陕西省烤烟智能施肥推荐模型的研究
|
摘要
烤烟作为一种重要的经济作物,施肥对烟叶的产量、产值和品质都起着决定性的作用。传统施肥模型往往建立在专家经验和大量田间试验的基础上,存在主观性强、试验周期长和通用性差等缺陷。为更好地指导烤烟精准施肥,解决肥料配制中的技术难题,本文在综合评价烤烟土壤肥力的基础上,分别建立了基于BP网络和最小二乘支持向量机的智能施肥推荐模型,设计开发了BP网络和最小二乘支持向量机两种施肥推荐平台,并结合GIS技术用于指导烤烟施肥。
本文的主要研究内容如下:
(1)烤烟土壤肥力适宜性评价研究。比较现有的土壤肥力评价方法,在专家指导下建立评价因素集,选用灰色关联分析和AHP-模糊综合评价两种方法,分别对研究区的烤烟土壤肥力进行评价。依据各地烤烟的历史产量水平,对两种方法的评价结果进行验证。结果表明,AHP-模糊综合评价法相比灰色关联分析法,评价结果更准确,评价过程更符合实际。
(2)建立基于BP网络平台的烤烟施肥推荐模型。针对传统施肥模型的不足,采用附加动量法和自适应学习速率法改进BP算法,构建基于BP网络平台的施肥推荐模型。综合考虑土壤养分差异对施肥量的影响,以土壤养分含量和施肥方案作为输入,以评价目标,如烤烟产量、产值或品质作为输出,BP网络各层神经元数由用户动态设定。实验结果表明,该模型对产量预测的平均准确率为88.55%,施肥推荐结果与实际一致。
(3)建立基于最小二乘支持向量机的烤烟施肥推荐模型。分析最小二乘支持向量机模型的优点和适用性,研究其基本原理,构建基于最小二乘支持向量机的智能施肥推荐模型。总结常见的核函数形式,选择径向基函数作为施肥推荐模型的核函数;对于模型中的两个待定参数,采用粒子群优化算法来确定。实验结果表明,基于最小二乘支持向量机的施肥推荐模型对产量的预测准确率高于BP网络模型,且特别适用于样本数量有限的情况。
(4)基于GIS的烤烟智能施肥推荐平台的开发。将构建的智能模型用于烤烟施肥推荐,设计开发了BP网络和最小二乘支持向量机两种施肥推荐平台。在GIS支持下,建立空间数据库,关联土壤肥力评价结果,绘制了烤烟土壤肥力适宜性分布图;将其与施肥推荐方案集成,发布到Web页面。测试结果表明,所建平台能有效地实现烤烟智能施肥推荐,具有较高的通用性、直观性和实用价值。
Tobacco is an important economic crop. Fertilization plays a decisive role on tobacco yield, output value and quality. Conventional fertilization models are often constructed on the basis of expert experience and plenty of experimentation. Most of them have many faults, such as strong subjectivity, long experimental period, weak generality, etc. In order to improve the ability of instructing tobacco fertilization accurately and solve the problems in fertilizer preparation. Two intelligent fertilization models are constructed after comprehensive evaluation of soil fertility for tobacco. One is based on Back- Propagation neural network, and the other is based on Least Squares Support Vector Machine. Accordingly, two intelligent fertilization recommended platform are developed.Finally, GIS is applied to instruct tobacco fertilization.
The main content of this research include:
(1) Study on comprehensive evaluation of soil fertility for tobacco plantation based on GIS. By analyzing and comparing staple methods on fertility evaluation of soil, the set of evaluation factors is built under expert direction, and two methods are selected to evaluate soil fertility of researchful areas, including Gray Correlation Analysis and AHP- Fuzzy Comprehensive Evaluation. According to the historical yield, the evaluation results of two methods are verified. Experimental results show that the accuracy of AHP- Fuzzy Comprehensive Evaluation is higher than Gray Correlation Analysis, and the former is more tally with the practice.
(2) Construction of tobacco fertilization recommendation model based on BP neural network. In view of the faults of conventional fertilization models, normal BP algorithm is improved using methods of the affixation momentum and the self-adaptation learning rate. A fertilization recommendation model is constructed based on BP neural network platform. Take most factors into consideration, some soil nutrient content and fertilization plans are viewed as input vector, and evaluation target (yield or output value or quality) is viewed as output vector. The number of neuron nodes in every layer of BP neural network is determined by user dynamically. Experimental results show that the mean prediction accuracy of this model is 88.55%, and the recommendation results coincide with the practice.
(3) Construction of tobacco fertilization recommendation model based on Least Squares Support Vector Machine(LS-SVM). By analyzing the merits and applicability of LS-SVM and studying on LS-SVM fundamental principle, an intelligent fertilization recommendation model is constructed based on LS-SVM. Comparison with familiar kernel function forms, Radial Basis Function is selected as the kernel function of this model. In this paper, Particle Swarm Optimization algorithm is used to optimize model parameters. Experimental results show that the mean predicting accuracy of the LS-SVM model is higher than BP neural network model. At the same time, the LS-SVM model is especially suitable for limited number of samples.
(4) Development of intelligent fertilization recommendation platform for tobacco. We apply the two models constructed in this paper into recommend fertilization for tobacco and develop two fertilization platforms. We construct a spatial database, associating with inner properties and draw a fertility distribution map for tobacco plantation in GIS environment. The results of fertilization recommendation are integrated with the distribution map and released to web page. Testing results show that both platforms can recommend fertilization for tobacco effectively and has pretty good commonality and practical value.
