Skip to main content

Über dieses Buch

This book constitutes the refereed post-conference proceedings of the 10th IFIP WG 5.14 International Conference on Computer and Computing Technologies in Agriculture, CCTA 2016, held in Dongying, China, in October 2016.
The 55 revised papers presented were carefully reviewed and selected from 128 submissions. They cover a wide range of interesting theories and applications of information technology in agriculture, including intelligent sensing, cloud computing, key technologies of the Internet of Things, precision agriculture, animal husbandry information technology, including Internet + modern animal husbandry, livestock big data platform and cloud computing applications, intelligent breeding equipment, precision production models, water product networking and big data , including fishery IoT, intelligent aquaculture facilities, and big data applications.



Study on the Theory and Practice of Data Visualization

Data visualization is a science and technology research on data visual form, which is originated in the 50’s of the twentieth Century. It went from scientific visualization, information visualization to data visualization. Based on computer graphics and pictures data visualization display and reveal the main information contained in data. Data visualization contains data acquisition, data analysis, data processing and data modeling. Based on psychology the motivation of data visualization is to expand the scope of visual perception which is easier to get information than other biological perceptions while the effect is better. Modern science and technology greatly extends the human sensory “arms”. Visual perception has very long “arm” and often “robs” other perceptions’ “business”. This paper introduces the basic concept and main content of data visualization, reveals the essence of data visualization. Through the “Agricultural planning visualization” case, the technology process of data visualization applied in production has been established, which can be described as 4 steps operated by order. The first step is to determine and decompose a target. The second step is data acquisition and processing. The third step is models designing and expression. The last step is video production.

Quan Wu, Xiaochen Li, Danqiong Wang, Weijie Jiao, Xue Han

Assessing the Ability of Image Processing Methods of Droplets Sprayed on Water Sensitive Papers for Aerial Application

In this study, 33 pieces of WSP were placed along three lines in a paddy. An M-18B Dromader AG aircraft flew and sprayed over the field, and the spray deposits were collected by water sensitive paper. Seven greyscale parameters were used to compare the color depth, deviation and homogeneity of digital water sensitive images. The greyscale images were converted to binary images with five threshold selection methods. The results of recognition of seven greyscale parameters and five threshold methods were compared to analyze the droplets in different scanned images on water sensitive paper. The effects of the threshold on the computation of deposit density and the stain size were evaluated. The most suitable grey scale was found to be luminosity. Finally, a manual validation was performed, and the relationship between the threshold and the stain size of was analyzed.

Gang Xu, Ruirui Zhang, Liping Chen, Qing Tang, Min Xu, Wanmin Zhang

Application of “GaoFen-1” Satellite Data and “Micro-UAV” Data in Remote Sensing Monitoring in Winter Wheat—Illustrated by a Case of Jizhou in Hebei Province

This research utilized “GaoFen-1” 2 m panchromatic, 8 m and 16 m multispectral satellite data to monitor the planting area of winter wheat. Calculate the correction coefficient by the results of planting area of winter wheat gotten from “GaoFen-1” 16 m multispectral satellite data and micro unmanned aerial vehicle data. Correct the area extraction result of “GaoFen-1” 16 m multispectral satellite data and verify the accuracy of the results got from fusion data of 2 m resolution and 8 m resolution of “GaoFen-1” by micro unmanned aerial vehicle data. Then compare with the area extraction results, extracted from the data of fusion data of 2 m resolution and 8 m resolution of “GaoFen-1” and the corrected 16 m multispectral satellite data, in Jizhou. The study result show that the corrected extraction result of planting area of winter wheat, from “GaoFen-1” 16 m multispectral satellite data, is accurate relatively and could better meet the requirements of the crop dynamic monitoring business operational running.

Yuechen Liu, Weijie Jiao, Haijun Wang, Xue Han

Research on Reflectance Spectra Measurement of Chlorophyll-Containing Water in Laboratory

Chlorophyll is the important index to estimate the phytoplankton biomass. In order to research phytoplankton biomass and eutrophication condition of water, the spectroscopy method has been used usually now. A large number of spectrum experiments also need to be taken in the laboratory. In this article, the gray and the white diffuse reference scale are respectively used to measure the character reflectance spectrum of the chlorophyll-containing water. Then we analyze the differences of the data quality between these two ways. The result shows that, when measuring the water object which has low reflectance in the laboratory, using the white scale will cause a big data noise and the data quality will be poor. But when using the gray scale to take the experiment, the data noise will be small and the data quality will be good enough to find the character reflectance spectrum.

Yinchi Ma, Yetao Li, Yonghua Qu, Wen Ding

Study on Simulation of Rice Yield with WOFOST in Heilongjiang Province

WOFOST (world food study) model had been successfully used in daily business of agro meteorological monitoring and yield forecasting in European Union, and also been widely used in crop growth process simulation and yield estimation all over the world. In this study, with the help of the rice growth observed data, the meteorological data at the same time and the rice planting regional planning data in Heilongjiang Province, the crop parameters for WOFOST model were improved. Based on the localization and regionalization of the model, the rice yield in county and region scale in Heilongjiang Province was simulated. In province scale, the WOFOST simulated yield was good, and the relative error between estimated yield and statistical yield from 2006 to 2013 were respectively 2.71%, 8.47%, 6.41%, –15.96%, 3.95%, 0.02%, –7.06%, 0.88%, four of which beyond ±5%. But in county scale, the correlation between WOFOST simulated and statistical yield was poor, and not passing the test of significance. In order to improve the precision, the trend yield calculated by the statistical yield and the WOFOST simulated yield were both used to build a comprehensive rice yield simulation model by the multiple linear regression method year by year from 2006 to 2013. Then the rice yield both in county and province scale in Heilongjiang Province was calculated by using the comprehensive model. In county scale, the comprehensive simulated yield and the statistical yield in county scale passed significant test of 0.01, and the correlation coefficients were respectively 0.715, 0.728, 0.829, 0.810, 0.888, 0.919, 0.868, 0.798, the R2 were respectively 0.511, 0.529, 0.686, 0.656, 0.789, 0.844, 0.753, 0.636. In province scale, the relative error between the estimated yield and statistical yield during 2006–2013 were respectively –1.72%, 2.12%, 3.02%, –2.45%, 1.27%, –0.89%, –0.38%, 1.96%. The comprehensive model had a good effect on improving the defects of fluctuation in individual year with a relative higher accuracy than that of only using WOFOST model, and could satisfy the application of rice yield estimation in large region.

