基于REMCC-BPNN的稻瘿蚊发生量预测研究

doi:10.11924/j.issn.1000-6850.2013-2871

中国农学通报 ›› 2014, Vol. 30 ›› Issue (13): 289-293.doi: 10.11924/j.issn.1000-6850.2013-2871

所属专题：水稻

基于REMCC-BPNN的稻瘿蚊发生量预测研究

隆轲张红燕谢元瑰李诚

收稿日期:2013-11-03 修回日期:2013-11-21 出版日期:2014-05-05 发布日期:2014-05-05
基金资助:
国家科技支撑计划重大项目“农村物联网基础平台共性关键技术研究”(2012BAD35B05)；湖南省研究生科研创新项目“时间序列分析方法在农业虫害预测中的应用研究”(CX2012B307)。

Study on the Forecast of Orseolia oryzae Emergency Size based on REMCC-BPNN

Received:2013-11-03 Revised:2013-11-21 Online:2014-05-05 Published:2014-05-05

摘要/Abstract

摘要： 为了提高预测稻瘿蚊发生量的准确度，有效防控稻瘿蚊虫害成灾面积，采用基于K近邻样本拟合相对误差绝对值与时序相关系数最小原则优化的BP神经网络预测模型REMCC-BPNN，选取广为认可的气温和降水量为影响因子，对稻瘿蚊的发生量进行独立预测。通过2个实例（化州市晚稻稻瘿蚊发生程度和广西邕宁县稻瘿蚊发生程度）验证显示：REMCC-BPNN模型的独立预测精度分别为94%和100%，明显优于经典回归分析、SVR-CAR、MIV-BPNN等参比模型。可见，REMCC-BPNN模型在虫害发生量预测方面有良好的应用前景。

关键词: 有机产业, 有机产业

Abstract: In order to improve the predictive accuracy of the Orseolia oryzae emergency size and control area affected by Orseolia oryzae effectively, an improved Back-propagation Neural Network (BPNN) model named REMCC-BPNN was proposed. REMCC-BPNN optimizes the training model for BPNN based on the minimum correlation coefficient of the absolute value of the K nearest neighbor training samples’ fitting relative error and the K training samples’ time order. This study utilized air temperature and precipitation as influencing factors to forecast pest management independently. The results of two instances (Orseolia oryzae emergency size in Huazhou City and Yongning County of Guangxi Province) indicated that the prediction accuracy of REMCC-BPNN was 94% and 100% respectively, which was better than that of several traditional used models, such as SVR-CAR, MIV-BPNN. REMCC-BPNN has a promising application prospect in the forecast of pest management.

隆轲张红燕谢元瑰李诚. 基于REMCC-BPNN的稻瘿蚊发生量预测研究[J]. 中国农学通报, 2014, 30(13): 289-293.

参考文献

[1] Lu J S, He L F, Xu J, et al. Study on Breeding of Rice Gall Midge [J]. Plant Diseases and Pests,2011,2(5):34-37.
[2] Feng R, Qin X Y, Tang J H, et al. Enhancement of Rice Germplasm by Pyramiding the Cultivars with Multi- resistance to Orseolia oryzae (Wood-Mason)[J]. Agrucultural Science & Technology,2009, 10(1):7-10.
[3] 陈观浩,张耀忠,杨果丰.晚稻稻瘿蚊主害代发生程度的预测模型[J].华东昆虫学报,2006,15(2):137-139.
[4] 刘思松,昝坚.采用判别分析预报稻瘿蚊主害代的发生趋势[J].昆虫知识,1998,35(6):323-325.
[5] Venkatesan R, Balamurugan B. A real-time hardware fault detector using an artificial neural network for distance protection[J]. IEEE Transactions on Power Delivery,2001,16(1):75-82.
[6] Vapnik V N. The nature of statistical learning theory[M]. New York: Springer Verlag Press,1995:87-189.
[7] 张永生,袁哲明,熊洁仪,等.基于 SVR和 CAR的多维视觉序列分析及其在生态学中的应用[J].生态学报,2007,27(6):2419-2424.
[8] 袁哲明,张永生,熊洁仪.基于 SVR的多维时间序列分析及其在农业科学中的应用[J].中国农业科学,2008,41(8):2485-2492.
[9] 向昌盛,周子英.基于支持向量机的害虫多维时间序列预测[J].计算机应用研究,2010,27(10):3694-3697.
[10] 张孝羲,周立阳.害虫预测预报基础知识[J].昆虫知识,1995,32(1): 55-60.
[11] Hagan M T, Menhaj M B. Training feed forward networks with Mraquart algorithm[J]. IEEE Trans on Neural Networks,1994,5(6): 75-79.
[12] 王凌.混合优化策略和神经网络中若干问题的研究[J].清华大学学报,1999:66-70
[13] 彭祖赠.数学模型与建模方法[M].大连:大连海事大学出版社, 1997:69-83.
[14] 汪璇,吕家恪.集成 GASA混合学习策略的 BP 神经网络在水稻虫害预测中的应用[J].中国农学通报,2007,23(4):404-409.
[15] 郝红卫,蒋蓉蓉.基于最近邻规则的神经网络训练样本选择方法[J].自动化学报,2007,33(12):1247-1251.
[16] 谢元瑰,张红燕,陈玉峰.基于 REMCC-BPNN的粮食预测研究[J].安徽农业科学,2013,41(6):2775-2777,2781.
[17] Dombi G M, Nandi P, Saxe J M, et al. Prediction of rib fracture injury outcome by an artificial neural network[J]. Journal of Trauma-Injury Infection & Critical Care,1995,39(5):915-921.
[18] 孙凡,陈汉荣.稻瘿蚊发生趋势的 B-P网络预测模型[J].计算机仿真,2000,17(3):61.

基于REMCC-BPNN的稻瘿蚊发生量预测研究

Study on the Forecast of Orseolia oryzae Emergency Size based on REMCC-BPNN

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

关于本刊

作者中心

审者中心

在线期刊

联系我们

[1]	吴中波,陈远新,赵光洁,郑芳. 区域有机产业链完整性评价指标体系研究初探[J]. 中国农学通报, 2016, 32(18): 198-204.
[2]	刁品春范雪梅. 在新版《有机产品》标准和相关法规要求下做好有机产业的初探[J]. 中国农学通报, 2013, 29(15): 216-220.