Computer and Computing Technologies in Agriculture XI

Inhaltsverzeichnis

1. Frontmatter

2. Research and Application of Spark Platform on Big Data Processing in Intelligent Agriculture of Jilin Province

   Siwei Fu, Guifen Chen, Shan Zhao, Enze Xiao

   Abstract

   Aiming at the demand of real-time massive data processing of Intelligent Agriculture in Jilin Province, this paper studies the big data processing of Intelligent Agriculture in Jilin Province based on Spark platform by acquiring real-time data through monitoring platform. This study first conducted the performance comparison experiment of Hadoop and Spark data processing platform, then used the Spark distributed cluster computing platform, real-time processing the big data of monitoring area. The experimental results show that the Spark platform speeds up 11.4 times faster than the Hadoop platform in the case of 100 million data sizes; and based on the Spark platform for real-time processing of big data intelligent agricultural monitoring network, not only provides memory calculations to reduce IO overhead, but also the results are faster and more accurate. The research results provide strong support for the implementation of precision agriculture technology in intelligent agriculture.

3. Summary of Agricultural Drought Monitoring by Remote Sensing at Home and Abroad

   Meng Wang, Tao Liu, Shouzhen Ling, Xueyan Sui, Huimin Yao, Xuehui Hou

   Abstract

   Drought is one of the major natural disasters which causes very severe impacts on economy and society, remote sensing is the efficient method which can dynamic monitor drought at a great range of scale, the research on agricultural drought monitoring has been an important issue. This paper introduces the principle of agricultural drought monitoring based on remote sensing technology, and reviews the current remote sensing approaches in drought monitoring. Combined with the current research hotspots, this paper offers the further research ideas by discussing the dominances and limitations of these methods.

4. Research and Application of 3D Visualization Plug-in Integration with ArcGIS

   Yinglun Li, Guifen Chen, Dongxue Wang

   Abstract

   With the development of agricultural production data, more and more three-dimensional visualization of monitoring data has become the focus of agricultural information technology research. The application of ArcGIS visualization technology, 3D visualization of auxiliary plug-in, and the national Spark Program demonstration area of farmland monitoring data obtained in Jilin province Nong’an County Helong town of application. In this study, the use of C++ language, the introduction of three-dimensional visualization library SDK, compiled auxiliary plug-in ArcGIS software, optimize the joint jiulongzhen farmland monitoring data 3D visualization. The experimental results show that the preparation of the postprocessing plug-ins integrated into ArcGis software can optimize the 3D visualization of monitoring data, the two-dimensional spatial variability of thematic map than the traditional representation of 3D data more natural, more clear, more intuitive, is of great significance for promoting the development of modern agriculture.

5. Growth and Spectral Characteristics of Grassland in Response to Different Soil Textures

   Xiaochun Zhong, Junchan Wang, Liu Tao, Chengming Sun, Zhemin Li, Shengping Liu

   Abstract

   Biomass and the chlorophyll content are important indicators to measure the growth and development of grasslands. Modeling using hyperspectral data is an important means to monitor grassland growth and development. In this paper, we studied Mexican maize grass, hybrid Pennisetum and hybrid Sudan grass under different soil texture treatments and determined the correlation between the canopy reflectance spectrum and plant growth status in different soil textures based on hyperspectral data. Our results showed that, under different soil texture treatments, the emergence rate of Mexican maize grass and hybrid Pennisetum did not differ significantly, whereas that of hybrid Sudan grass indicated a significant difference. Under different soil texture treatments, the trend of plant height variation was consistent. In terms of different types of grassland, it is generally feasible to establish a grassland yield spectral model based on the vegetation indexes NDVI and RVI, and the leaf SPAD values of the three types of grassland best fit the spectral parameter red edge area.

