欢迎访问《棉花学报》! 今天是

棉花学报 ›› 2018, Vol. 30 ›› Issue (4): 300-307.doi: 10.11963/1002-7807.wxfwxf.20180709

• 研究与进展 • 上一篇    下一篇

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. 1.西京学院理学院,西安 710123;2. Tableau Software,Seattle,WA 98103,USA
  • 收稿日期:2018-03-01 出版日期:2018-07-15 发布日期:2018-07-15
  • 基金资助:
    国家自然科学基金(61473237)

Application of modified Deep Belief Network in Forecasting Cotton Diseases and Insect Pests

Wang Xianfeng1, Ding Jun1, Zhu Yihai2   

  1. 1. School of Science, Xijing University, Xi'an 710123, China; 2. Tableau Software, Seattle, WA 98103, USA
  • Received:2018-03-01 Online:2018-07-15 Published:2018-07-15

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。

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 words: cotton; disease and pest forecasting; environmental information; deep belief network; restricted Boltzmann machine

中图分类号: 
  • S562:TH164