本文的主要研究内容如下:
(1)烤烟土壤肥力适宜性评价研究。比较现有的土壤肥力评价方法,在专家指导下建立评价因素集,选用灰色关联分析和AHP-模糊综合评价两种方法,分别对研究区的烤烟土壤肥力进行评价。依据各地烤烟的历史产量水平,对两种方法的评价结果进行验证。结果表明,AHP-模糊综合评价法相比灰色关联分析法,评价结果更准确,评价过程更符合实际。
(2)建立基于BP网络平台的烤烟施肥推荐模型。针对传统施肥模型的不足,采用附加动量法和自适应学习速率法改进BP算法,构建基于BP网络平台的施肥推荐模型。综合考虑土壤养分差异对施肥量的影响,以土壤养分含量和施肥方案作为输入,以评价目标,如烤烟产量、产值或品质作为输出,BP网络各层神经元数由用户动态设定。实验结果表明,该模型对产量预测的平均准确率为88.55%,施肥推荐结果与实际一致。
(3)建立基于最小二乘支持向量机的烤烟施肥推荐模型。分析最小二乘支持向量机模型的优点和适用性,研究其基本原理,构建基于最小二乘支持向量机的智能施肥推荐模型。总结常见的核函数形式,选择径向基函数作为施肥推荐模型的核函数;对于模型中的两个待定参数,采用粒子群优化算法来确定。实验结果表明,基于最小二乘支持向量机的施肥推荐模型对产量的预测准确率高于BP网络模型,且特别适用于样本数量有限的情况。
(4)基于GIS的烤烟智能施肥推荐平台的开发。将构建的智能模型用于烤烟施肥推荐,设计开发了BP网络和最小二乘支持向量机两种施肥推荐平台。在GIS支持下,建立空间数据库,关联土壤肥力评价结果,绘制了烤烟土壤肥力适宜性分布图;将其与施肥推荐方案集成,发布到Web页面。测试结果表明,所建平台能有效地实现烤烟智能施肥推荐,具有较高的通用性、直观性和实用价值。
Tobacco is an important economic crop. Fertilization plays a decisive role on tobacco yield, output value and quality. Conventional fertilization models are often constructed on the basis of expert experience and plenty of experimentation. Most of them have many faults, such as strong subjectivity, long experimental period, weak generality, etc. In order to improve the ability of instructing tobacco fertilization accurately and solve the problems in fertilizer preparation. Two intelligent fertilization models are constructed after comprehensive evaluation of soil fertility for tobacco. One is based on Back- Propagation neural network, and the other is based on Least Squares Support Vector Machine. Accordingly, two intelligent fertilization recommended platform are developed.Finally, GIS is applied to instruct tobacco fertilization.
The main content of this research include:
(1) Study on comprehensive evaluation of soil fertility for tobacco plantation based on GIS. By analyzing and comparing staple methods on fertility evaluation of soil, the set of evaluation factors is built under expert direction, and two methods are selected to evaluate soil fertility of researchful areas, including Gray Correlation Analysis and AHP- Fuzzy Comprehensive Evaluation. According to the historical yield, the evaluation results of two methods are verified. Experimental results show that the accuracy of AHP- Fuzzy Comprehensive Evaluation is higher than Gray Correlation Analysis, and the former is more tally with the practice.
(2) Construction of tobacco fertilization recommendation model based on BP neural network. In view of the faults of conventional fertilization models, normal BP algorithm is improved using methods of the affixation momentum and the self-adaptation learning rate. A fertilization recommendation model is constructed based on BP neural network platform. Take most factors into consideration, some soil nutrient content and fertilization plans are viewed as input vector, and evaluation target (yield or output value or quality) is viewed as output vector. The number of neuron nodes in every layer of BP neural network is determined by user dynamically. Experimental results show that the mean prediction accuracy of this model is 88.55%, and the recommendation results coincide with the practice.
(3) Construction of tobacco fertilization recommendation model based on Least Squares Support Vector Machine(LS-SVM). By analyzing the merits and applicability of LS-SVM and studying on LS-SVM fundamental principle, an intelligent fertilization recommendation model is constructed based on LS-SVM. Comparison with familiar kernel function forms, Radial Basis Function is selected as the kernel function of this model. In this paper, Particle Swarm Optimization algorithm is used to optimize model parameters. Experimental results show that the mean predicting accuracy of the LS-SVM model is higher than BP neural network model. At the same time, the LS-SVM model is especially suitable for limited number of samples.
(4) Development of intelligent fertilization recommendation platform for tobacco. We apply the two models constructed in this paper into recommend fertilization for tobacco and develop two fertilization platforms. We construct a spatial database, associating with inner properties and draw a fertility distribution map for tobacco plantation in GIS environment. The results of fertilization recommendation are integrated with the distribution map and released to web page. Testing results show that both platforms can recommend fertilization for tobacco effectively and has pretty good commonality and practical value.
引文
[1]吕晓男.土壤肥力综合评价和作物施肥咨询系统研制与应用[D].浙江:浙江大学,2000.
[2]房俊杰,戚国强,王立舒等.黑龙江省大豆施肥专家系统[J].农机化研究,2006,11(11):103-105.
[3]姚玉霞,王越,赵月玲等.玉米精准施肥专家系统在玉米生产中的应用[J].农业网络信息,2007,(9):24-27.
[4]孙治贵,黎贞发,李杰等.基于组件式GIS技术的水稻生产管理信息系统开发研究[J].农业工程学报,2004,20(3):137-140.