6. Soil Moisture Estimation by Combining L-Band Brightness Temperature and Vegetation Related Information

   Yuanyuan Fu, Chunjiang Zhao, Guijun Yang, Haikuan Feng

   Abstract

   Passive radiometry at L-band has been widely accepted as one of the most promising techniques for monitoring soil moisture content (SMC). However, with vegetation cover, the scatter and attenuation of microwave signals by vegetation make the discrimination of SMC related signal complicated. To improve SMC estimate, this study proposed the combined use of L-band brightness temperature (T_B) and optical remote sensing data to take into account the effect of vegetation. The normalized difference infrared index (NDII) and enhanced vegetation index (EVI) were used as proxy for including the effect of vegetation water content and structure. Considering viewing angle effects, T_B data were normalized to three different angles (7°, 21.5°, and 38.5°). The model based on the combination of NDII and horizontally polarized T_B normalized to 7° produced the best result (R² = 0.678, RMSE = 0.026 m³/m³). It suggests that involving NDII into the model could significantly improve pasture covered SMC estimation accuracy.

7. Study on Precision Fertilization Model Based on Fusion Algorithm of Cluster and RBF Neural Network

   Shan Zhao, Guifen Chen, Siwei Fu, Enze Xiao

   Abstract

   Precision fertilization is the core content of precision agriculture technology. There was a complex non-linear relationship between crop optimal fertilization and soil fertility. The single model is difficult to accurately describe its complex relationship and change law, making the crop accurate fertilizer is difficult to determine; Neural network technology to solve this problem provides a new way of thinking. But a single radial basis function network (RBF) neural network fertilization model is too dependent on the selection of the hidden layer data center. Therefore, this paper proposes a decision-making technique based on fuzzy C-means (FCM) clustering and RBF neural network fusion algorithm. The fusion algorithm first uses the FCM algorithm to select multiple RBF networks in the training samples. Based on this, the least squares (OLS) training network is used to optimize the data center. Finally, an improved RBF neural network model is established. In this paper, the model is applied to the maize precision operation demonstration base, soil nutrient and maize yield as the input of neural network, using the precision fertilization amount of maize as output. The model of precision fertilization of maize was established. And the model was used to make the precision fertilization decision of maize. Experimental results show: The improved RBF neural network is compared with the traditional BP network to reduce the error by 0.47. Compared with the model, the error of the RBF neural network method is reduced by 0.045. Significantly improve the prediction accuracy, reduce the calculation time. Can effectively guide the precise fertilization.

8. Study on Three-Dimensional Data Acquisition of Crop Grains

   Zetao Yu, Weiliang Wen, Xinyu Guo, Xianju Lu

   Abstract

   The rapid, efficient and non-destructive 3D morphological data acquisition of plants are great significance to the study of digital plant, functional structural plant model and crop phenotype. This paper discusses 3D data acquisition methods for smaller plant organs, which take maize grain as an example. Smartscan and Micro-CT scanning can be used to obtain the morphological data of the grains. The efficiency, accuracy, processing of data in two scanning ways are compared and analyzed. The results shows that the Micro-CT is more suitable for obtaining information of internal structure of maize grain. While grain morphology in SmartScan can get better visualization than Micro-CT, and the former one can also obtain image texture information. These two kinds of methods for volume measurement have good consistency except for Denghai 605. The study will provide theoretical basis for obtaining 3D data of plant organs at smaller scales.

9. An Agricultural Habitat Information Acquisition and Remote Intelligent Decision System Based on the Internet of Things

   Ze Lin Hu, Yi Gao, Miao Li, Hua Long Li, Xuan Jiang Yang, Zhi Run Ma

   Abstract

   On the basis of the information perception technology and mobile interconnection technology, through the technology of Agriculture Internet of Things, the multi-sensor system integration is realized, and the collaborative sensing of habitat information come true in crop production. This paper designs architecture of hardware and software for the system. By wireless multi-hop and seamless connection technologies of “triple net integration”, common interfaces and scanning technologies of multi-sensor standard signal transform are used to achieve the multi-parameter information acquisition of crop during its growth. Wireless monitoring nodes of the Agriculture Internet of Things are distributed in each measurement point of the farmland, and they are responsible for information collection, pretreatment, and wireless transmission of eight parameters data, including the environment temperature, environment temperature, Light intensity, Carbon dioxide content, soil temperature, soil humidity, soil pH, soil salt. The data processing and service system execute remote data storage and on-line information release. The intelligent decision support system achieve real-time warning of abnormal parameters. Experiments show that the architecture of the system is reasonable, and the system has good accuracy, stability and reliability, in line with the practical application of grassroots agricultural field.

