of influence of each geometric parameter on the flow regime was T>B>S>D>A, and the optimal scheme was T0.18B2.2S2.2D0.2A4. The regression coefficient of the model was significant. The value of the F statistic was 16.670, corresponding to the significance level Sig.=0<0.05, and the error of the experimental and simulated values of the flow index was less than 5%, which proved the accuracy and reliability of the regression model. This paper provides a new idea for agricultural drip irrigation control technology.