[5]廖桂平,官春云,陈社员.基于Web的油菜生产专家系统的研究与应用[J].农业系统科学与综合研究,2005,21(1):8-12.
[6]李建军,沈佐锐,贺超兴等.日光温室番茄长季节生产专家系统的研制[J].农业工程学报,2003,19(3):267-268.
[7]谭宗琨,欧钊荣,陈恩波.香蕉智能专家系统中的实时决策[J].计算机工程,2007,33(19):262-264.
[8]田东,张小栓,李道亮.网络化淡水虾养殖专家系统的实现[J].农机化研究,2004,11(6):105-107.
[9]刘建利,李志宏,陈江华等. GIS应用于植烟土壤肥力分区及施肥区划的研究[J].中国烟草学报,2004,10(3):19-24.
[10]刘吉振,张天平,徐卫红.国内优质烤烟施肥研究进展[J].广西农业科学,2005,36(6):539-543.
[11]韩锦锋,范艺宽,王根恒等.不同栽培方式对烤烟根系发育的影响[J].河南农业科学,1996,(11):12-13.
[12] Cowell, J. D. Soil fertilizer relations of National Soil Fertility Project[J]. CRISO Australia, 1979, Vol.2.
[13] Cowell, J.D. Development and evaluation of general or transfer models of relationships between wheat yield and fertilizer rate in Southern Australia[J]. Soil Res. 1984, 22: 191-205.
[14] Cowell, J.D. Fertilizer requirements [J]. In soil: An Australian Viewpoint, Division of soils, CSIRO, 1983, 795-815.
[15] Cowell, J.D. Development of Gereral Soil Fertility Models for Variable Regions[C]. In Transaction of the 13 Congress of the international Society of Soil Science, Extended information Summaries, 1986, Part 2, 708-709.
[16] Harsh, S. B. Nutrient management system for agricultural producers[C]. In Computers in agricultural extension programs: proceeding of the 4th International Conference, Orlands, Florida. ASAE. Publication, 1992,589-594.
[17] Janise, B. H., et al. A system of quantitative evaluation of the fertility of tropical soils[J]. Geoderma, 1990, Vol.46(4): 299-318.
[18] Janssen, B. H., et al. A system for quantitative evaluation of soil fertility and the response to fertilizer[J]. Land qualities in space and time, 1989: 185-188.
[19] Johnson, G. V., D.L. Nofziger. NPKSPLUS: a computer program to examine agronomic and economic value of alternative fertilizer rates[J]. Journal-of-Production-Agriculture, 1992, Vol.(5): 4,415-420.
[20] Sinclair,A.H., A.G, Reaves, K.W.M, Brown. Design of a Scottish soil fertility information system[J]. Analytical-Proceedings, 1988,Vol.25: (4),120-122.
[21] Thomson, S. J. et al. Nutrient management software for Virginia farmers[C]. In Computers in agricultural extension programs: proceedings of the 4th International Conference. Orlando, Florida. ASAE, 1992, 584-588.
[22] Lemmon H. Comax: An expert system for cotton crop management [J]. Science, 1986, 233: 29-33.
[23] Howard, D., P. E. Hoskinson, M.Smith. Evaluation of the GOSSYM-COMAX cotton growth simulation model/expert management system in Tennessee[M]. 1994.
[24] Kruger, G. A., R. E. Karamanos. Fertility analysis and recommendation manager, Commum[J]. Soil Sci, Plant anal, 1994, 25(7&8): 955-965.
[25] Mc Callister, R., K. B. Shelley, P. Thum. The use of GIS for nitrogen management planning in Wisconsin[J]. Progress-in-rural-policy-and-planning, 1992, Vol.2(2): 5-16.
[26] Mc Cauley .J.D. Simulating spatial fertilizer applications in cotton production[C]. In Computers in agricultural extension programs. Proceedings of the 4th intermational conference, Orlando, Florida. ASAE Publication,1992: 159-164;
[27]李小平,胡文林.土壤肥料试验和农业统计程序包的设计、研制及其应用[J].计算机农业应用,1991,(1):30-36.
[28]张全德,胡秉民.农业试验统计模型和BASIC程序[M].浙江:科学技术出版社,1985.
[29]熊范纶,郭霖,吴文荣等.砂姜黑土小麦施肥计算机专家咨询系统[J].信息与控制,1987,16(2):7-11.
[30]孙波,严浩,施建平等.基于组件式GIS的施肥专家决策支持系统开发和应用[J].农业工程学报,2006,22(4):75-79.
[31]王海江,吕新.基于GIS技术的新疆棉花施肥专家系统[J].农业工程学报,2006,22(10):167-170.
[32]徐剑波,胡月明,李华兴等.优质稻高产优化施肥与栽培配套技术专家系统的研制[J].科技通报,2003,19(2):98-101.
[33]吕新,魏亦农,李少昆.基于GIS的土壤肥力信息管理及棉花施肥推荐支持决策系统研究[J].中国农业科学,2002,35(7):883-887.
[34]朱红春,张蕾,刘海英.基于GIS的猕猴桃土壤养分评价与施肥建议模型研究[J].农业工程学报,2007,23(6):194-198.
[35]陈赞章.基于WebGIS的橡胶精准施肥信息系统的设计与实现[D].北京:北京邮电大学,2007.
[36]聂艳,周勇,田有国等.基于3S的土壤肥料专家系统研究[J].土壤,2003,35(4):339-343.