Shangjie Ma, Zhiyuan Pei, Yajuan He

Application of the Data from Landsat8 OLI - The New Generation of Landsat Series in the Cultivated Land Information Extraction

By making use of the image data of Landsat8 OLI newly launched by the United States and taking Liaocheng, Shandong Province as an example, we conduct computer correction and enhancement for the remote sensing image data of Liaocheng through the adoption of ENVI (a remote sensing image processing software) to extract information of cultivated land with the methods of visual interpretation, supervised classification and unsupervised classification. The result shows that based on the combination of Band5, 4, 3 and Band6, 5, 2 of Landsat8 OLI data, a relatively satisfactory cultivated land information can be acquired through visual interpretation, interactive methods of supervised classification and unsupervised classification.

Luyan Niu, Taichang Cui, Jiabo Sun, Xiaoyan Zhang

Research on High Precision pH Sensing Device Based on Cloud Platform Service

This project tries to design a wireless intelligent pH sensor to monitor the pH value of nutrient solution in real time by using the analog front circuit LMP91200, microprocessor STM32F103c8t6 and WiFi module. The experiment shows: this equipment has a high accuracy, can be 0.01; it can access business cloud services platform to achieve the functions like accurate acquisition and calibration of pH value, Interactive with cloud platform through WiFi Networks; APP and PC for the remote measurement is stable, after 12 h of testing there is no packet loss phenomenon; Because of high uploading speed, in 5 s it can complete the device networking and upload, besides, the cloud services have changed the traditional way of nutrient solution measurement.

Zhiyue Shang, Xin Zhang, Cheng Zeng, Yuanfang Yao, Yunlong Bu, Yu Cai

Effects of Waterlogging and Shading at Jointing Stage on Dry Matter Distribution and Yield of Winter Wheat

Continuous rain is the main meteorological constraint for winter wheat production in Jiangsu Province, accompanied by stresses of both waterlogging and shading. To evaluate the independent and combined effects on winter wheat at jointing stage, pot experiments were conducted using two cultivars, Ningmai 13 and Yangmai 13. Four treatments, CK (non-stressed), WA (waterlogging alone), SA (shading alone) and WS (both waterlogging and shading) were established with different durations. In the non-stressed environment, Yangmai 13 had higher production than Ningmai 13. However, Ningmai 13 had better production under stresses, indicating a better tolerance to waterlogging and shading. Comparing dry matter distribution and grain production showed that the negative effects of the stresses were in the order WA > WS > SA, demonstrating that shading had compensative effects on waterlogging at jointing stage. Results indicate that production loss of winter wheat due to continuous rain at jointing stage might be overestimated.

Yang Liu, Xiaoyu Liu, Jing Cao, Chunlin Shi, Shouli Xuan

Identification of Eggplant Young Seedlings Infected by Root Knot Nematodes Using Near Infrared Spectroscopy

In this paper, eggplant young seedlings infected by root knot nematodes were identified using near infrared spectroscopy. The main research on MSC and SG pretreatment method and PCA principal component extraction method with the combination of effects on model for classification. Results show: The best classification process is to do the first MSC after SG smoothing pretreatment, after using PCA extracted as the main component of the SIMCA input variables for classification, and achieved a classification average accuracy higher than 90%. It is an effective method to classify the degree of infection of the root knot nematodes by using the visible and near infrared spectral characteristics of the eggplant leaves.

Wei Ma, Xiu Wang, Lijun Qi, Dongyan Zhang

Applicability of Model Updating Method to Different Detection Indexes of Cold Fresh Pork

Model updating method is used to maintain the hyperspectral models established to predict water content, pH value, and TVB-N content of cold fresh pork. After adding 11 slave variety samples to the calibration set of the master variety samples, the prediction results of the updated model of water content for the slave variety samples were $$ {\text{R}}_{\text{p}}^{ 2} \, = \,0. 8 2 2 4 $$ and RPD = 1.94. After adding 45 slave variety samples, the prediction results of the updated model of pH value for the slave variety samples were $$ {\text{R}}_{\text{p}}^{ 2} \, = \,0. 6 1 60 $$ and RPD = 1.34. After adding 9 slave variety samples, the results of the updated model of TVB-N content for the slave variety samples were $$ {\text{R}}_{\text{p}}^{ 2} \, = \,0. 90 7 3 $$ and RPD = 3.04. The findings show that the model updating method can well maintain the TVB-N content model but shows poor maintenance ability for water content model, and it cannot be used to maintain the pH value model. Therefore, the applicability of the model updating method varies in different detection index models for cold fresh pork.

Shanmei Liu, Hui Peng, Ruifang Zhai, Jun Luo

Detection of Defects in Malus asiatica Nakai Using Hyperspectral Imaging

Hyperspectral imaging technology was employed to detect defects such as rot, bruise and rust in Malus asiatica Nakai. 213 RGB images of samples, including 3 types of damage samples and sound ones, were acquired by hyperspectral imaging system. Spectral data were extracted from the regions of interest (ROI) using ENVI4.7 software. Competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were used to select characteristic wavelength points. As a result, 11 and 6 characteristic wavelength points were chosen for CARS and SPA respectively. Extreme learning machine (ELM) discrimination model was established based on the spectral data of selected wavebands. The results showed that the accuracy of the SPA-ELM discrimination model was as great as 94.74%. Then, images corresponding to six sensitive bands (532 nm, 563 nm, 611 nm, 676 nm, 812 nm, and 925 nm) selected by SPA were selected for principal components analysis (PCA). Finally, the images of PCA were employed to identify the location and area of a defect’s feature through imaging processing. Through sobel operator and region growing algorithm, the edge and defective feature of 38 Malus asiatica Nakai can be recognized and the detection precision was 92.11%. This study demonstrated that the defects, (rot, bruise, and rust) of Malus asiatica Nakai can be detected in spectral analysis and feature detection in hyperspectral imaging technology, which provides a theoretical reference for the online detection of defects in Malus asiatica Nakai.

Jianglong Liu, Shujuan Zhang, Haixia Sun, Zhiming Wu

Study and Development of the Precision Management System for Livestock

The article studies the precision management for livestock including breeding, feeding, disease preventing, safety supervision and environmental monitoring. The system based on the wireless mode is developed to monitoring the whole production procedure of livestock. It comprises breeding management, automatic feeding formulation, disease diagnose and prevention, production safety supervision and environmental monitoring subsystems. The study greatly promotes the efficiency of intensive cultivation. Through the practical application in farm, it is proved that the system comprehensive performance is significantly better than the extensive management.

