基于个体优势遗传算法的水稻生育期模型参数优化

doi:10.3864/j.issn.0578-1752.2013.11.005

摘要/Abstract

摘要： 【目的】快速并准确估算作物生育期模型参数。【方法】本文提出了一种新的改进型遗传算法——个体优势遗传算法（individual advantages genetic algorithm，IAGA），并应用于水稻生育期模型参数估算。在遗传算法的基础上引入个体优势算子，并改进了变异算子及种群更新策略。以完全嵌入方式耦合RiceGrow和ORYZA2000水稻生育期模型，实现了模型参数的自动率定。利用汕优63等5个水稻品种在徐州、高要等地的多年田间试验资料，对IAGA算法的有效性进行对比试验。【结果】（1）试验验证结果的RMSE<3.05 d，NRMSE<3.19%，MDA<2.41 d，R2>0.9885，表明利用IAGA获得的模型参数准确性较高。（2）调参的实测数据量大小对调参结果影响不大。由3年数据增加到6年数据，试验拟合结果最大NRMSE值由2.58%增大到3.08%，增加了0.5%。选择隔年并包含全生育期天数最大值与最小值的调参数据，可以获得较准确的模型参数值。（3）IAGA与复合形混合演化算法、遗传模拟退火算法以及标准粒子群算法相比，可获得更准确的模型参数值。【结论】IAGA算法可以实现水稻生育期模型参数的自动率定，为作物生长模型参数的快速准确估算提供了一种有效新方法。

关键词: 水稻 , 生育期模型 , 参数优化 , 遗传算法 , RiceGrow , ORYZA2000

Abstract: 【Objective】 Fast and accurate estimation of crop growth model parameters is the basis of the crop system simulation.【Method】In this paper, a newly improved genetic algorithm, named individual advantage genetic algorithm (IAGA), is proposed and applied to the field of the parameters evaluation of the rice development stages model. Firstly, the individual advantage operator was introduced into the genetic algorithm, thus improved the mutation operator and the update strategy of population. Secondly, two rice development stages models, RiceGrow and ORYZA2000, were coupled with IAGA in a way of total embedment, and realized automatic estimation of the parameters in the models. At last, a series of comparative experiments were carried out to verify the effectiveness of IAGA with multi-year field trial data of Shanyou63, and other four rice varieties in Xuzhou, Gaoyao, etc.【Result】The experimental verification results which cover RMSE＜3.05 d, NRMSE＜3.19%, MDA＜2.41 d, R2＞0.9877, indicated that the accuracy of the model parameters obtained by IAGA was pretty high. The amount of data used for the parameters estimation had little effect on the results. The maximum NRMSE of the fitting results increased from 2.58% to 3.08% when the amount of data used for the parameters estimation from three years to six years was changed. More accurate model parameters were obtained when we select the data of every other year, including the maximum and minimum value of the whole growth period. Compared with the shuffled complex evolution algorithm, genetic simulated annealing algorithm and standard particle swarm algorithm, IAGA could obtain more accurate model parameters.【Conclusion】The IAGA can achieve automatic determination of rice development stages model parameters, therefore it provides an effective and new method for estimating parameters for crop growth model quickly and accurately.

Key words: rice , development stages model , parameters optimization , genetic algorithm , RiceGrow , ORYZA2000

庄嘉祥, 姜海燕, 刘蕾蕾, 王芳芳, 汤亮, 朱艳, 曹卫星. 基于个体优势遗传算法的水稻生育期模型参数优化[J]. 中国农业科学, 2013, 46(11): 2220-2231.

ZHUANG Jia-Xiang, JIANG Hai-Yan, LIU Lei-Lei, WANG Fang-Fang, TANG Liang, ZHU Yan, CAO Wei-Xing. Parameters Optimization of Rice Development Stages Model Based on Individual Advantages Genetic Algorithm[J]. Scientia Agricultura Sinica, 2013, 46(11): 2220-2231.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2013.11.005

https://www.chinaagrisci.com/CN/Y2013/V46/I11/2220

参考文献

[1]曹卫星, 朱艳, 田永超, 姚霞, 刘小军. 数字农作技术研究的若干研究进展与发展方向. 中国农业科学, 2006, 39(2): 281-288.