[37]张蕾.基于GIS的果树施肥信息系统的研制与初步应用——以周至县猕猴桃为例[D].西安:西北大学,2005.
[38]周保平.黑龙江省水稻生态平衡施肥决策支持系统总体设计及部分模块功能实现[D].哈尔滨:东北农业大学,2003.
[39]赵东.测土施肥专家系统设计与实现[D].长春:长春理工大学,2008.
[40]程功,刘济,李跃峰等.烤烟配方施肥专家系统的研究与应用[J].河南农业大学学报,1997,31(2):166-170.
[41]熊玉唐,范勇,李显荣.麻江烤烟专家系统的开发与应用[J].贵州农业科学,2004,32(5):48-50.
[42]王军艳,张凤荣,王茹等.应用指数和法对潮土农田土壤肥力变化的评价研究[J].农村生态环境.2001,17(3):13-16,20.
[43]郑立臣,宇万太,马强等.农田土壤肥力综合评价研究进展[J].生态学杂志,2004,23(5):156-161.
[44]谢延敏.于Kriging模型和灰色关联分析的板料成形工艺稳健优化设计研究[D].上海:上海交通大学,2007.
[45] Burrough P A. Fuzzy mathematical methods for soil survey and land evaluation[J]. Journal of Soil Science,1989, 40: 477-490.
[46]曹志洪.解释土壤质量演变规律,确保土壤资源持续利用[J].世界科技研究与发展, 2001,23(3):28-32.
[47]熊毅.中国土壤[M].北京:科学出版社,1978.
[48]孙波,张桃林,赵其国.我国东南丘陵山区土壤肥力的综合评价[J].土壤学报,1995,32(4):362-369.
[49]陈海生,叶协峰,刘国顺等.基于GIS的河南省烤烟土壤肥力适宜性研究[J].土壤通报,2007,38(6):1081-1085.
[50]王桂芝.基于GIS的三亚市热作土地适宜性评价模型的建立[J].测绘与工程. 1997(2):23-28.
[51]周勇,张海涛,汪善勤等.江汉平原后湖地区土壤肥力综合评价方法及其应用[J].水土保持学报, 2001,15(4):70-74.
[52]左天觉,朱尊权译.烟草的生产、生理和生物化学[M].上海:远东出版社,1993,199-222,272-273.
[53] D. Layten Davis,Mark T.Nielsen.编.烟草——生产,化学和技术[M].北京:化学工业出版社,2003,76-78.
[54]陈义强.氮磷钾肥对烤烟内在品质的影响及其施肥模型[D].郑州:河南农业大学,2008.
[55]曹志洪.优质烤烟生产的土壤与施肥[M].江苏:科学技术出版社,1991,21-24,29-90, 208-235.
[56] Marchand M, Etourneaud F, Bourrie B.不同钾肥品种对烟草产量和化学成分的影响研究[J].中国烟草科学,1999,18(2): 6-11.
[57] Leggett, J. E. et al. Potassium and magnesium nutrition effects on yield and chemical composition of burley tobacoo leaves and smoke. Can J. Plant Sci., 1977 ,57: 159-166.
[58]广东省土壤普查办公室.广东土壤[M].北京:科学出版社,1993:412-499.
[59]胡国松,郑伟,王震东等.烟草营养原理[M].北京:科学出版社,2000:45-252.
[60]唐莉娜,熊德中.土壤酸度的调节对烤烟根系生长与烟叶化学成份含量的影响[J].中国生态农业学报,2002,10(4):65-67.
[61]陈建军,陈建勋,吕永华等.根系pH值对烟草无机营养的影响[J].植物生理学通讯,1996, 32(5):341-344.
[62]邓聚龙.灰色系统理论教程[M].武汉:华中理工大学出版社,1990.
[63]谢松云.基于灰色系统理论的目标识别研究[D].西安:西北工业大学,2001.
[64]周晓洁.基于模糊综合评价法的船舶热源系统优选研究[D].上海:上海交通大学,2008.
[65] Saaty T L.The analysis hierarchy process: planning, priority setting, resource allocation [M].New York:McGraw Hill,1980.
[66] SIFOLA M I, POSTIGLINE L. The effect of increasing NaCl in irrigation water on growth , gas exchange and yield of tobacco Burley type[J]. Field Crops Research, 2002, (74): 81-91.
[67]何振立,周启星,谢正苗.污染及有益元素的土壤化学平衡[M].北京:中国环境科学出版社,1998,75-79.
[68]宋承鉴.广西植烟区土壤特性分析[J].中国烟草,1994,(2).
[69]吕英华,秦双.测土与施肥[M].北京:中国农业出版社,2002.
[70]陈研,胡克林,冯凌等.基于土壤—作物系统模型模拟的冬小麦田间水氮优化管理[J].农业工程学报,2007,23(6):55-60.
[71]马新明,张娟娟,席磊等.基于叶面积指数(LAI)的小麦变量施氮模型研究[J].农业工程学报,2008,24(2):22-26.
[72]刘军,周连仁,梁桂荣等.白浆土生态平衡施肥参数的研究[J].东北农业大学学报,2007,38(2):215-220.
[73]陈家金,徐宗焕,林晶等.基于RCSODS的东南沿海水稻施肥量决策[J].中国农业气象,2008,29(1):71-74.
[74]席运官,钦佩,丁公辉等.基于RCSODS的有机水稻栽培施肥与效果分析[J].上海农业学报,2007,23(2):28-33.