Fengyun Wang, Wenjie Feng, Jiye Zheng, Huaijun Ruan

Kinematic Simulation of Vibrating Disc No-Till Seeder Based on Creo Software

In order to solve the problems of wheat no-till seeders in annual double cropping area of North China Plain such as large amount of straw-covering, stubble-bulky, residue-blocking, and bad passing capacity and planting quality, the new vibrating disc no-till seeder was designed. This paper analyzed the structure and elaborated the working principle. Creo software was used to establish three-dimensional motion simulation model, and add the constraints of seeder’s parts to realize the movement of seeder and its anti-blocking device. The change of displacement, velocity and acceleration of vibrating disc was obtained by simulation. The result showed that there was no collision between components of the seeder, and the main circular motion occurred in y direction, which was beneficial to cut the straw. The study provides theoretical basis for the trajectory optimization and dynamics simulation analysis of vibrating disc no-till seeder in the future.

Caiyun Lu, Zhijun Meng, Xiu Wang, Guangwei Wu, Liwei Li, Weiqiang Fu, Jiayang Yu

Calculation of Effective Rainfall in the Spring Maize Growing Period

Effective rainfall accurate determination can promote the technology development of planning crop irrigation, irrigation water management, irrigation and drainage design and highly efficient use of water resources. However, the effective rainfall will be affected by many factors, such as the characteristics of rainfall, characteristic of the crop’s type and crop water consumption, soil characteristics and the way farming farmland management. In addition, geographical location, climatic conditions and other factors will also affect the calculation of effective rainfall. Thus, a reasonable calculation method of effective rainfall should be determined based on the specific conditions of the region. In this paper, based on the meteorological data of Changzhi in Shanxi, the effective rainfall in the spring maize growing period was calculated by the method of water balance, under different hydrological conditions and different irrigation. And then this paper applied this method to analyze the effective rainfall of spring maize and simulate daily soil water content. The results show that: with the increase of rainfall, effective rainfall decreases. With the increase of irrigation amount, effective rainfall gradually reduced. With the increase of crop water requirements, effective rainfall gradually increased. Therefore, this paper analyzes the relationship between effective rainfall and rainfall, irrigation and crop water requirement. The correlation coefficient is 0.802. It is closely related. The simulated and measured values of the growing period of spring maize daily soil moisture better fit, weather in the irrigation or non-irrigation conditions. This verified the calculation method of the effective rainfall.

Nana Han, Gangyan Lou, Yangren Wang, Qingyun Zhou, Jianhua Jin, Songmin Li, Lantao Ye

Simulation of Evaporation and Transpiration of Eggplant Under Mulch Drip Irrigation in Greenhouse

Based on the principle of soil water balance, the change of soil water content during the whole growth period of eggplant with the variety “Angela” as the material is simulated through the test of greenhouse environmental factors. The crop coefficient is determined by the optimization method. The evapotranspiration of eggplant is simulated under the condition of drip irrigation under mulch film. The results showed that the simulated values of soil water content in the growth period of eggplant are in good agreement with the measured values, and the relative error is less than 10%. The variation rule of the crop coefficient and eggplant leaf area index are consistent. The crop coefficient in the early increases gradually, in the vigorous growth period of crop coefficient reaches the maximum value of 0.518, then began to decreases from 0.518 reduced to 0.505 and then increased gradually. The fluctuation is mainly affected by pruning management. The change of water requirement of eggplant in greenhouse is smaller in the early stage of growth between 0.2–2.4 mm/d. And the change in the late of the growth period is larger between 0.1–3.1 mm/d. The accumulated value of evaporation and transpiration increases gradually, and the highest value is 290 mm/d.

Zhiwei Zheng, Liuyan Yu, Xiushui Liu

Design and Development of Greenhouse Energy Management Platform Based on STM32

Greenhouse energy management system can make some systemic administration such as measure and analysis for water flow, electric quantity and quality, heat energy, gas flow and some other energy parameters in greenhouse for achieving a certain energy-saving effect. The introduction of the technology is mostly based on PC platform. The embedded greenhouse energy management platform based on STM32 was designed. This paper gave the system hardware and software architecture including the selection of hardware, transplantation of μCOS-III, transplantation of embedded database, design of human-machine interface and the main process of software. Finally, the platform is verified by STM32-V5 development board of Arm fly. The results show that the platform can meet the basic needs of energy management in greenhouse, and it has the advantages of low cost, strong expansibility and so on, it is feasible and effective to apply it to the greenhouse industry in China.

Junlin Sun, Xin Zhang, Cheng Zeng, Wengang Zheng, Lipeng Guo, Yali Du

Study on the Dynamic Low Limit of Irrigation for Winter Wheat

The concept of dynamic irrigation low limit (DILL) was proposed and the determination method of DILL was given based on crop-water model. The parameters of the crop-water model were calibrated with winter wheat experimental data of 2008 and 2009. The optimal irrigation scheduling of five typical years under different irrigation water supply were determined, which resulted in 58 groups of data on the average soil moisture content of main root zone (0–60 cm) before an irrigation, the corresponding irrigation time, and water supply. The results showed that, the crop yield under the irrigation times of 3 and 2 increased by 7.42% and 5.62% averaged from 2009 to 2013, and the economic benefit increased by 7.64% and 7.24% than those under the empirical irrigation practices, respectively. The irrigation forecast based on DILL provides an important method to implement and dynamically correct optimal irrigation scheduling under limited water supply.

Hongzheng Shen, Yangren Wang

Research on Plant Growth Simulation Method Based on ARToolkit

Augmented Reality is a new technology which can combine the real world information with the virtual world information seamless. In order to increase the sense of immersion and interactivity, thereby improving agricultural information service capabilities and expanding the exchange of seed industry exhibition and promotion capabilities, this paper provides a kind of interactive method to simulate the plant growth. Based on the target tracking localization algorithm of ARToolkit, through the relative distance positioning two rectangular markers, corresponding to different plant growth development period, the method can interact to realize the control of virtual objects, such as translation, rotation and zoom.The experimental results show that the method can simulate the true process of the wheat plant growth, that can simulate different kinds of virtual wheats. The method has a good compatibility, low requirement on the hardware, stable capability, better expansibility and transferability.

Peng-fei Zhao, Tian-en Chen, Wei Wang, Fang-yi Chen

Control System Design of Soy Sauce Koji-Making Based on ARM

Koji-making is an important part in the production of soy sauce. The traditional means of yeast pool ventilation starter depends on the experience of staff to control the environment of yeast antrum, which koji way automation level is not high, koji product stability is not guaranteed. This paper proposes a design method of soy sauce koji-making control system based on ARM processor S3C2440. It mainly consists of embedded microprocessor S3C2440, power conversion circuit, data storage circuit, display circuit, communication circuit composition. The Linux operating system is used to achieve the automatic control of the traditional process of making koji. The staff can judge the bending machine, fan working time directly through the soy sauce making koji control system, which improves the traditional production of soy sauce production level, and ensures the stability of the quality of the product.