Cao W X, Zhu Y, Tian Y C, Yao X, Liu X J. Research progress and prospect of digital farming techniques. Scientia Agricultura Sinica, 2006, 39(2): 281-288. (in Chinese)

[2]曹宏鑫, 赵锁劳, 葛道阔, 刘永霞, 刘岩, 孙金英, 岳延滨, 张智优, 陈煜利. 作物模型发展探讨. 中国农业科学, 2011, 44(17): 3520-3528.

Cao H X, Zhao S L, Ge D K, Liu Y X, LIU Y, Sun J Y, Yue Y B, Zhang Z Y, Chen Y L. Discussion on development of crop models. Scientia Agricultura Sinica, 2011, 44(17):3520-3528. (in Chinese)

[3]房全孝. 根系水质模型中土壤与作物参数优化及其不确定性评价. 农业工程学报, 2012, 28(10): 118-123.

Fang Q X. Optimizing and uncertainty evaluation of soil and crop parameters in root zone water qualitymodel. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(10): 118-123. ( in Chinese)

[4]潘登, 任理. 分布式水文模型在徒骇马颊河流域灌溉管理中的应用Ⅰ参数率定和模拟验证. 中国农业科学, 2012, 45(3): 471-479.

Pan D, Ren L. Application of distributed hydrological model in irrigation management of Tuhai-Majia river basin I parameter calibration and validation. Scientia Agricultura Sinica, 2012, 45(3): 471-479. (in Chinese)

[5]Pabico J P, Hoogenboom G, Mcclendon R W. Determination of cultivar coef?cients of crop models using a genetic algorithm: a conceptual framework. American Society of Agricultural Engineers, 1999, 42(1): 223-232.

[6]Calmon M A, Jones J W, Shinde D, Specht J E. Estimating parameters for soil water balance models using adaptive simulated annealing. Applied Engineering in Agriculture, 1999, 15(6): 703-713.

[7]Ferreyra R A. A faster algorithm for crop model parameterization by inverse modeling: simulated annealing with data reuse. Transactions of the ASABE, 2004, 47(5): 1793-1801.

[8]朱元励, 朱艳, 黄彦, 姚霞, 刘蕾蕾, 曹卫星, 田永超. 应用粒子群算法的遥感信息与水稻生长模型同化技术. 遥感学报, 2010, 14(6): 1226-1240.

Zhu Y L, Zhu Y, Huang Y, Yao X, Liu L L, Cao W X, Tian Y C. Assimilation technique of remote sensing information and rice growth model based on particle swarm optimization. Journal of Remote Sensing, 2010, 14(6): 1226-1240. ( in Chinese)

[9]Dai C N, Yao M, Xie Z J, Chen C H, Liu J G. Parameter optimization for growth model of greenhouse crop using genetic algorithms. Applied Soft Computing, 2009, 9: 13-19.

[10]刘铁梅, 王燕, 邹薇, 孙东发, 汤亮, 曹卫星. 大麦叶面积指数模拟模型. 应用生态学报, 2010, 21(1): 121-128.

Liu T M, Wang Y, Zou W, Sun D F, Tang L, Cao W X. Simulation model of barley leaf area index. Chinese Journal of Applied Ecology, 2010, 21(1): 121-128. (in Chinese)

[11]任建强, 陈仲新, 唐华俊, 周清波, 秦军. 基于遥感信息与作物生长模型的区域作物单产模拟. 农业工程学报, 2011, 27(8): 257-264.

Ren J Q, Chen Z X, Tang H J, Zhou Q B, Qin J. Regional crop yield simulation based on crop growth model and remote sensing data. Transactions of the Chinese Society of Agricultural Engineering, 2011, 27(8): 257-264. (in Chinese)

[12]靳华安, 王锦地, 柏延臣, 陈桂芬, 薛华柱. 基于作物生长模型和遥感数据同化的区域玉米产量估算. 农业工程学报, 2012, 28(6): 162-173.

