Please wait a minute...

   检索  |  高级检索
棉花学报  208, Vol. 30 Issue (4): 300-307    DOI: 10.11963/1002-7807.wxfwxf.20180709
  研究与进展 本期目录 | 过刊浏览 | 高级检索 |
一种改进的深度置信网络在棉花病虫害预测中的应用
王献锋1,丁军1,朱义海2
1.西京学院理学院,西安 710123;2. Tableau Software,Seattle,WA 98103,USA
Application of modified Deep Belief Network in Forecasting Cotton Diseases and Insect Pests
Wang Xianfeng1, Ding Jun1, Zhu Yihai2
1. School of Science, Xijing University, Xi'an 710123, China; 2. Tableau Software, Seattle, WA 98103, USA
全文: PDF(1125 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 【目的】棉花病虫害发生和发展主要与环境信息相关,由于环境信息多且复杂多变,使得棉花病虫害预测方法研究具有一定的挑战性。本文旨在探索及时、准确地预测棉花病虫害的方法。【方法】提出1种基于环境信息和深度信念网络的棉花病虫害预测模型。该模型由3层限制玻尔兹曼机网络(Restricted Boltzmann machines,RBM)和1个监督反向传播(Back-propagation,BP)网络组成,利用RBM将环境信息数据转换到与病虫害发生相关的新的特征空间,利用BP网络对最后1层输出的特征向量进行分类预测,利用动态学习率和对比分散准则加快RBM的训练过程,并利用该模型对近6年棉花的棉铃虫、棉蚜虫、红蜘蛛和黄萎病、枯萎病进行预测试验。【结果】与传统棉花病虫害预测模型相比,提出的预测模型能够深度挖掘棉花病虫害发生与环境信息之间的深层次相关关系,具有更高的预测精度,预测平均正确率在83%以上。【结论】该方法是1种有效的农作物病虫害预测方法,为棉花病虫害防治提供了有效的技术支持。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
王献锋
丁军
朱义海
关键词 棉花病虫害预测环境信息深度信念网络受限玻尔兹曼机    
Abstract:[Objective] The occurrence and development of cotton diseases and insect pests are mainly related to environmental information. Because this environmental information is various, complex and unstable, the study on the  prediction methods of cotton diseases and insect pests is a certain challenge. This study aims to establish a forecasting model for the timely and accurate prediction of cotton diseases and insect pests. [Method] A forecasting model of cotton diseases and insect pests is proposed based on environmental information and a modified Deep Belief Network (DBN) that is constructed by a three-layer restricted Boltzmann machine (RBM) and a supervised back-propagation (BP) network. In the method, the RBM is used to transform the original environmental information vectors into a new feature space related to the diseases and pests; the BP network is trained to classify and forecast the features generated by the last RBM layer and two rules of dynamic learning and comparison and dispersion are adopted to accelerate the training process of RBM. The proposed model was validated on a dataset of cotton bollworm, aphids, spider, cotton Verticillium wilt, and Fusarium wilt in a recent six-year period. [Result] Compared with the traditional prediction models of cotton diseases and insect pests, the proposed model can deeply explore the extensive correlation between the occurrence of cotton diseases and pests and environmental information. The results show that the proposed model has a higher accuracy compared with the classical predictive models, and the average forecasting accuracy is above 83%. [Conclusion] The proposed method is an effective crop disease and pest forecasting method that can provide a technical support for preventing cotton disease and insect pests.
Key wordscotton    disease and pest forecasting    environmental information    deep belief network    restricted Boltzmann machine
收稿日期: 2018-03-01      出版日期: 2018-08-16
中图分类号:  S562:TH164   
基金资助:国家自然科学基金(61473237)
引用本文:   
王献锋,丁军,朱义海 一种改进的深度置信网络在棉花病虫害预测中的应用[J]. 棉花学报, 208, 30(4): 300-307.
Wang Xianfeng,Ding Jun,Zhu Yihai Application of modified Deep Belief Network in Forecasting Cotton Diseases and Insect Pests[J]. Cotton Science, 208, 30(4): 300-307.