Min Zhang, Yuhua Wu, Ting Yang, Shijun Li

Research on the Comprehensive Evaluation of Alfalfa Management in Zuli River Basin

Taken Alfalfa as an example, this study analyzed the impact of returning cultivated land to grassland in Zuli River basin. The entropy weight method was used to appraise the growth years for alfalfa. The results showed that the appropriate years for alfalfa in the northern of the basin is nine and sex for the southern of the basin. After the recommended planting years, the composite index significantly decreased. Then, the yield of alfalfa in Zuli river basin was expressed in map using multiple regression method.

Rui Guo, Cui Yun Wang, Xue Ying Shang, Xuan Mi

Fruit Tree Image Registration Based on Improved FAST Algorithm

In order to promote the efficiency and accuracy of image registration, this paper proposes an improved registration algorithm for fruit tree images acquired by a dual-sensor vision system. In the algorithm, feature points are extracted by FAST detectors from Gaussian scale space, and main orientation is determined and SURF descriptor is created with statistical method of neighbor intensity distribution, matching pairs are determined with a relative ratio method and a iterative purifying method in succession. Experimental results show that the proposed algorithm outperforms previous algorithms comprehensively.

Juan Feng, Lihua Zeng, Jianping Li

Development of a Recognition System for Alfalfa Leaf Diseases Based on Image Processing Technology

To implement rapid identification and diagnosis of leaf diseases on alfalfa, an image-based recognition system was developed using the GUIDE platform under MATLAB software environment. An integrated segmentation method of K_median clustering algorithm and linear discriminant analysis was applied to implement the lesion image segmentation in this developed recognition system. A multinomial logistic regression model for disease recognition was built based on 21 color, shape and texture features selected by using correlation-based feature selection method. Using this system, disease image reading, image segmentation and lesion image recognition can be done. This system can be applied to conduct image recognition of four common kinds of leaf diseases on alfalfa including alfalfa Cercospora leaf spot, alfalfa rust, alfalfa common leaf spot and alfalfa Leptosphaerulina leaf spot. Some basis was provided for further development of image recognition system of various alfalfa diseases and for building a network-based automatic diagnosis system of alfalfa diseases.

Feng Qin, Haiguang Wang

Design Optimization and Performance Evaluation of a Tillage Depth Precision Measurement System

Tillage depth measuring is essential in modernization of agricultural production, including tillage depth, seed germination, plant growth and soil conservation. At present, there are no reliable measuring method or equipment for on-line tillage depth data acquisition. To solve this problem, equipment for real-time measuring tillage depth was designed based on ultrasonic sensing technology. This system comprises mainly mechanical constructions, hardware structure, software, specific measurement process and data processing technology. To improve the measuring accuracy, Kalman filter method is used to reduce the influence of uneven surface, weed, and stubble in field. This device was installed on subsoiler, and a field test was conducted. The test results show that: The accuracy of the ultrasonic measuring depth is comparable with the manual measuring method in the field condition of ploughed field, bare field and stubble field.

Kang Niu, Yanwei Yuan, Junning Zhang, Fengzhu Wang, Yangchun Liu, Xianfa Fang, Hong Cheng

Research on Evaluation of Soil Fertility Resource Space Based on Regional Hotspots and Clustering Method

Based on each unit of Nong’an County, With ArcGis software platform, the establishment of a part of the total nitrogen in the soil attribute data Nong’an topsoil fertility resources, phosphorus, potassium and organic matter and effective nutrient database, Global Clustering and outlier analysis and hot spot analysis of the autocorrelation method, the county topsoil fertility resources were analyzed and evaluated. The results for farmland protection and optimal layout policy to provide a reference for the theory and methods, but also on the implementation of the agricultural work provides precise basis for decision making.

Guifen Chen, Jian Lu, Ying Meng, Dongxue Wang

Research on GA-RBF Optimization Algorithm in the Prediction of Yield Loss of Maize Diseases and Pests

In view of the high complexity and nonlinearity of crop pests and diseases, using the traditional BP network and RBF network model method to predict is pretty difficult. And the prediction accuracy is low. Also the effect is not ideal when the sample size is small and the noise is more, therefore, this article presents a fusion optimization algorithm based on genetic-algorithm (GA) and radial basis function neural network (RBF). By unified coding the data center of RBF neural network and its corresponding expansion constant and weight, strengthened the cooperation between the hidden and output layer, furthermore using the functional characteristics of global search using genetic algorithm to obtain the optimal model of yield loss, finally predict on yield loss of maize diseases and pests. By making simulation test data of the National 863 project demonstration area - 13 village, Gong’ peng town in Jilin province Yu’shu County, the experimental results show that: After using the GA to optimize the RBF in the network’s structure and approximation has obvious improvement and enhancement, can effectively reflect the fluctuation characteristics of maize diseases and pests, has been widely application prospect in the agricultural field.

Guifen Chen, Dongxue Wang, Shan Zhao, Siwei Fu

The Association Rules Algorithm Based on Clustering in Mining Research in Corn Yield

With the popularization of agricultural information technology, the use of data mining techniques to analyze the impact of different types of soil nutrient content and yield of corn has become a hot topic in the field of agriculture. Association rule mining is an important part of the field in Data mining, association rules can be found associated with agricultural data attributes. This article will use cluster analysis and association rule to analysis correlation between corn yield and soil nutrient. Firstly compare different clustering algorithm to chooses the optimal algorithm, make data collected in scientific classification, and based on expert knowledge of the collected data into different levels; then determine the type and content of different soil by association rules corn yield and soil nutrient; final inspection algorithm is correct. The results showed that: comparing K-means, hierarchical clustering analysis, and PAM, K-means algorithm to determine the optimal clustering; K value can be determined at selected intervals. K is equal to 3, 4 or 6, clustering effect is good according to Sil value when K from 3 to 10. Based on the principle of association rules, clustering algorithm to select a K value associated with the combination of rule 6; After clustering algorithm of association rules, support and credibility and improve degree of accuracy is better than not clustering; by mining association rules after clustering, a great influence on the different levels of soil nutrients in corn yield. The results for the corn yield provides intelligent decision support data.

Bo Liu, Guifen Chen

Application of Principal Component Cluster Analysis in the Quality of Cordyceps Sinensis

In this paper, the kinds and contents of amino acids in Cordyceps sinensis from different habitats of Tibet components using principal component analysis and cluster analysis, the principal component cluster analysis to evaluate the nutritional value of different localities, and provide scientific basis for the further research and development and utilization of Cordyceps resources in Tibet area. The principal component analysis method is a method of using the central idea of dimensionality reduction, the analysis method of multi indicators into a multivariate data several comprehensive index of a few statistics. The principal component analysis method can guarantee the minimizing loss of original data information, with less comprehensive variables instead of multiple variables of the original. Cluster analysis can be used to classify samples of multiple variables by using comprehensive information, the classification results are intuitive, clustering dendrogram clearly show the results of numerical classification, clustering analysis results than the traditional classification method is more detailed, comprehensive, reasonable.