Jin H A, Wang B D, Bo Y C, Chen G F, Xue H Z. Estimation on regional maize yield based on assimilation of remote sensing data and crop growth model. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(6): 162-173. (in Chinese)

[13]Goldberg D E, Holland J H. Genetic algorithms and machine learning. Machine Learning, 1988, 3(2/3):95-99.

[14]Kirkpatrick S, Gelatt C D, Vecchi M P. Optimization by simulated annealing. Science, 1983, 220(4598):671-680.

[15]Kennedy J, Eberhart R C. A discrete binary version of the particle swarm algorithm//Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Orlando, Florida, USA, 1997: 4104-4108.

[16]Yin X Y. Quantifying the effects of temperature and photoperiod on phenological development to flowering in rice[D]. Wageningen: Wageningen Agricultural University, 1996.

[17]Tang L, Zhu Y, Hannaway D, Meng Y L, Liu L L, Chen L, Cao W X. RiceGrow: A rice growth and productivity model. NJAS -Wageningen Journal of Life Sciences, 2009, 57(1): 83-92.

[18]孟亚利, 曹卫星, 周治国, 柳新伟. 基于生长过程的水稻阶段发育与物候期模拟模型. 中国农业科学, 2003, 36(11): 1362-1367.

Meng Y L, Cao W X, Zhou Z G, Liu X W. A process-based model for simulating phasic development and phenology in rice. Scientia Agricultura Sinica, 2003, 36(11): 1362-1367. (in Chinese)

[19]Bouman B A M, Kropff M J, Tuong T P, Wopereis M C S, ten Berge H F M, van Laar H H. ORYZA2000: Modeling lowland rice. Los Banos: IRRI and Wageningen: Wageningen University and Research Centre, 2001.

[20]刘全, 王晓燕, 傅启明, 张永刚, 章晓芳. 双精英协同进化遗传算法. 软件学报, 2012, 23(4): 765-775.

Liu Q, Wang X Y, Fu Q M, Zhang Y G, Zhang X F. Double elite coevolutionary genetic algorithm. Journal of Software, 2012, 23(4): 765-775. (in Chinese)

[21]魏波, 李元香, 徐星, 申鼎才. 基于稳定策略的粒子群优化算法. 计算机科学, 2011, 38(12): 221-223.

Wei B, Li Y X, Xu X, Shen D C. Particle swarm optimization algorithm based on stable strategy. Computer Science, 2011, 38(12): 221-223. (in Chinese)

[22]王文义, 秦广军, 王若雨. 基于粒子群算法的遗传算法研究. 计算机科学, 2007, 34(8):145-147.

Wang W Y, Qin G J, Wang R S. Research on genetic algorithm based on particle swarm algorithm. Computer Science, 2007, 34(8): 145-147. (in Chinese)

[23]朱玉洁, 冯利平, 易鹏, 杨晓光, 胡跃高. 紫花苜蓿光合生产与干物质积累模拟模型研究. 作物学报, 2007, 33(10): 1682-1687.

Zhu Y J, Feng L P, Yi P, Yang X G, Hu Y G. A dynamic model simulating photosynthetic production and dry matter accumulation for alfalfa. Acta Agronomica Sinica, 2007, 33(10): 1682-1687. (in Chinese)

[24]曹卫星, 朱艳, 汤亮, 荆奇, 田永超, 姚霞, 刘小军. 数字农作技术. 北京: 科学出版社, 2008.

Cao W X, Zhu Y, Tang L, Jing Q, Tian Y C, Yao X, Liu X J. Digital Farming Technology. Beijing: Science Press, 2008.

[25]Duan Q Y, Gupta V K, Sorooshian S. Shuffled complex evolution approach for effective and efficient global minimization. Journal of Optimization Theory and Application, 1993, 76(3): 501-521.

[26]石春林, 冯慧慧, 金之庆, 王华. 水稻发育期模型的比较. 中国水稻科学, 2010, 24(3): 303-308.

Shi C L, Feng H H, Jin Z Q, Wang H. Comparison of phasic development models in rice. Chinese Journal of Rice Science, 2010, 24(3): 303-308. (in Chinese)