﻿ 基于农业气象的稻瘟病发生程度预警数学模型

# 基于农业气象的稻瘟病发生程度预警数学模型An Early Warning Mathematical Model of Rice Blast Degree Based on Agrometeorology

Abstract: Objective: This study aims at prediction of the occurrence degree of rice blast by meteorological factor data. Method: In this paper, ten-day average temperature, ten-day average precipitation and ten-day average water vapor pressure are selected as early warning meteorological factors to establish a mathematical model for the occurrence degree of rice blast. Result: The empirical results show that when the model is used to predict the highest degree of rice blast, the accuracy is 98.6%. When the model is used to predict the actual degree of rice blast, the completely accurate proportion was 24.70%, and the deviation within one grade was 70.73%. Conclusion: This shows that the model has good warning accuracy.

1. 引言

2. 气象因子选择

Figure 1. Preliminary selection of meteorological factors

Figure 2. Selection of meteorological factors

Table 1. Observation data near the red line

3. 预警数学模型

3.1. 数学模型和拟合结果

$D={k}_{1}{x}_{1}+{k}_{2}{x}_{2}+{k}_{3}{x}_{3}$ (1)

$D=0.0294{x}_{1}-0.0102{x}_{2}+0.1533{x}_{3}$ (2)

Table 2. Parameters of fitting results

3.2. 预警等级处理

4. 实证分析

Figure 3. Warning results

5. 结论

[1] 俞孕珍, 毛国杰, 魏松红, 等. 辽宁省丹东、盘锦地区稻瘟病流行预测统计模型研究[J]. 沈阳农业大学学报, 1999, 30(1): 55-57.

[2] 张雷, 燕亚菲, 刘志红, 向卫国. 灰色人工神经网络在稻瘟病发生预报中的应用[J]. 中国农学通报, 2010, 26(12): 238-241.

[3] 邱靖, 吴瑞武, 黄雁鸿, 杨毅, 彭莞云. 混沌理论与BP网络融合的稻瘟病预测模型[J]. 农业工程学报, 2010, 26(14): 88-93.

[4] 魏代俊, 曾艳敏, 邹迎春. 基于无偏灰色马尔科夫链的稻瘟病预测研究[J]. 安徽农业科学, 2010, 38(34): 19399-19400+19427.

[5] 宁万光, 谢瑛, 史洪中, 陈利军. 信阳水稻稻瘟病发生规律及基于灰色预测模型的预测预报[J]. 江苏农业科学, 2014, 42(6): 102-104.

[6] 齐龙, 马旭, 梁柏, 张稳成, 傅荣富, 谭永炘. 稻瘟病监测预测方法研究现状及流行风险评估体系构建初探[J]. 中国农学通报, 2011, 27(33): 213-216.

[7] 康晓慧, 陈浩, 张梅. 3种时间序列分析模型在水稻稻瘟病预测中的应用[J]. 西北农林科技大学学报(自然科学版), 2011, 39(6): 173-177.

[8] 李晓菲, 刘振华, 陈涛, 王园媛, 王云月. 基于BP神经网络的稻瘟病预测技术研究[J]. 云南农业大学学报: 自然科学版, 2013, 28(4): 551-560.

[9] 刘坤, 钱永德, 张福军. 蚁群灰色神经网络模型在稻瘟病预测中的应用[J]. 自动化仪表, 2013, 34(2): 30-33.

[10] 江平, 康晓慧. 用逐步回归分析模型预测水稻稻瘟病流行趋势[J]. 广东农业科学, 2014, 41(12): 72-74.

[11] 周丽娜, 于海业, 张蕾, 任顺, 隋媛媛, 于连军. 基于叶绿素荧光光谱分析的稻瘟病害预测模型[J]. 光谱学与光谱分析, 2014, 34(4): 1003-1006.

[12] 刘庭洋, 李烨, 浦仕磊, 李志宇, 李文静, 吴奇, 王云月. 基于BP神经网络的稻瘟病预测预报研究[J]. 西南农业学报, 2017, 30(7): 1546-1553.

[13] 徐敏, 徐经纬, 高苹, 吴洪颜, 罗晓春, 任义方. 基于大尺度因子的江苏稻区稻瘟病气象等级长期预测[J]. 植物保护, 2017, 43(4): 36-41.

[14] Nettleton, D.F., Katsantonis, D., Kalaitzidis, A., Sarafijanovic-Djukic, N., Puigdollers, P. and Confalonieri, R. (2019) Predicting Rice Blast Disease: Machine Learning versus Process-Based Models. BMC Bioinformatics, 20, Article No. 514.
https://doi.org/10.1186/s12859-019-3065-1

[15] Katsantonis, D., Kadoglidou, K., Dramalis, C., et al. (2017) Rice Blast Forecasting Models and Their Practical Value: A Review. Phytopathologia Mediterranea, 56, 187-216.

[16] Kaundal, R., Kapoor, A.S. and Raghava, G.P.S. (2006) Machine Learning Techniques in Disease Forecasting: A Case Study on Rice Blast Prediction. BMC Bioinformatics, 7, Article No. 485.
https://doi.org/10.1186/1471-2105-7-485

[17] Calvero Jr., S.B., Coakley, S.M. and Teng, P.S. (1996) Develop-ment of Empirical Forecasting Models for Rice Blast Based on Weather Factors. Plant Pathology, 45, 667-678.
https://doi.org/10.1046/j.1365-3059.1996.d01-168.x

Top