Xin Zhao, Hongjian Yang, Yuqi Sheng, Yang Jiao, Haijiao Yu, Yao Qin, Guogang Zhao

Principal Component Clustering Analysis Apply to the Amino Acid Content in Antler Based on Matlab

The antler is a very high nutritional value of supplements, but also a very important medicine, antler occupies a very important position in Chinese medicine. Antler is rich in amino acids, which contains more than seven kinds of essential amino acids. In the organic component of antler, amino acids are the topped content of nutrients, and in them, the highest is glycine; amino acids are the basic components of living organism tissue cells, and play a pivotal role for life events. If the body lacks any kind of essential amino acids, it can cause physiological dysfunction, affecting the normal antibody metabolism, leading to disease. In the paper, it accord to the data of amino acids which contain different specifications antler herbs, analyze and compare the relationship of amino acids between sika deer antler and red deer antler using the principal component cluster analysis. The results showed that sika deer antler with red deer antler have the similar medicine effect and different essential amino acids nutrients.

Xin Zhao, Jing Wang, Yang Jiao, Haijiao Yu, Yao Qin, Quanming Li, Guogang Zhao

The Principal Component Analysis and Cluster Analysis of Trace Elements in Gentian

In this paper, using principal component analysis and cluster analysis method, combining with the statistics software MATLAB. The Qingyuan rough gentian, Zuojia rough gentian, Zuojia leaf gentiana system clustering analysis of experimental data. Main ingredients swertia glycosides, Swertia bitter glycosides, gentian bitter glycosides and oleanolic acid and ursolic acid, etc. Cluster analysis results showed that the three principal component contribution rate of the Qingyuan rough gentian is 89.24%, the three principal component contribution rate of the Zuojia rough gentian is 89.85%, the three principal component contribution rate of the Zuojia leaf gentian is 93.56%. By cluster analysis to Qingyuan rough gentian, Zuojia rough gentian, Zuojia leaf gentiana aristata 3 groups of data were divided into 6, 5, 4 classes, and determine the appearance characteristics of the high quality gentian, provide the basis for breeding to select high quality gentian.

Xin Zhao, Mingwei Xu, Guoqing Sun, Yang Jiao, Haijiao Yu, Quanming Li, Guogang Zhao

Research on Color and Shape Recognition of Maize Diseases Based on HSV and OTSU Method

With the application of IOT technology in maize disease images for monitoring and collecting, timely detection of the types and characteristics of identification of disease has become a hot research in the diagnosis and treatment of diseases and insect pests. In order to improve the recognition accuracy of maize leaf, achieve rapid diagnostic purposes, this paper takes the leaf spot of maize gray leaf spot and image as the research object, use the computer image processing technology is studied on the effective segmentation and recognition of color and shape features. The genetic algorithm was adopted to optimize the selection of maize disease images real-time filtering; $$ 3 * 3 $$ mode noise suppression of the image selected by value smoothing; then select the HSV component of the color feature extraction of the disease; the maximum between class variance (OTSU) disease shape character segmentation and recognition. The results show that, based on genetic algorithm optimization based on image In HSV and Otsu method can be more accurate segmentation and recognition of the disease of color and shape features, and enhance the real-time and accuracy of the image of maize disease detection and recognition and oriented under the condition of things plant diseases and insect pests of maize and provide technical support.

Guifen Chen, Ying Meng, Jian Lu, Dongxue Wang

Research on Variation Rule of Sensible Heat Flux in Field Under Different Soil Moisture Content and Underlying Surface by Large Aperture Scintillometer

The surface sensible heat flux has a profound impact on regional energy balance of payments and regional water cycle, which is an important part of composition of the surface energy balance. This research was based on the large aperture scintillometer (LAS), combined with eddy covariance system. Sensible heat fluxes in field in September 2015 - April 2016 were observed continuously on Daxing district experimental base in Beijing. The original data was processed by BLS software and the data process cycle of large aperture scintillometer was established.The analysis of sensible heat fluxes in field under different soil moisture content and different underlying surface could provide theoretical basis for variability of sensible heat fluxes in field.

Xin Han, Qingyun Zhou, Baozhong Zhang, Di Xu

Design Method for Chemical Clogging Emitters Boundary Optimization

Fractal flow channel structure as research object, based on chemical clogging condition of the physical model. It was analyzed using computational fluid dynamics (CFD) simulation and reveals the fractal flow channel internal flow characteristics of water and sediment. Fractal flow channel non-energy dissipation of the arc angle design optimization. Using standard κ-ε turbulence model and the DPM model, calculated: (1) As for the hydraulic performance analysis, before optimization emitter flow exponent of 0.487, 0.489 after optimization; From the inner flow field analysis, When the pressure head from 5 m to 15 m, before optimization emitter maximum flow rate from 2.09 m/s to 3.70 m/s, the maximum flow rate to optimize the emitter from 2.15 m/s to 3.81 m/s, the maximum optimization of flow rates were increased compared to the previous 2.87%, 3.34%, 2.97%, the flow rate improved. After optimizing the eddy region, the velocity of the outer edge of the eddy region increased from (0.005–0.752 m/s) to (0.311–0.930 m/s), which improved the self-cleaning ability of the irrigator. Based on the analysis of blockage performance, the passing rate of particles is significantly improved after optimizing the flow channel. Considering the optimized emitter has excellent hydraulic performance and anti-clogging properties.

Xu Li, Peiling Yang, Shumei Ren, Lili Zhangzhong, Lihong Yang

Strategies of Agricultural Manufacturing Industrial Cluster Knowledge Service Platform Construction and Optimization: The Case of Shandong Province

This paper aims to point out the necessity and feasibility of the construction of the agricultural manufacturing industrial clusters’ knowledge service platform based on the prior research of clusters’ knowledge service platforms. And then the knowledge service platform of Shandong province has been illustrated as an instance to analyze the current situation of industrial development, the construction and operation aspect of the knowledge service platform. This paper presents several basic recommendations such as the alliance development, professional development, diversified development, sharing development and coordinated development to optimize agricultural machinery manufacturing cluster knowledge service platform, so as to improve the overall level of the knowledge service platform as well as promote the transformation and the upgrade of the agricultural machinery manufacturing industry.