10. Comprehensive Evaluation of Soil Fertility in Yanzhou District Based on Principal Component Analysis

    Qiuting Zhang, Xia Geng

    Abstract

    Soil fertility is the basis of sustainable agricultural development. Scientific and rational evaluation of soil fertility can better promote the development of agricultural informatization and modernization. Based on the data of 166 soil samples in Yanzhou District in 2014, the effects of pH, OM, AN, AP and AK were chosen as evaluation indexes, SPSS was used to analyze the soil fertility status. The results showed that the overall level of soil fertility was below the medium: Among the 166 samples, there were 149 in the medium and low fertility, accounting for 89.76%. The content of soil OM and AN was in medium and slightly lower level. In view of the above results, organic fertilizer, humic acid and nitrogen fertilizer should be added. Soil AP and AK content was in the middle and above the level, so the fertilizer could be maintained in order to achieve balanced fertilization.

11. Advances in Monitoring Soil Nutrients by Near Infrared Spectroscopy

    Yan Wang, Bei Cui, Yanhua Zhou, Xiudong Sun

    Abstract

    Soil nutrients play an important role in crop growth, and traditional monitoring methods are still the first choice for high precision measurement. However, it is necessary to have a quicker and simpler way to improve the efficiency of soil nutrient monitoring because of its long monitoring time, pollution and high labor cost. Near infrared spectroscopy has become the focus of its research because of its rapid and pollution-free advantages. At present, using near infrared spectroscopy to distinguish soil types, soil heavy metal pollution technology has become increasingly mature, but the soil nutrients, such as monitoring of soil organic matter, available phosphorus, available potassium, available nitrogen is still in the research stage. This paper reviews the recent research results of soil nutrients in near infrared spectrum monitoring technology based on collation, summary and key technology of common data processing method, and analysis the advantages and disadvantages of different detection methods for soil nutrient direction of near infrared spectroscopy technology put forward suggestions to further research.

12. Microwave Mixing Technique for Nondestructive Measurement of Moisture Content of Particulate Agricultural Products

    Chenxiao Li, Yanlei Xu, He Gong, Yuanyuan Liu, Qian Song

    Abstract

    A new method for nondestructive measurement of moisture content of particulate agricultural products is developed using microwave mixing technique. A double horn system with a relative vertical distance of one-fourth wavelengths is designed to measure the reflected microwave signals. The particulate materials are interacted with microwave at a frequency of 10.5 GHz, and the reflected microwave signal is mixed with the launch signal. Corns with different moisture contents are chosen as samples. Calibration models for moisture content are proposed in accordance with the measurement of the differential attenuation of the microwave mixing signal. A moisture content from 6.8% to 30.1% is obtained with a coefficient of determination of 0.98 and a standard error of calibration value of 1.12%.

13. China’s Wine Import Industry: An Economic Analysis of Influencing Trade Factors

    Yu Hu, Wei Ma, Ruimei Wang, Huan Song, Weisong Mu, Dong Tian, Jianying Feng

    Abstract

    In recent years, China is undergoing a huge economic transformation since joining in World Trade Organization (WTO) and it has showed an increasing demand for wine. As China’s wine consumption market is increasingly larger, the European market is becoming increasingly saturated, more and more wine foreign trade and foreign capital have chosen to enter China. Since 1996, China’s wine imports have gradually increased and the trade deficit has significantly expanded. Thus, the objective of this study is to analyze the China’s competiveness of wine in the international market. We mainly focus on the factors that most influenced the performance of imported wines from 1995 to 2014. The aim is to testify if the wine imports affect the China’s own wine industry and examine which factors influence the Chinese wine industry most. This study uses Constant Market Share (CMS) econometric model to analyze the influencing factors of China’s grain import fluctuation. The deep introduction on wine trade has important practical significance for the development of international trade and the improvement of industrial policies. The procured result of empirical model demonstrates that competitiveness is not always a predominant factor throughout the period, especially in wine industry.