[75]马新明,张娟娟,刘合兵等.基于氮素胁迫的WCSODS模型订正与检验[J].中国农业科学,2008, 41(2):391-396.
[76] David Makowski, Daniel Wallach, Jean-Marc Meynard. Models of yield, grain protein, and residual mineral nitrogen responses to applied nitrogen for winter wheat [J]. Agron J, 1999, 91: 377-385.
[77] Terry L, Kastens, John P, et al. Yield models implied by traditional fertilizer recommendations and a framework for including nontraditional information [J]. Soil Sci. Soc.Am.J., 2003,67: 351-364.
[78]柯庆明,林文雄,黄珍发等.小白菜平衡施肥数学模型模拟研究[J].中国生态农业学报,2005,13(1):119-121.
[79]吴才聪.精确农业变量施肥决策研究与技术经济分析[D].吉林:吉林大学,2003.
[80]张立明.人工神经网络的模型及其应用[M].上海:复旦大学出版社,1993.
[81]李孝安,张晓溃.神经网络与神经元计算导论[M].西安:西北工业大学出版社,1994.
[82] Hecht-Nielsen R. Theory of the back propagation neural network[J]. Proc.OFIJCNN,1989,1:593-603.
[83] Hecht-Nielsen R. Computer propagation networks[J]. Applied Potics, 1987, 26: 4979-4984.
[84]从爽.面向MATLAB工具箱的神经网络理论与应用[M].合肥:中国科学技术大学出版社,1998.
[85]李晓峰,刘光中.人工神经网络BP算法的改进及其应用[J].四川大学学报(工程科学版),2000,32(2):105-109.
[86]胥斌.奶牛疾病诊断遗传神经网络模型研究[D].重庆:重庆大学,2004.
[87]王合山.基于遗传算法的模糊神经网络及其在中医类风湿性关节炎诊断中的应用研究[D].云南:昆明理工大学,2004.
[88]王永骥,徐健.神经元网络控制[M].北京:机械工业出版社,1998.
[89]叶进,邢传鼎.基于人工神经网络的病症诊断原型系统[J].东华大学学报(自然科学版).2004,29(4):43-47.
[90]叶世伟,史忠植.神经网络原理[M].北京:机械工业出版社,2004.
[91]杨立成.基于最小二乘支持向量机的短期电力负荷预测方法研究[D].南宁:广西大学,2008.
[92]耿艳.基于最小二乘支持向量机的短期负荷预测方法及应用研究[D].济南:山东大学,2008.
[93]李晓东,席升阳,潘立.基于最小二乘支持向量机的中国粮食产量预测模型研究[J].水土保持研究,2007,14(6):322-324.
[94]辛治运,顾明.基于最小二乘支持向量机的复杂金融时间学列预测[J].清华大学学报(自然科学版),2008,48(7):1147-1149.
[95]徐立中.基于支持向量机的水质评价和预测研究[D].南京:河海大学,2006.
[96]陶少辉.最小二乘支持向量机的改进及其在化学化工中的应用[D].浙江:浙江大学,2006.
[97]姜静清.最小二乘支持向量机算法及应用研究[D].吉林:吉林大学,2007.
[98]李悦卿.基于神经网络和最小二乘支持向量机的软测量技术应用研究[D].青岛:青岛科技大学,2007.
[99] V.N. Vapnik, E. Levin, C.Y. Le. Measuring the VC-dimension of a learning machine[J]. Neural Computation, 1994, 6: 851-876.
[100]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42
[101] Suykens J A K, Vandewalle,J. Least squares support vector machine classifiers[J]. Neural processing letters, 1999, 9 : 293-300.
[102] Suykens J A K, Van Gestel T, De Brabanter J, et al. Least squares support vector machines[M], Singapore: World Scientific Publishing Co., Pte, Ltd., 2002.
[103] Zhao Ying,Kwoh Chee Keong. Fast leave-one-out evaluation and improvement on inference for LS-SVM[J], ICPR’04, 2004, 3: 494-497.
[104]占勇.基于支持向量机的电能质量分析和复合建模研究[D].上海:上海交通大学,2007.
[105]王海龙,周辉仁,宗蕴等. LS-SVM的一种参数优选方法及混沌时间序列预测[J].统计与决策,2009,(1):22-24.
[106] Kennedy J., Eberhart R. Particle swarm optimization[C]. IEEE International Conference on Neural Networks,1995. Proceedings,Vol.4, Nov.1 Dec.1995:1942-1948.
[107] Shi Y H,Eberhart R C. Parameter Selection in Particle Swarm Optimization[C]. Annual Conference on Evolutionary Programming. San Diego:1998.
[108] Kennedy, J., Eberthart, R.C. A discrete binary version of the particle swarm algorithm[C]. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 1997, Vol.5: 4104-4108.
[109]马文涛.参数优化LSSVM的巷道围岩松动圈预测研究[J].岩土力学,2007,28(增刊):460-464.
[110]张红梅,卫志农,龚灯才等.基于粒子群支持向量机的短期电力负荷预测[J]. 2006,34(3):28-31.
[111]林智杨,范明翔,陈锦辉.深入浅出Java Swing程序设计[M].北京:中国铁道出版社,2006.
[112] JFreeChart教程[EB/OL]. http://www.360doc.com/showWeb/0/0/217411.aspx,2008-10-5.
[2]房俊杰,戚国强,王立舒等.黑龙江省大豆施肥专家系统[J].农机化研究,2006,11(11):103-105.