Qiong He, Minli Yang

Application of GIS and Modified DRASTIC Model Based on Entropy Weight and Fuzzy Theory to Ground Water Vulnerability Evaluation

Groundwater vulnerability assessment coupling with geographic information systems (GIS) should be considered as an important means for groundwater management, especially in agricultural areas. Nowadays, for groundwater vulnerability evaluating, DRASTIC model has been very popular and widely used in the world. However, DRASTIC model has some disadvantage. To overcome the problem, this paper proposed a modified DRASTIC model based on entropy theory and fuzzy theory. Moreover,three additional parameters, were added to the modified DRASTIC model, which were wastewater discharge of unit area, fertilizer usage of unit area, and density of river network. Using ArcGIS10.2 and the modified model, groundwater vulnerability grade (GVG) in Tianjin plain was analyzed and calculated. Groundwater vulnerability map of the plain area in Tianjin was constructed. According to the results, the study area was divided into five level zones: low vulnerability zone, lower vulnerability zone, medium vulnerability zone, higher vulnerability zone and high vulnerability zone, with coverage area of 17.1%, 26.7%, 25.2%, 22% and 9%, respectively. The results are consistent with the actual situation of studied area.

Shaofei Li, Guanyou Li

Simulation Research on Water Quality in the Irrigation Section of Jinsha River

A two-dimensional water quality model is established on a section in the middle reaches of Jinsha River, based on the numerical simulation method. Considering the situation within the reach of many sewage outlets, the transport of pollutants in the river is simulated. Calculation results reveal the distribution characteristics of pollutants concentration under the effect of multi-sewage outlet discharge. The results show that the transport of pollutants along the riverside has little effect on the other side of the river. According to the predicted results, the water quality of the water intakes near the downstream reaches may not meet the standard of water quality. Therefore, the water obtained by intakes is not suitable for irrigation. It is essential to carry out effective measures to improve the water intake scheme. The paper can provide a scientific basis for the planning and design of the reasonable water intakes of the Jinsha River.

Xu Wang, Ping Yu

Research on Virtual Simulation of Flood Propagation in Agricultural Area Under the Land Subsidence

Agricultural areas are mainly distributed in the suburbs, however suburs of metropolis are often used as flood storage and detention areas in order to ensure the safety of urban from flood. Severe land subsidence would make a decrease use of flood control facilities like dike and sluice which protect the agricultural areas, and there are important significance to analyze the flood control in agricultural areas affected by double natural disasters. In this paper, the land subsidence observations and sedimentation rate over recent 20 years in Dahuangbao agricultural areas are the object of study, and the flood routing mathematical model is established using the alternating direction implicit method (ADI) with high stability and precision. The results reveal that after comparing the flood values with different return periods between before and after land subsidence, the inundated area and capacity after land subsidence increases, which directly affects the safety of agricultural areas.

Ping Yu, Shaofei Li, Xu Wang

Research on the Clustering Method of Agricultural Scientific Data Based on the Author’s Scientific Research Relationship

Focusing on semantic parse and bias problems during the clustering process of agricultural scientific data, a clustering method for agricultural scientific data based on author’s scientific research relationship is proposed in this paper. Meanwhile, an assessment algorithm of the scientific research relationship based on co-author ship and authors’ inter-citation is put forward. Finally, the experimental results proved that the proposed clustering method for the agricultural scientific data can effectively improve error classification caused by semantic parse and bias.

Dingfeng Wu, Liyun Wang, Jian Wang, Hua Zhao, Guomin Zhou

Evaluating E-Service Quality of Agricultural Business Websites in China: E-S-QUAL Model Approach

This paper focuses on measuring electronic service quality of agri-business websites in China by means of E-S-QUAL scales in a service-and-commerce oriented setting. The research covers assessment of the e-service quality from 105 current and potential users including farmers, officials, peddlers, merchants and agri-business managers. The findings indicate that e-service quality from customers’ perspective is obviously most related to efficiency. The confirmatory factor analysis confirmed the validity and reliability of the conclusion. Thus, efficiency is recommended to pay attention to for improving e-service quality of agri-business websites in China.

Ke Sun, Yan Li, Yiliang Wang, Xi Wu, Yiming Huang

Design of Agaricus Bisporus Automatic Grading System Based on Machine Vision

Aim at the agaricus bisporus postharvest automatic classification problem, this paper designed a kind of agaricus bisporus grading system based on machine vision, the system is mainly composed of machine vision system, mechanical system, automatic control system three parts, and analyzed the key technologies involved in every part. Extracted the feature parameters from the mushroom cap color, mushroom cap area and mushroom stem three aspects, combined with the classification standard, the final classification result is given by using edible fungus intelligent recognition platform, and then control the robot grabbing the agaricus bisporus into the corresponding classification box, the rate of accuracy reached over 88%. The results show that using machine vision based automatic grading system for the agaricus bisporus classification is feasible.

Jiye Zheng, Wenjie Feng, Bingfu Liu, Fengyun Wang

Study on China-Laos Forestry Cross-Border Cooperation Strategy Model

Natural resources are the basic elements of economic development. Laos is rich in forest resources, while the technology is backward. On the contrary, the forest resources of China which can be developed and used are less and the developing technology is advanced. In this case, the construction of “One Belt And One Road” provides a lot of opportunities to these two countries on cooperation. This paper analyzes the synergetic dynamics of forestry cross-border coordination strategy and puts forward the “Overseas Jiangsu” mode of forestry cross-border coordination strategy. This paper establishes the framework of cross-border collaborative cloud platform for forestry and analyzes the characteristics of cross-border coordination strategy. Lastly, this paper puts forward the relevant policy recommendations.

Yu He

The Monitoring System for Agricultural Environment Based on Point Surface Fusion with the Internet of Things and WebGIS

Today, the technology of Internet of things in the field of agricultural environmental monitoring has been widely used, but the network monitoring technology based on the node is still faced with the monitoring points distribution design, data space, continuous expression and many other problems. According to the characteristics of agricultural environmental monitoring objects, this paper presents transference of zone simulation and evaluation method, design a set of things based on the “point” of the monitoring data and WebGIS solution based on the “face” of the space data fusion and analysis. In established networking monitoring center system platform based and optimization of WebGIS integrated graphical spatial analysis technology, in Helong and Kaian town of Nong’an County of Jilin Province in the national Spark plan experimental base fusion networking monitoring data and WebGIS spatial data points of agricultural environment monitoring system is established. System to achieve the display of data location map and transference of the regional simulation and evaluation, regional monitoring thematic map management three functions. The results of experimental base in maize field monitoring of growth for the case of application of the system show that the system can effectively realize the transference of agricultural environment dynamic monitoring of the region, corn crop disaster comprehensive monitoring ability can be improved, and can provide a more convenient application services for agricultural production management.