链接本文:  
http://journal.cricaas.com.cn/Jweb_mhxb/CN/10.11963/1002-7807.wxfwxf.20180709      或      http://journal.cricaas.com.cn/Jweb_mhxb/CN/Y208/V30/I4/300
[1] Patki S S, Sable G S. A review: Cotton leaf disease detection[J]. IOSR Journal of VLSI and Signal Processing, 2016, 6(3): 78-81.<br />
[2] 新疆维吾尔自治区植物保护站. 2017年新疆棉花主要病虫害发生长期趋势预报[R/OL]. (2017-02-28) [2018-03-01]. http://www.cncotton.com/sy_59/xjztc/201702/t20170228_567968.html.<br />
[3] Joseeduardoba M, Pauloc S, Markl G, et al. Development of ramulosis disease of cotton under controlled environment and field conditions[J]. Phytopathology, 2009, 99(6): 659-665.<br />
[4] Singh D, Singh P, Gill J S, et al. Weather based prediction model for forecasting cotton leaf curl disease in American cotton[J]. Indian Phytopathology, 2010, 62(1):87-90.<br />
[6] Buttar D S, Singh P. Cotton leaf curl virus disease (CLCuVD) predictive model based on environmental variables[J]. Indian Journal of Agricultural Sciences, 2017,87(5): 681-684.<br />
[7] 赵冰梅, 李贤超, 王俊刚. 2011年新疆兵团棉花病虫害发生特点及原因分析[J]. 中国棉花, 2012, 39(3): 9-11.<br />
Zhao Bingmei, Li Xianchao, Wang Jungang. Analysis of the characteristics and causes of cotton disease and insect pests in Xinjiang Corps in 2011[J]. China Cotton, 2012, 39(3): 9-11.<br />
[8] 刘俊稚. 几种典型植物对大气CO2浓度升高的生理和病理响应研究[D]. 杭州: 浙江大学, 2010.<br />
Liu Junzhi. Study on eco-physiological and pathological responses of several typical plant species to elevated atmospheric CO2[D]. Hangzhou: Zhejiang University, 2010.<br />
[9] 张建华, 祁力钧, 冀荣华, 等. 基于粗糙集和BP神经网络的棉花病害识别[J].农业工程学报, 2012, 28(7): 161-167.<br />
Zhang Jianhua, Qi Lijun, Ji Ronghua, et al. Cotton diseases identification based on rough sets and BP neural network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2012, 28(7): 161-167.<br />
[10] He Q, Ma B, Qu D. Cotton pests and diseases detection based on image processing[J]. Telkomnika, 2013, 11(6): 3445-3450.<br />
[11] 赵庆展, 靳光才, 周文杰, 等. 基于移动GIS的棉田病虫害信息采集系统[J]. 农业工程学报, 2015, 31(4): 183-190.<br />
Zhao Qingzhan, Jin Guangcai, Zhou Wenjie, et al. Information collection system for diseases and pests in cotton field based on mobile GIS[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2015, 31(4): 183-190. <br />
[12] 陈光绒, 李小琴.基于物联网技术的农作物病虫害自动测报系统[J]. 江苏农业科学, 2015, 43(4): 406-410.<br />
Chen Guangrong, Li Xiaoqin. Automatic measurement and report system of crop diseases and insect pests based on Internet of things technology[J]. Jiangsu Agricultural Science, 2015, 43(4): 406-410.<br />
[13] 王翔宇, 温皓杰, 李鑫星. 农业主要病害检测与预警技术研究进展分析[J]. 农业机械学报, 2016, 47(9): 266-277.<br />
Wang Xiangyu, Wen Haojie, Li Xinxing. Analysis of the research progress on the detection and early warning technology of major agricultural diseases[J]. Journal of Agricultural Machinery, 2016, 47(9): 266-277. <br />
[14] 王献锋, 张善文, 王震, 等. 基于叶片图像和环境信息的黄瓜病害识别方法[J]. 农业工程学报, 2014, 30(14): 148-153.<br />
Wang Xianfeng, Zhang Shanwen, Wang Zhen, et al. Recognition of cucumber diseases based on leaf image and environmental information[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2014, 30(14): 148-153.<br />
[15] 许金霞. 基于WebGIS棉花虫害监测系统平台研发[D]. 石河子: 石河子大学, 2017.<br />
Xu Jinxia. Research and development platform of cotton pest monitoring system based on WebGIS[D]. Shihezi: Shihezi University, 2017.<br />