[3]姚玉霞,王越,赵月玲等.玉米精准施肥专家系统在玉米生产中的应用[J].农业网络信息,2007,(9):24-27.
[4]孙治贵,黎贞发,李杰等.基于组件式GIS技术的水稻生产管理信息系统开发研究[J].农业工程学报,2004,20(3):137-140.
[5]廖桂平,官春云,陈社员.基于Web的油菜生产专家系统的研究与应用[J].农业系统科学与综合研究,2005,21(1):8-12.
[6]李建军,沈佐锐,贺超兴等.日光温室番茄长季节生产专家系统的研制[J].农业工程学报,2003,19(3):267-268.
[7]谭宗琨,欧钊荣,陈恩波.香蕉智能专家系统中的实时决策[J].计算机工程,2007,33(19):262-264.
[8]田东,张小栓,李道亮.网络化淡水虾养殖专家系统的实现[J].农机化研究,2004,11(6):105-107.
[9]刘建利,李志宏,陈江华等. GIS应用于植烟土壤肥力分区及施肥区划的研究[J].中国烟草学报,2004,10(3):19-24.
[10]刘吉振,张天平,徐卫红.国内优质烤烟施肥研究进展[J].广西农业科学,2005,36(6):539-543.
[11]韩锦锋,范艺宽,王根恒等.不同栽培方式对烤烟根系发育的影响[J].河南农业科学,1996,(11):12-13.
[12] Cowell, J. D. Soil fertilizer relations of National Soil Fertility Project[J]. CRISO Australia, 1979, Vol.2.
[13] Cowell, J.D. Development and evaluation of general or transfer models of relationships between wheat yield and fertilizer rate in Southern Australia[J]. Soil Res. 1984, 22: 191-205.
[14] Cowell, J.D. Fertilizer requirements [J]. In soil: An Australian Viewpoint, Division of soils, CSIRO, 1983, 795-815.
[15] Cowell, J.D. Development of Gereral Soil Fertility Models for Variable Regions[C]. In Transaction of the 13 Congress of the international Society of Soil Science, Extended information Summaries, 1986, Part 2, 708-709.
[16] Harsh, S. B. Nutrient management system for agricultural producers[C]. In Computers in agricultural extension programs: proceeding of the 4th International Conference, Orlands, Florida. ASAE. Publication, 1992,589-594.
[17] Janise, B. H., et al. A system of quantitative evaluation of the fertility of tropical soils[J]. Geoderma, 1990, Vol.46(4): 299-318.
[18] Janssen, B. H., et al. A system for quantitative evaluation of soil fertility and the response to fertilizer[J]. Land qualities in space and time, 1989: 185-188.
[19] Johnson, G. V., D.L. Nofziger. NPKSPLUS: a computer program to examine agronomic and economic value of alternative fertilizer rates[J]. Journal-of-Production-Agriculture, 1992, Vol.(5): 4,415-420.
[20] Sinclair,A.H., A.G, Reaves, K.W.M, Brown. Design of a Scottish soil fertility information system[J]. Analytical-Proceedings, 1988,Vol.25: (4),120-122.
[21] Thomson, S. J. et al. Nutrient management software for Virginia farmers[C]. In Computers in agricultural extension programs: proceedings of the 4th International Conference. Orlando, Florida. ASAE, 1992, 584-588.
[22] Lemmon H. Comax: An expert system for cotton crop management [J]. Science, 1986, 233: 29-33.
[23] Howard, D., P. E. Hoskinson, M.Smith. Evaluation of the GOSSYM-COMAX cotton growth simulation model/expert management system in Tennessee[M]. 1994.
[24] Kruger, G. A., R. E. Karamanos. Fertility analysis and recommendation manager, Commum[J]. Soil Sci, Plant anal, 1994, 25(7&8): 955-965.
[25] Mc Callister, R., K. B. Shelley, P. Thum. The use of GIS for nitrogen management planning in Wisconsin[J]. Progress-in-rural-policy-and-planning, 1992, Vol.2(2): 5-16.
[26] Mc Cauley .J.D. Simulating spatial fertilizer applications in cotton production[C]. In Computers in agricultural extension programs. Proceedings of the 4th intermational conference, Orlando, Florida. ASAE Publication,1992: 159-164;
[27]李小平,胡文林.土壤肥料试验和农业统计程序包的设计、研制及其应用[J].计算机农业应用,1991,(1):30-36.
[28]张全德,胡秉民.农业试验统计模型和BASIC程序[M].浙江:科学技术出版社,1985.
[29]熊范纶,郭霖,吴文荣等.砂姜黑土小麦施肥计算机专家咨询系统[J].信息与控制,1987,16(2):7-11.
[30]孙波,严浩,施建平等.基于组件式GIS的施肥专家决策支持系统开发和应用[J].农业工程学报,2006,22(4):75-79.
[31]王海江,吕新.基于GIS技术的新疆棉花施肥专家系统[J].农业工程学报,2006,22(10):167-170.
[32]徐剑波,胡月明,李华兴等.优质稻高产优化施肥与栽培配套技术专家系统的研制[J].科技通报,2003,19(2):98-101.
[33]吕新,魏亦农,李少昆.基于GIS的土壤肥力信息管理及棉花施肥推荐支持决策系统研究[J].中国农业科学,2002,35(7):883-887.
[34]朱红春,张蕾,刘海英.基于GIS的猕猴桃土壤养分评价与施肥建议模型研究[J].农业工程学报,2007,23(6):194-198.
[35]陈赞章.基于WebGIS的橡胶精准施肥信息系统的设计与实现[D].北京:北京邮电大学,2007.