14. Three - Dimensional Visualization of Soil Nutrient Evolution in Maize Precision Operation Area Based on ArcGIS

    Enze Xiao, Guifen Chen, Shan Zhao, Siwei Fu

    Abstract

    With the development of 3D GIS technology, the application of 3D GIS in agriculture has become a hotspot in agricultural information technology research. A total of 109 soil samples were collected from the soil of Jilin Province Yushu City Gongpeng Town No. 13 Village No. 7 test area. Three - dimensional visualization of soil nutrient evolution in maize precise operation area was carried out by using ArcGIS technology. Firstly, the Kriging optimal interpolation method was used to calculate the sampling points of soil nutrient space in the field of maize test field. Then three-dimensional spatial map of soil available phosphorus, available potassium available nitrogen and other nutrient contents during the period from 2005 to 2009 were established by using the spatial analysis technique of 3D GIS. By comparing its three-dimensional thematic map, analyze trends in the evolution of its soil fertility characteristics. The results showed that the difference of soil fertility was gentle after four years of variable fertilization, and the effect of precision fertilization was verified.

15. Characteristics of the Warming Trend During Winter Wheat Growing Seasons in Jiangsu Province of China

    Xiangying Xu, Xinkai Zhu, Wenshan Guo, Chunyan Li, Jinfeng Ding

    Abstract

    Global warming has great influences on crop yields. However, several researchers have concluded that global warming has taken a “hiatus” in recent years. Here, we hope to identify the temperature trends of the winter wheat growing seasons and quantitatively estimate the effects of temperature variations on wheat yields. We carry out trend analysis on daily maximum (Tmax) and minimum temperatures (Tmin) from 1980 to 2014 in Jiangsu Province of China. The results indicate there are increasing trends for both Tmax and Tmin during 35 years, but no significant trends in the years after 2000. In addition, the increasing rates of the Tmin are larger than those of Tmax over the 35 years within all stations and all growing stages, which suggests that winter wheat is exposed to asymmetrical warming. The results of correlation analysis and regression analysis reveal that increases in Tmin have significant adverse effects on wheat yields.

16. Estimation of Leaf Nitrogen Concentration of Winter Wheat Using UAV-Based RGB Imagery

    Qinglin Niu, Haikuan Feng, Changchun Li, Guijun Yang, Yuanyuan Fu, Zhenhai Li, Haojie Pei

    Abstract

    Leaf nitrogen concentration (LNC) of winter wheat can reflect its nitrogen (N) status. Rapid, non-destructive and accurate monitoring of LNC of winter wheat has important practical applications in monitoring N nutrition and fertilizing management. The experimental site of winter wheat was located at Xiaotangshan National Demonstration Base of Precision Agricultural Research located in Changping District, Beijing, China. High spatial resolution digital images of the winter wheat were acquired using a low-cost unmanned aerial vehicle (UAV) with digital camera system at three key growth stages of booting, flowering and filling during April to June in 2015. Firstly, the acquired UAV digital images were mosaicked to generate a Digital Orthophoto Map (DOM) of the entire experimental site and 15 digital image variables were constructed. Then, based on the ground measured data onto LNC and digital image variables derived from the DOM for 48 sampling plots of winter wheat, linear and stepwise regression models were constructed for estimating LNC. Finally, the optimum model for estimating LNC was screened out by comprehensively considering the coefficient of determination (R²), the root mean square error (RMSE), the normalized root mean square error (nRMSE) and the simplicity of model calibrating and validating. The experimental results showed that the linear regression model of r/b that was one of the digital image variables for estimating LNC had the best accuracy with the model’s calibration and validation of R², RMSE and nRMSE were 0.76, 0.40, 11.97% and 0.69, 0.43, 13.02%, respectively. The results suggest that it is feasible to estimate LNC of winter wheat based on the DOM acquired by UAV remote sensing platform carrying a low-cost, high-resolution digital camera, which can rapidly and non-destructively obtains the LNC of winter wheat experiment site and provide a quick and low-cost method for monitoring N nutrition and fertilizing management.