Guifen Chen, Yinglun Li

Study on Social Stability Risk Detection of Large Hydraulic Project Construction Based on Social Vulnerability Evaluation

Reducing vulnerability of social system is the foundation of social stability, if the social system becomes more and more vulnerable, then the social stability risk is greater, on the contrary, it is smaller, which put forward higher request for developing social risk detection platform. Risk detection is a kind of typical fuzzy pattern problem, a technology based on vulnerability evaluation is used for social stability risk. This paper analyzes the reasons of social vulnerability in the large hydraulic project construction area from three dimensions which are characteristic function of social risk exposure, social sensitivity and social adaptability capability, and builts the vulnerability evaluation model and risk detection index system, using entropy method to calculate the detection index weight. The paper finds that Wanzhou social vulnerability (social stability risk) present reduced year by year from 1999 to 2011, and the change caused by the enhancement of social adaptability capability, not by the fall of social system risk. The finding proves that social economic development, social security and public opinion promote the Social adaptability capability in Wanzhou.

Aihua Wu, Changzheng Zhang, Ma Zhijie

Research on Intelligent Decision of Pulmonary Tuberculosis Disease Based on Data Mining

Aiming at the problem that the low diagnostic efficiency and low accuracy of the single data mining method for Diagnosis of pulmonary tuberculosis, In this study, the electronic records of 1203 cases of tuberculosis patients in Changping District City, Beijing City of Beijng and Beijing Institute of tuberculosis control and tuberculosis control were build, Tuberculosis disease diagnosis model is built by application of rough set and decision tree method, On the basis of this, the diagnosis system of pulmonary tuberculosis was constructed. In this study, the combining method of rough set and decision tree was approached to attribute reduction, the model reduced redundant 57 attributes and remained 22 attributes, and articled 7 the decision rules. The model accuracy is 89.46%. Compared with the non reduction method, the decision rule was reduced by 128%, and the accuracy of the model remained unchanged. The research results showed that the algorithm can reduce the time and space complexity of the algorithm while ensuring the accuracy of the model, so as to improve the efficiency of the mining, and provide some references for clinical diagnosis.

Guifen Chen, Wang Ke, Ma Li

Removing Stray Noise Quickly from Point Cloud Data Based on Sheep Model

The noise data could be produced when we scanned the object by Handy 3D scanner due to human factors, the target surface and the instrument itself factors etc. Noised point cloud data could seriously affect the precision and efficiency of three-dimensional reconstruction in late stage. To this problem, we used the sheep body’s three-dimensional point cloud data and changed the algorithm of k-nearest neighbors and presented method that combined the k-nearest neighbor denoising and median filtering. Firstly, the improved k-nearest neighbors algorithm could establish topology relationship fast, identify and delete some noise data; then, using the filter method processed the point cloud data and all noise data could be identified and deleted. The experimental results show that the method we presented can eliminate the stray noise from the point cloud data quickly and accurately and keep ideal target.

Chunlan Wang, Heru Xue, Xinhua Jiang, Yanqing Zhou, Liyan Wang

Modelling and Predicting of Soil Electrical Conductivity and PH from Semi-arid Grassland Using VIS-NIR Spectroscopy Technology

The electrical conductivity (EC) and pH value are key indicators for soil physical and chemical properties, which can reflect the level of soil acid and alkali, furthermore, influence the vegetation growth. The spectroscopy technique can estimate and evaluate electrical conductivity and pH value rapidly and efficiently, which can provide useful information on the real-time soil management in the semi-arid rangeland or grassland. We picked the semi-arid grassland of northern China covering an area about 200 km2 as the target research area, given that it is highly sensitive to grazing and mining affect. Soil samples were collected from 72 sampling sites in this area, which covered grazing exclusion, over grazing and grassland restoration area. The SVC HR-1024 spectroradiometer was used to acquire soil spectrum. This study aims to indicate the spectral characteristic for soil EC and pH, and propose a predicting modeling method with optimal input spectral region and transformation by comparing the support vector machine (SVM) regression method and partial least squares (PLSR) regression modeling method. Our results showed that: (1) once EC value is larger than 0.10 μs/m, the soil spectral reflectance decreases with increasing of EC value. The absorption depth, width and area at 1900 nm reduce with increasing of EC value as well; (2) There are positive correlation between EC, pH value and soil spectral reflectance. The highest correlation coefficient value of 0.7 between pH and reflectance is recorded at visible region around 500 nm; (3) The SVM modeling method produce the higher prediction accuracy (RPD = 2.18, RMSE = 0.035, R2 = 0.78 for EC, RPD > 3, RMSE = 0.349, R2 = 0.91 for pH) rather than PLSR methods in soil EC and pH prediction. This study indicated that it was possible to use the spectroradiometer technology to predict EC and pH value for the soil from semi-arid grassland, which would provide the basis for soil acid and alkali detecting using hyper-spectral remote sensing technology.

ShangBin Lei, NiSha Bao, ShanJun Liu, XiaoCui Liu

Effect of Plants Combination in Purifying Farmland Drainage

Drainage from farmland contains a lot of nitrogen and phosphorus, it is one of the important causes of water eutrophication. In order to reduce the concentration of nutrients before it discharged into receiving waters, 7 aquatic plants were selected to plant in outdoor planting box in the experiment, 5 different aquatic plant combinations were constructed, the removal effect of different combination was studied under same conditions, the reduction rule was researched, and the nitrogen and phosphorus in sediment were investigated. The results showed: after 49 days, the purifying effect of aquatic plants was significantly higher than that with no plant. Among them, the combination with Lythrum salicaria, Reed, Canna has the best effect in TN and TP removal, the removal rate reach: 90.98%, 95.95%, 98.46% respectively. Reductive process of total nitrogen, ammonia nitrogen and total phosphorus in water are accord with polynomial regression, the concentration decreased along with time increasing. When initial nitrogen and phosphorus content in sediment is higher, nitrogen and phosphorus in the sediment will decrease because of plants absorbing; whereas the initial sediment nitrogen and phosphorus content is low, nitrogen and phosphorus in the water can transfer into the sediment, at the same time, the water was purified.

Songmin Li, Qingyun Zhou, Nana Han, Shuhong Sun

Problems and Countermeasures of 3S Technologies Application in Precision Agriculture

3S technologies are the core technologies of precision agriculture. On the basis of deep analysis of the current 3S technologies application in precision agriculture, this thesis points out some problems about this application, mainly including incomplete agricultural remote sensing mode, low level of remote sensing interpretation, low standardization and sharing degree of remote sensing, lack of GIS basic data. It also puts forward some suggestions and countermeasures to solve these problems, including improving and expanding agriculture database, researching the mechanism of agricultural remote sensing image interpretation, enhancing standardization of remote sensing data, improving positioning accuracy of farmland operations, attaching importance to integration of new farm machinery and 3S technologies, and applying seamless integration of multi-source spatial data.