[36]聂艳,周勇,田有国等.基于3S的土壤肥料专家系统研究[J].土壤,2003,35(4):339-343.
[37]张蕾.基于GIS的果树施肥信息系统的研制与初步应用——以周至县猕猴桃为例[D].西安:西北大学,2005.
[38]周保平.黑龙江省水稻生态平衡施肥决策支持系统总体设计及部分模块功能实现[D].哈尔滨:东北农业大学,2003.
[39]赵东.测土施肥专家系统设计与实现[D].长春:长春理工大学,2008.
[40]程功,刘济,李跃峰等.烤烟配方施肥专家系统的研究与应用[J].河南农业大学学报,1997,31(2):166-170.
[41]熊玉唐,范勇,李显荣.麻江烤烟专家系统的开发与应用[J].贵州农业科学,2004,32(5):48-50.
[42]王军艳,张凤荣,王茹等.应用指数和法对潮土农田土壤肥力变化的评价研究[J].农村生态环境.2001,17(3):13-16,20.
[43]郑立臣,宇万太,马强等.农田土壤肥力综合评价研究进展[J].生态学杂志,2004,23(5):156-161.
[44]谢延敏.于Kriging模型和灰色关联分析的板料成形工艺稳健优化设计研究[D].上海:上海交通大学,2007.
[45] Burrough P A. Fuzzy mathematical methods for soil survey and land evaluation[J]. Journal of Soil Science,1989, 40: 477-490.
[46]曹志洪.解释土壤质量演变规律,确保土壤资源持续利用[J].世界科技研究与发展, 2001,23(3):28-32.
[47]熊毅.中国土壤[M].北京:科学出版社,1978.
[48]孙波,张桃林,赵其国.我国东南丘陵山区土壤肥力的综合评价[J].土壤学报,1995,32(4):362-369.
[49]陈海生,叶协峰,刘国顺等.基于GIS的河南省烤烟土壤肥力适宜性研究[J].土壤通报,2007,38(6):1081-1085.
[50]王桂芝.基于GIS的三亚市热作土地适宜性评价模型的建立[J].测绘与工程. 1997(2):23-28.
[51]周勇,张海涛,汪善勤等.江汉平原后湖地区土壤肥力综合评价方法及其应用[J].水土保持学报, 2001,15(4):70-74.
[52]左天觉,朱尊权译.烟草的生产、生理和生物化学[M].上海:远东出版社,1993,199-222,272-273.
[53] D. Layten Davis,Mark T.Nielsen.编.烟草——生产,化学和技术[M].北京:化学工业出版社,2003,76-78.
[54]陈义强.氮磷钾肥对烤烟内在品质的影响及其施肥模型[D].郑州:河南农业大学,2008.
[55]曹志洪.优质烤烟生产的土壤与施肥[M].江苏:科学技术出版社,1991,21-24,29-90, 208-235.
[56] Marchand M, Etourneaud F, Bourrie B.不同钾肥品种对烟草产量和化学成分的影响研究[J].中国烟草科学,1999,18(2): 6-11.
[57] Leggett, J. E. et al. Potassium and magnesium nutrition effects on yield and chemical composition of burley tobacoo leaves and smoke. Can J. Plant Sci., 1977 ,57: 159-166.
[58]广东省土壤普查办公室.广东土壤[M].北京:科学出版社,1993:412-499.
[59]胡国松,郑伟,王震东等.烟草营养原理[M].北京:科学出版社,2000:45-252.
[60]唐莉娜,熊德中.土壤酸度的调节对烤烟根系生长与烟叶化学成份含量的影响[J].中国生态农业学报,2002,10(4):65-67.
[61]陈建军,陈建勋,吕永华等.根系pH值对烟草无机营养的影响[J].植物生理学通讯,1996, 32(5):341-344.
[62]邓聚龙.灰色系统理论教程[M].武汉:华中理工大学出版社,1990.
[63]谢松云.基于灰色系统理论的目标识别研究[D].西安:西北工业大学,2001.
[64]周晓洁.基于模糊综合评价法的船舶热源系统优选研究[D].上海:上海交通大学,2008.
[65] Saaty T L.The analysis hierarchy process: planning, priority setting, resource allocation [M].New York:McGraw Hill,1980.
[66] SIFOLA M I, POSTIGLINE L. The effect of increasing NaCl in irrigation water on growth , gas exchange and yield of tobacco Burley type[J]. Field Crops Research, 2002, (74): 81-91.
[67]何振立,周启星,谢正苗.污染及有益元素的土壤化学平衡[M].北京:中国环境科学出版社,1998,75-79.
[68]宋承鉴.广西植烟区土壤特性分析[J].中国烟草,1994,(2).
[69]吕英华,秦双.测土与施肥[M].北京:中国农业出版社,2002.
[70]陈研,胡克林,冯凌等.基于土壤—作物系统模型模拟的冬小麦田间水氮优化管理[J].农业工程学报,2007,23(6):55-60.
[71]马新明,张娟娟,席磊等.基于叶面积指数(LAI)的小麦变量施氮模型研究[J].农业工程学报,2008,24(2):22-26.
[72]刘军,周连仁,梁桂荣等.白浆土生态平衡施肥参数的研究[J].东北农业大学学报,2007,38(2):215-220.
[73]陈家金,徐宗焕,林晶等.基于RCSODS的东南沿海水稻施肥量决策[J].中国农业气象,2008,29(1):71-74.