17. New NNI Model in Winter Wheat Based on Hyperspectral Index

    Wang Jianwen, Li Zhenhai, Xu Xingang, Zhu Hongchun, Feng Haikuan, Liu Chang, Gan Ping, Xu Xiaobin

    Abstract

    Nitrogen nutrition index (NNI) can monitor winter wheat nitrogen status precisely. Current studies by remote sensing data are to construct the above-ground biomass (AGB) and plant nitrogen concentration (PNC) with spectral indices, respectively, and then substitute them into established NNI equation. This leads to an accumulation of unavoidable error. Therefore, the objective in the study was to construct a direct NNI equation with remote sensing data to reduce this error. Field measurements data including AGB, PNC and canopy hyperspectral at different winter wheat growth stages during 2012/2013, 2013/2014, 2014/2015, 2015/2016 growing seasons in Beijing, China were collected. This study was endeavored to establish a vegetation index critical N dilution curve (N_vic) with two different spectral indices, RTVI (Red edge Triangular Vegetation Index) and NDVI/PPR (the ratio of the normalized difference vegetation index to the plant pigment ratio), which are sensitive to AGB and PNC, respectively. The vegetation index NNI (NNI_vi) was calculated from the ratio between the NDVI/PPR and N_vic. Results showed that (1) N_vic can be described by an equation, N_vic = 1106.4(VIRTVI)^−1.512, where RTVI ranged from 2.39 to 22.14; the determination coefficient (R²) was 0.57; (2) The NNI based on the above N_vic dilution curve was in good accordance with the classical NNI, with the root mean square error (RMSE), normalized RMSE (nRMSE) and normalized average error (NAE) of 0.194, 22%, and 11%, respectively. The critical nitrogen dilution model constructed in this study was available for winter wheat nitrogen status monitoring. Thus, this study offers a new method which was suitable and convenient for estimating the NNI of the winter wheat and it can reduce quadric error for constructing NNI through indices directly instead of inversing AGB and PNC.

18. Fruit Trees 3D Data Acquisition and Reconstruction Based on Multi-source

    Sheng Wu, Boxiang Xiao, Weiliang Wen, Xinyu Guo, Long Liu

    Abstract

    In order to realize three-dimensional reconstruction of canopy at different growth stages of fruit trees, 3D data acquisition methods and canopy reconstruction methods were studied. Based on the analysis of morphological and structural changes in fruit phonological phase, and integrating the advantages of different data acquisition techniques, the data acquisition method of fruit tree morphological structure based on multi-source is proposed. In the dormant period, the canopy skeleton is extracted based on point cloud data; in the leaf curtain stage, a new artificial coding method of canopy structure is constructed, and the data of new shoots and leafs is obtained efficiently; and organ template data is obtained synchronously, and the organ template library is constructed. Then, a multi-source data fusion modeling method is proposed to reconstruct the three-dimensional canopy of fruit trees at different growth stages. And the feasibility of the method is verified by 12 year old open central leader system apple trees, the results show that compared with the manual data acquisition method, the method improves the efficiency by more than 5 times, and the error rate is less than 6%. It provides a feasible scheme for the continuous data acquisition and canopy 3D reconstruction of fruit trees, so as to provide technical support for virtual modeling, scientific calculation and experimental simulations.