Qiulan Wu, Zhihong Liu, Dandan Yang, Zhenrong Han

Feature Selection for Cotton Matter Classification

Feature selection are highly important to improve the classification accuracy of recognition systems for foreign matter in cotton. To address this problem, this paper presents six filter approaches of feature selection for obtaining the good feature combination with high classification accuracy and small size, and make comparisons using support vector machine and k-nearest neighbor classifier. The result shows that filter approach can efficiently find the good feature sets with high classification accuracy and small size, and the selected feature sets can effectively improve the performance of recognition system for foreign matter in cotton. The selected feature combination has smaller size and higher accuracy than original feature combination. It is important for developing the recognition systems for cotton matter using machine vision technology.

Xuehua Zhao, Ying Huang, Zhao Li, Shukai Wu, Xiuhong Ma, Hua Chen, Xu Tan

Effect of Calibration Set Selection on Quantitatively Determining Test Weight of Maize by Near-Infrared Spectroscopy

To study the effect of calibration set on quantitatively determining test weight of maize by near-infrared spectroscopy, 584 maize samples were collected and scanned for near-infrared spectral data. Test weight was measured following the standard GB 1353-2009, resulting the sample test weight of 693–732 g•L−1. Two calibration models were respectively built using partial least squares regression, based on two different calibration sets. Test weight of two calibration sets distribute differently, with normal and homogeneous distributions. Both quantitative models were selected by root mean square error of cross validation (RMSECV), and evaluated by validation set. Results show the RMSECV of the model based on normal distribution calibration set is 4.28 g•L−1, the RMSECV of the model based on homogeneous distribution calibration set is 2.99 g•L−1, the predication of two models have significant difference for the samples with high or low test weight.

Lianping Jia, Peng Jiao, Junning Zhang, Zhen Zeng, Xunpeng Jiang

Research on Method of Image Extraction for Crop Monitoring with Multi Rotor UAV

In this paper, the distribution of weeds in winter wheat was obtained by UAV. A model is established by K value clustering and edge detection algorithms. Key images of different flying angle of UAV for farmland weeds were extracted. The research results show that the edge detection algorithm is suitable for UAV image processing. The recognition accuracy of the weeds was more than 90%. The accuracy of the identification of three typical grass conditions is achieved 98.3%. The conclusion of the study is to provide guidance for UAV variable spraying.

Wei Ma, Xiu Wang, Lijun Qi, Cuiling Li

Prediction of Drying Indices for Paddy Rice in a Deep Fixed-Bed Based on Neural Network

In this study, four artificial neural network models are developed for paddy rice drying in a deep fixed-bed to predict five drying performance indices, including additional crack percentage, drying moisture uniformity, energy efficiency rate, germinating percentage and drying time. The four neural networks are BP, RBF, GRNN and ELMAN. After plenty of trials with a variety of neural network architectures, neural network with five inputs and five outputs is better than network with five inputs and any other outputs. Five drying parameters including paddy original moisture content, air temperature, air velocity, paddy thickness and tempering time are regarded as input vectors of the neural networks. The experimental results show that neural networks have good performance in predicting the paddy drying process. And also, the simulation indicate that the RBF neural network has advantages over other three neural networks in performance.

Danyang Wang, Chenghua Li, Benhua Zhang, Ling Tong

Definition Management Zones of Drip Irrigation Cotton Field Based on the GIS and RS

A fuzzy c-means clustering algorithm was used to assign soil nutrient to management zones which was based on remote sensing as data source in Nongwushi 81 Tuan Xin Jiang drip irrigation in cotton based on GIS and RS. The results showed that the variation coefficient of nutrient index was decreased in management zones based on remote sensing data source, space distribution were all the same direction. There were no significant differences among the three management zones. The space variation of soil nutrient content was different lowest in the same management zone. The conformity degree of the integration of management zones based on remote sensing NDVI as data was reached 75.47%. A fuzzy c-means clustering algorithm which was based on remote sensing as data source can achieve good management zones results, which could be used to help guide the rate of variable inputs and precise fertilizer application and provide the theory basis of soil nutrient management in cotton.

Ze Zhang, Zhouyang Li, Lulu Ma, Xin Lv, Lifu Zhang

A Survey on Development of “Internet + Farmer Cooperative” in China

As a new production mode, “Internet+” helps achieve innovative development and mutual benefits by providing online and information-based functions of traditional industries. In spite of the numerous explorations and practices of “Internet+” that have been made so far in China, for farmer cooperatives, it is still a new thing requiring much development. In this paper, current conditions of “Internet + farmer cooperative” business pattern in China are studied through field investigations and literature review. Four existing modes are summarized from the perspective of industrial chain. Also, issues and challenges confronted by farmer cooperatives during use of “Internet+” are analyzed on three levels: society, industry, and entity. Finally, corresponding policy recommendations are proposed with the intention of boosting development of “Internet + farmer cooperatives” in China.

Guo-peng Zhang, Jie-ling Zou, Jing Hua, Li-ming Wang, Jing-shun Du, Yu-bin Wang

Hyperspectral Estimation of Leaf Area Index of Winter Wheat Based on Akaike’s Information Criterion

Leaf Area Index (LAI) is an important parameter for assessing the crop growth and winter wheat yield prediction. The objectives of this study were(1) to establish and verify a model for the LAI of winter wheat, where the regression models, extended the Grey Relational Analysis (GRA), Akaike’s Information Criterion (AIC), Least Squares Support Vector Machine (LSSVM) and (ii) to compare the performance of proposed models GRA-LSSVM-AIC. Spectral reflectance of leaves and concurrent LAI parameters of samples were acquired in Tongzhou and Shunyi districts, Beijing city, China, during 2008/2009 and 2009/2010 winter wheat growth seasons. In the combined model, GRA was used to analyse the correlation between vegetation index and LAI, LSSVM was used to conduct regression analysis according to the GRA for different vegetation index order of the number of independent variables, AIC was used to select the optimal models in LSSVM models. Our results indicated that GRA-LSSVM-AIC optimal models came out robust LAI evaluation (R = 0.81 and 0.80, RMSE = 0.765 and 0.733, individually). The GRA-LSSVM-AIC had higher applicability between different years and achieved prediction of LAI estimation of winter wheat between regional and annual levels, and had a wide range of potential applications.

Haikuan Feng, Fuqin Yang, Guijun Yang, Haojie Pei


Weitere Informationen

Premium Partner