[74]席运官,钦佩,丁公辉等.基于RCSODS的有机水稻栽培施肥与效果分析[J].上海农业学报,2007,23(2):28-33.
[75]马新明,张娟娟,刘合兵等.基于氮素胁迫的WCSODS模型订正与检验[J].中国农业科学,2008, 41(2):391-396.
[76] David Makowski, Daniel Wallach, Jean-Marc Meynard. Models of yield, grain protein, and residual mineral nitrogen responses to applied nitrogen for winter wheat [J]. Agron J, 1999, 91: 377-385.
[77] Terry L, Kastens, John P, et al. Yield models implied by traditional fertilizer recommendations and a framework for including nontraditional information [J]. Soil Sci. Soc.Am.J., 2003,67: 351-364.
[78]柯庆明,林文雄,黄珍发等.小白菜平衡施肥数学模型模拟研究[J].中国生态农业学报,2005,13(1):119-121.
[79]吴才聪.精确农业变量施肥决策研究与技术经济分析[D].吉林:吉林大学,2003.
[80]张立明.人工神经网络的模型及其应用[M].上海:复旦大学出版社,1993.
[81]李孝安,张晓溃.神经网络与神经元计算导论[M].西安:西北工业大学出版社,1994.
[82] Hecht-Nielsen R. Theory of the back propagation neural network[J]. Proc.OFIJCNN,1989,1:593-603.
[83] Hecht-Nielsen R. Computer propagation networks[J]. Applied Potics, 1987, 26: 4979-4984.
[84]从爽.面向MATLAB工具箱的神经网络理论与应用[M].合肥:中国科学技术大学出版社,1998.
[85]李晓峰,刘光中.人工神经网络BP算法的改进及其应用[J].四川大学学报(工程科学版),2000,32(2):105-109.
[86]胥斌.奶牛疾病诊断遗传神经网络模型研究[D].重庆:重庆大学,2004.
[87]王合山.基于遗传算法的模糊神经网络及其在中医类风湿性关节炎诊断中的应用研究[D].云南:昆明理工大学,2004.
[88]王永骥,徐健.神经元网络控制[M].北京:机械工业出版社,1998.
[89]叶进,邢传鼎.基于人工神经网络的病症诊断原型系统[J].东华大学学报(自然科学版).2004,29(4):43-47.
[90]叶世伟,史忠植.神经网络原理[M].北京:机械工业出版社,2004.
[91]杨立成.基于最小二乘支持向量机的短期电力负荷预测方法研究[D].南宁:广西大学,2008.
[92]耿艳.基于最小二乘支持向量机的短期负荷预测方法及应用研究[D].济南:山东大学,2008.
[93]李晓东,席升阳,潘立.基于最小二乘支持向量机的中国粮食产量预测模型研究[J].水土保持研究,2007,14(6):322-324.
[94]辛治运,顾明.基于最小二乘支持向量机的复杂金融时间学列预测[J].清华大学学报(自然科学版),2008,48(7):1147-1149.
[95]徐立中.基于支持向量机的水质评价和预测研究[D].南京:河海大学,2006.
[96]陶少辉.最小二乘支持向量机的改进及其在化学化工中的应用[D].浙江:浙江大学,2006.
[97]姜静清.最小二乘支持向量机算法及应用研究[D].吉林:吉林大学,2007.
[98]李悦卿.基于神经网络和最小二乘支持向量机的软测量技术应用研究[D].青岛:青岛科技大学,2007.
[99] V.N. Vapnik, E. Levin, C.Y. Le. Measuring the VC-dimension of a learning machine[J]. Neural Computation, 1994, 6: 851-876.
[100]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42
[101] Suykens J A K, Vandewalle,J. Least squares support vector machine classifiers[J]. Neural processing letters, 1999, 9 : 293-300.
[102] Suykens J A K, Van Gestel T, De Brabanter J, et al. Least squares support vector machines[M], Singapore: World Scientific Publishing Co., Pte, Ltd., 2002.
[103] Zhao Ying,Kwoh Chee Keong. Fast leave-one-out evaluation and improvement on inference for LS-SVM[J], ICPR’04, 2004, 3: 494-497.
[104]占勇.基于支持向量机的电能质量分析和复合建模研究[D].上海:上海交通大学,2007.
[105]王海龙,周辉仁,宗蕴等. LS-SVM的一种参数优选方法及混沌时间序列预测[J].统计与决策,2009,(1):22-24.
[106] Kennedy J., Eberhart R. Particle swarm optimization[C]. IEEE International Conference on Neural Networks,1995. Proceedings,Vol.4, Nov.1 Dec.1995:1942-1948.
[107] Shi Y H,Eberhart R C. Parameter Selection in Particle Swarm Optimization[C]. Annual Conference on Evolutionary Programming. San Diego:1998.
[108] Kennedy, J., Eberthart, R.C. A discrete binary version of the particle swarm algorithm[C]. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 1997, Vol.5: 4104-4108.
[109]马文涛.参数优化LSSVM的巷道围岩松动圈预测研究[J].岩土力学,2007,28(增刊):460-464.
[110]张红梅,卫志农,龚灯才等.基于粒子群支持向量机的短期电力负荷预测[J]. 2006,34(3):28-31.
[111]林智杨,范明翔,陈锦辉.深入浅出Java Swing程序设计[M].北京:中国铁道出版社,2006.
[112] JFreeChart教程[EB/OL]. http://www.360doc.com/showWeb/0/0/217411.aspx,2008-10-5.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |