LIANG Xu-guang,WANG Fu-lin,ZHAO Hong-lei,et al.Optimization of Soybean Planting Density and Fertilizer Application Rate Based on RBF Neural Network[J].Soybean Science,2020,39(03):406-413.[doi:10.11861/j.issn.1000-9841.2020.03.0406]
基于RBF神经网络的大豆种植密度和施肥量优化
- Title:
- Optimization of Soybean Planting Density and Fertilizer Application Rate Based on RBF Neural Network
- Keywords:
- Neural network; Regression; Optimization; Soybean; Planting density; Fertilizer application rate
- 文献标志码:
- A
- 摘要:
- 为解决使用传统回归模型对大豆种植密度及施肥量进行优化时存在的拟合精度低、优化结果不准确等问题，提出一种基于RBF神经网络的优化方法。将大豆种植密度、N、P2O5、K2O施用量作为试验因素，产量作为影响指标，选取黑河43作为试验材料，进行四因素五水平的正交旋转试验，获得各处理下大豆产量数据。对种植密度、施肥量与产量关系构建RBF神经网络拟合模型，对模型进行优化，得到最优种植密度42.65×104株·hm-2、施N量61.82 kg·hm-2、施P2O5量106.05 kg·hm-2、施K2O量19.81 kg·hm-2，该配比下大豆产量为3 821.48 kg·hm-2。对优化结果进行试验验证，最优配比下大豆实际产量为3 742.29 kg·hm-2，与优化结果相对误差为-2.17%，表明该方法有效，且优化结果准确。
- Abstract:
- In order to solve the problems of low fitting accuracy and inaccurate optimization results when soybean planting density and fertilizer application rate was optimized with the traditional regression model, this study proposed an optimization method based on RBF neural network. Soybean planting density, fertilizer application rate of N, P2O5, K2O were taken as experimental factors, and soybean yield was taken as impact indicator. An experiment of 4 factors and 5 levels was designed by the orthogonal rotation method on the seed of Heihe 43. The data of soybean yield under each treatment was obtained. The RBF neural network fitting model was constructed for the relationship between planting density, fertilizer application rate and yield, and the optimization method proposed in this paper was used to optimize this model. The optimization result was planting density 42.65×104 plants?ha-1, N fertilizer application rate 61.82 kg?ha-1, P2O5 fertilizer application rate 106.05 kg?ha-1, K2O fertilizer application rate 19.81 kg?ha-1, the yield of soybean under this combination was 3 821.48 kg?ha-1. Another experiment was carried out to verify the optimization result. The actual soybean yield at the optimal ratio was 3 742.29 kg?ha-1. The relative error between actual yield and optimum yield was -2.17%. It showed that the optimization method was effective and the optimization result was accurate.
参考文献/References:
［1］任小俊, 吕新云, 马俊奎. 种植密度与施肥水平对山西早熟夏大豆产量与主要农艺性状的影响［J］. 大豆科学, 2019, 38(6): 921-927. (Ren X J, Lyu X Y, Ma J K. Effects of different planting densities and fertilization levels on yield and main agronomic characters of early-maturing summer soybean in Shanxi province［J］. Soybean Science, 2019, 38(6): 921-927.)［2］Liu B, Liu X B, Wang C, et al. Responses of soybean yield and yield components to light enrichment and planting density［J］. International Journal of Plant Production, 2010, 4(1): 1-9.［3］杨继学, 黄珊珊, 杨明亮, 等. 密度和施肥量对不同分枝类型大豆产量的影响［J］. 大豆科学, 2012, 31(3): 381-384. (Yang J X, Huang S S, Yang M L, et al. Effect of density and fertilizer amount on yield of different branching types of soybeans［J］. Soybean Science, 2012, 31(3): 381-384.)［4］张洪刚, 周琴, 何小红, 等. 播期、密度和肥料对菜用大豆南农9610产量和品质的影响［J］. 江苏农业学报, 2008(5): 662-667. (Zhang H G, Zhou Q, He X H, et al. Effects of sowing date, planting density and N, P and K fertilizer on yield and quality of vegetable soybean［J］. Jiangsu Journal of Agricultural Sciences, 2008(5): 662-667.）［5］刘渊, 李文龙, 李喜焕, 等.施肥水平和种植密度对河北山区夏播大豆产量及品质影响［J］. 中国农业科技导报, 2017, 19(8): 115-123. (Liu Y, Li W L, Li X H, et al. Effects of fertilization level and planting density on yield and quality of summer-sowing soya in mountainous areas of Hebei［J］. Journal of Agricultural Science and Technology, 2017, 19(8): 115-123.)［6］李忠芳, 徐明岗, 张会民, 等. 长期施肥下中国主要粮食作物产量的变化［J］. 中国农业科学, 2009, 42(7): 2407-2414. (Li Z F, Xu M G, Zhang H M, et al. Grain yield trends of different food crops under long-term fertilization in China［J］. Scientia Agricultura Sinica, 2009, 42(7): 2407-2414.)［7］程伟燕, 李志刚, 李瑞平. 密度对大豆光合特性和产量的影响［J］. 作物杂志, 2010(4): 65-72. (Cheng W Y, Li Z G, Li R P. Effect of densities on photosynthetic characteristic and yield in soybean［J］. Crops, 2010(4): 65-72.)［8］刘玉兰, 陈殿元, 元明浩, 等. 种植密度对小粒大豆光合生产能力的影响［J］. 大豆科学, 2018, 37(4): 551-557. (Liu Y L, Chen D Y, Yuan M H, et al. Effects of planting density on photosynthetic capactity of glycine gracilis［J］. Soybean Science, 2018, 37(4): 551-557.)［9］张伟 ,张惠君, 王海英, 等. 株行距和种植密度对高油大豆农艺性状及产量的影响［J］. 大豆科学, 2006，14(3): 283-287. (Zhang W, Zhang H J, Wang H Y, et al. Effects of spacings and planting densities on agronomic traits and yield in high-oil soybeans［J］. Soybean Science, 2006，14(3):283-287.)［10］Muoneke C O, Ogwuche M A O, Kalu B A. Effect of maize planting density on the performance of maize/soybean intercropping system in a guinea savannah agroecosystem［J］. African Journal of Agricultural Research, 2007, 2(12): 667-677.［11］Sharma V, Rudnick D R, Irmark S. Development and evaluation of ordinary least squares regression models for predicting irrigated and rainfed maize and soybean yields［J］. Transactions of the ASABE, 2013, 56(4): 1361-1378.［12］陈怀珠,杨守臻, 唐向民, 等. 华南春大豆氮磷钾肥配施效应及用量研究［J］. 大豆科学, 2018, 37(1): 117-125. (Chen H H, Yang S Z, Tang X M, et al. Study on the effects and amounts of combined application of nitrogen, phosphorus and potassium fertilizers for spring soybean in southern China［J］. Soybean Science, 2018, 37(1): 117-125.)［13］申晓慧, 姜成, 刘婧琦, 等. 栽培因子对合农63大豆产量的影响［J］. 大豆科学, 2012, 31(4): 589-592. (Shen X H, Jiang C, Liu J Q, et al. Effect of cultural factors on yield characters of soybean cv. Henong 63［J］. Soybean Science, 2012, 31(4): 589-592.)［14］王会鹏. 大豆多因素养分密度效应试验及模型研究［D］. 哈尔滨: 东北农业大学, 2016: 40-50. (Wang H P. Research on nutrient density effect of multifactor test and model of soybean［D］. Harbin: Northeast Agricultural University, 2016: 40-50.)［15］徐督, 任海祥, 宁海龙. 栽培密度、施肥量及有效含量对大豆产量的影响［J］. 大豆科技, 2013(1): 21-25. (Xu D, Ren H X, Ning H L. Effect of planting density, fertilization rate and effective concentration on soybean yield［J］. Soybean Science & Technology, 2013(1): 21-25.)［16］井力群, 王福林, 邢丽超. 多因素播种施肥技术研究［J］. 东北农业大学学报, 2009, 40(10): 119-121. (Jing L Q, Wang F L, Xing L C. Study on multifactor technology of sowing and fertilization［J］. Journal of Northeast Agricultural University, 2009, 40(10): 119-121.)［17］张淑娟, 何勇, 方慧. 人工神经网络在作物产量与土壤空间分布信息关系分析中的应用［J］. 系统工程理论与实践, 2003(12): 121-127. (Zhang S J, He Y, Fang H. Application of artificial neutral network on relationship analysis of crop yield and soil space distributing information［J］. System Engineering Theory and Practice, 2003(12): 121-127.)［18］张漫, 李婷, 季宇寒, 等. 基于BP神经网络算法的温室番茄CO2增施策略优化［J］. 农业机械学报, 2015, 46(8): 239-244. (Zhang M, Li T, Ji Y H, et al. Optimization of CO2 enrichment strategy based on BPNN for tomato plants in greenhouse［J］. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(8): 239-244.)［19］王福林, 董志贵, 吴志辉, 等. 基于BP神经网络的玉米种植密度和施肥量优化［J］. 农业工程学报, 2017, 33(6): 92-99. (Wang F L, Dong Z G, Wu Z H, et al. Optimization of maize planting density and fertilizer application rate based on BP neural network［J］. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(6): 92-99.)［20］董志贵, 宋庆凤, 王福林, 等. 基于BP神经网络的整株秸秆还田机功耗优化［J］. 系统工程理论与实践, 2018, 38(9): 2401-2408. (Dong Z G, Song Q F, Wang F L, et al. Optimize on power dissipation of whole-straw returning device based on BP neural network［J］. Systems Engineering-Theory and Practice, 2018, 38(9): 2401-2408.)［21］韩力群. 人工神经网络教程［M］. 北京:北京邮电大学出版社, 2006: 127-142. (Han L Q. Artificial neural network tutorial［M］. Beijing: Beijing University of Posts and Telecommunications, 2006: 127-142.)［22］Poggio T, Girosi F. Networks for approximation and learning［J］. Proceedings of the IEEE, 1990, 78(9): 1481-1497.［23］王伟. 黑龙江省大豆合理施肥参数的研究［D］. 哈尔滨:东北农业大学, 2009: 10-20. (Wang W. A study on parameters of rational fertilization for soybean in Heilongjiang［D］. Harbin: Northeast Agricultural University, 2009: 10-20.)［24］高隽. 人工神经网络原理及仿真实例［M］. 北京: 机械工业出版社, 2003: 55-61. (Gao J. Principle of artificial neural network and simulation examples［M］. Beijing: China Machine Press, 2003: 55-61.)
相似文献/References:
[1]谢来超,沈群,张新艳,等.基于神经网络法对原料大豆豆腐加工特性的评价[J].大豆科学,2013,32(01):93.[doi:10.3969/j.issn.1000-9841.2013.01.022]
XIE Lai-chao,SHEN Qun,ZHANG Xin-yan,et al.Evaluation on Tofu Processing Characteristics of Soybean Based on Neural Network[J].Soybean Science,2013,32(03):93.[doi:10.3969/j.issn.1000-9841.2013.01.022]
备注/Memo