[16] Sannakki S, Rajpurohit V S, Sumira F, et al. A neural network approach for disease forecasting in grapes using weather parameters[C/OL]// 2013 Fourth International Conference on Computing, Communications and Networking Technologies, Tiruchengode, India July 4, 2013 to July 6, 2013. New York: IEEE, 2014: 1-5 (2014-01-30) [2018-03-01]. https://doi.org/10.1109/ICCCNT.2013.6726613.<br />
[17] Shi Mingwang. Based on time series and RBF network plant disease forecasting [J]. Procedia Engineering, 2011, 15: 2384-<br />
23 87.<br />
[18] Ehetisha-mul-haq M, Rashid A, Kamran M, et al. Disease forecasting model for newly emerging bacterial seed and boll rot of cotton disease and its vector (<em>Dysdercus cingulatus</em>)[J/OL]. Archives of Phytopathology & Plant Protection, 2017, 50: 885-899 (2017-11-14) [2018-03-01]. https://doi.org/10.1080/<br />
03 235408.2017.1401759.<br />
[19] 王秀美. 深度学习在回归预测中的研究及应用[D]. 泰安: 山东农业大学, 2017.<br />
Wang Xiumei. Research and application of deep learning in regression prediction[D]. Tai'an: Shandong Agricultural University, 2017.<br />
[20] 张善文, 张传雷, 丁军. 基于改进深度置信网络的大棚冬枣病虫害预测模型[J]. 农业工程学报, 2017, 33(19): 202-208.<br />
Zhang Shanwen, Zhang Chuanlei, Ding Jun. Disease and insect pest forecasting model of greenhouse winter jujube based on modified deep belief network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(19): 202-208.<br />
[21] 王秀美, 牟少敏, 邹宗峰, 等. 基于深度学习的小麦蚜虫预测预警[J]. 江苏农业科学, 2018, 46(5):183-187.<br />
Wang Xiumei, Mou Shaomin, Zou Zongfeng, et al. Prediction and early warning of wheat aphids based on deep learning[J]. Jiangsu Agricultural Sciences, 2018, 46(5): 183-187.<br />
[22] 占卫国. 马尔科夫转移矩阵在江汉平原2012年棉花病虫害预测中的应用[J]. 中国棉花, 2012, 39(1): 22-24.<br />
Zhan Weiguo. Application of Markov transfer matrix in on cotton diseases forecasting and pest prediction in Jianghan plain, Hubei province[J]. China Cotton, 2012, 39(1): 22-24.<br />
[23] 胡小平, 梁承华, 杨之为, 等. 植物病虫害BP神经网络预测系统的研制与应用[J]. 西北农林科技大学学报(自然科学版), 2001, 29(2): 73-76.<br />
Hu Xiaoping, Liang Chenghua, Yang Zhiwei, et al. Development and application of the BP neural network prediction system on plant diseases and pests[J]. Journal of Northwest Science-Technology University of Agriculture and Forest (Natural Science Edition), 2001, 29(2): 73-76. <br />
[24] 姜培刚.气候变化对昌邑市农作物病虫害发生程度的影响[D]. 泰安: 山东农业大学, 2015.<br />
Jiang Peigang. Influence of climate change on the occurrence of crop diseases and insect pests in Changyi[D]. Tai’an: Shandong Agricultural University, 2015. <br />
[25] 陈兵, 李少昆, 王克如, 等. 棉花黄萎病病叶光谱特征与病情严重度的估测[J]. 中国农业科学, 2007, 40(12): 2709-2715.<br />
Chen Bing, Li Shaokun, Wang Keru, et al. Spectrum characteristics of cotton single leaf infected by Verticillium wilt and estimation on severity level of disease[J]. Scientia Agricultura Sinica, 2007, 40(12): 2709-2715. <br />
[26] 陈忠凤, 吴昊, 段沙丽, 等. 棉花苗期病害气象等级预报方法[J]. 棉花科学, 2007, 29(5): 28-29.<br />
Chen Zhongfeng, Wu Hao, Duan Shali, et al. Prediction method of meteorological grade for cotton seedling diseases[J]. Cotton Sciences, 2007, 29(5): 28-29.<br />
[27] 吴昊, 杨柳, 鲁速明, 等. 江西棉花主要病虫害影响预估指标研究[J]. 棉花科学, 2017, 39(5):13-16.<br />
[1] 李冬旺, 张永江, 刘连涛, 孙红春, 刘玉春, 白志英, 李存东. 干旱胁迫对棉花冠层光合、光谱和荧光的影响[J]. 棉花学报, 2018, 30(3): 242-251.
[2] 栗战帅, 魏恒玲, 庞朝友, 王寒涛, 马启峰, 宿俊吉, 陈全家, 曲延英, 范术丽, 喻树迅. 棉花果枝节间长短性状内源激素的差异以及外施激素对其影响[J]. 棉花学报, 2018, 30(3): 224-230.
[3] 李淑叶, 马慧娟, 张思平, 刘绍东, 沈倩, 陈静, 葛常伟, 庞朝友, 赵新华. 外源24-表油菜素内酯对低温胁迫下棉花幼苗光合生理的影响[J]. 棉花学报, 2018, 30(3): 252-260.
[4] 李映程, 张国丽, 任毓忠, 李海强, 武刚, 李天义, 李国英, 张莉. 基于rDNA-ITS和组蛋白3基因序列分析鉴定新疆棉花叶斑病病原[J]. 棉花学报, 2018, 30(3): 271-281.
[5] 陈丽华, 何鹏飞, 袁德超, 欧晓慧, 吴毅歆, 何月秋. 一种防治棉花黄萎病的生物复合种衣剂的研制[J]. 棉花学报, 2018, 30(3): 282-290,封三.
[6] 梅磊, 李玲, 肖钦之, 陈进红, 祝水金. 陆地棉植物络合素合酶基因的鉴定与功能预测[J]. 棉花学报, 2018, 30(3): 215-223.
[7] 徐瑞强, 董合林, 徐文修, 卡地力亚·阿不都克力木, 阿地娜·白山哈力, 董泰丽, 付传翠, 吾仁图雅·皮力加, 唐江华. 喷施浓缩沼液对棉花幼苗生长发育和生理特性的影响[J]. 棉花学报, 2018, 30(3): 261-271.
[8] 张希鹤, 李岩, 郁凯, 霍钰阳, 王友华, 陈兵林. 黄萎病胁迫影响棉花幼苗光合及叶绿素荧光特性的机理[J]. 棉花学报, 2018, 30(2): 136-144.
[9] 龙金辉, 朱真峰. 融合马尔可夫随机场与量子粒子群聚类的棉花图像分割算法[J]. 棉花学报, 2018, 30(2): 197-204.
[10] 孔令磊, 石玉真, 李邵琦, 黎波涛, 李俊文, 刘爱英, 龚举武, 商海红, 巩万奎, 葛群, 王艳玲, 宋威武, 袁有禄. 棉花陆海渐渗系双交分离群体产量和纤维品质性状的QTL定位[J]. 棉花学报, 2018, 30(2): 119-127.
[11] 张帆, 李晓林, 张敬泽, 祝水金. 病原物协同致病性对棉花黄萎病严重度的影响[J]. 棉花学报, 2018, 30(2): 188-196.
[12] 李青军, 张 炎, 哈丽哈什·依巴提, 冯固. 膜下滴灌棉花对3种水溶性磷肥的利用效率和产量响应[J]. 棉花学报, 2018, 30(2): 172-179.
[13] 乔清华, 张传云, 袁哲诚, 王芙蓉, 张军. 多年连作土壤中棉花根际细菌群落结构及其动态[J]. 棉花学报, 2018, 30(2): 128-135.
[14] 宋兴虎, Tufail Ahmed Wagan, Biangkham Souliyanonh, Saif Ali, 黄颖, 袁源, 杨国正. 氮肥用量及其后效对棉花产量和生物质累积动态的影响[J]. 棉花学报, 2018, 30(2): 145-154.
[15] 高超, 李明思, 蓝明菊. 土壤水分空间胁迫对棉花根系构型的影响[J]. 棉花学报, 2018, 30(2): 180-187.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed