基于神经网络的水稻不同生育周期长势预测模型
|
摘要
水稻的生长发育是一个复杂的过程,其中土壤、气候等环境因子对水稻的最终产量影响巨大。虽然有研究提出了天气、土壤等环境因素对水稻产量影响的预测模型,但因缺乏对水稻各个生育周期的长势的定量描述,所以对水稻不同生育周期的长势预测还不够细致。文章在水稻各周期生长模型特性和高邮灌区的水稻种植历史数据的基础上,设计并训练出环境因素对水稻各生育生长趋势影响预测模型。实验结果证明了该方法的有效性及合理性,对预测水稻在不同周期长势情况有一定的参考价值。
The growth and development of rice is a complex process, in which environmental factors such as soil and climate have a great impact on the final yield of rice. Although some studies have proposed a prediction model for the effects of environmental factors such as weather and soil on rice yield, the lack of quantitative description of the growth cycle of rice has not been sufficiently detailed for the growth cycle of rice. Based on the characteristics of rice growth cycle and the rice planting historical data in Gaoyou irrigation district,this paper designs and trains a prediction model of the influence of environmental factors on the growth and growth trends of rice. The experimental results demonstrate the validity and rationality of the method, and have certain reference value for predicting the growth of rice in different periods.
The growth and development of rice is a complex process, in which environmental factors such as soil and climate have a great impact on the final yield of rice. Although some studies have proposed a prediction model for the effects of environmental factors such as weather and soil on rice yield, the lack of quantitative description of the growth cycle of rice has not been sufficiently detailed for the growth cycle of rice. Based on the characteristics of rice growth cycle and the rice planting historical data in Gaoyou irrigation district,this paper designs and trains a prediction model of the influence of environmental factors on the growth and growth trends of rice. The experimental results demonstrate the validity and rationality of the method, and have certain reference value for predicting the growth of rice in different periods.
引文
[1]郭庆春,王素娟,何振芳.基于BP人工神经网络的土壤含水量预测模型的研究[J].山东农业科学,2012(12):11-15.
[2]程曼,袁洪波,蔡振江,等.基于全局变量预测模型的温室环境控制方法[J].农业工程学报,2013(s1):177-183.
[3]AIPING W.Establishment of wheat yield prediction model in dry farming area based on neural network[J].Neuro Quantology,2018(6):768-775.
[4]ZHANG Y,QIN Q.Winter wheat yield estimation with ground based spectral information[J].IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium,Valencia,2018(66):6863-6866.
[5]邱才飞,邵彩虹,关贤交,等.节水灌溉对双季晚稻农田生态及水肥利用的影响[J].西北农业学报,2018(4):509-517.
[6]张倩.基于天气预报信息解析的冬小麦灌溉预报研究[D].杨凌:西北农林科技大学,2015.
[7]沈花玉,王兆霞,高成耀,等.BP神经网络隐含层单元数的确定[J].天津理工大学学报,2008(5):13-15.
[8]张清良,李先明.一种确定神经网络隐层节点数的新方法[J].吉首大学学报(自然科学版),2002(1):89-91.
[9]DAYHOFF J E,DELEO J M.Artificial neural networks[J].Cancer,2001(8):1615-1634.
[10]高大文,王鹏,蔡臻超.人工神经网络中隐含层节点与训练次数的优化[J].哈尔滨工业大学学报,2003(2):85-87.
[11]冯艳,付强,李国良,等.水稻需水量预测的小波BP网络模型[J].农业工程学报,2007(4):66-69.
[12]庄德续.不同栽培、灌溉模式对水稻需水规律和产量的影响研究[D].哈尔滨:东北农业大学,2015.
[13]朱士江,孙爱华,张忠学,等.不同节水灌溉模式对水稻分蘖、株高及产量的影响[J].节水灌溉,2013(12):16-19.
[14]HOU,ZHAO Y X,ZHANG H F,et al.A novel method for predicting cadmium concentration in rice grain using genetic algorithm and back-propagation neural network based on soil properties[J].Environmental Science and Pollution Research International,2018(35):35682-35692.
[15]YASEEN Z M,FU M,WANG C,et al.Application of the hybrid artificial neural network coupled with rolling mechanism and grey model algorithms for streamflow forecasting over multiple time horizons[J].Water Resources Management,2018(5):1883-1899.
[2]程曼,袁洪波,蔡振江,等.基于全局变量预测模型的温室环境控制方法[J].农业工程学报,2013(s1):177-183.
[3]AIPING W.Establishment of wheat yield prediction model in dry farming area based on neural network[J].Neuro Quantology,2018(6):768-775.
[4]ZHANG Y,QIN Q.Winter wheat yield estimation with ground based spectral information[J].IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium,Valencia,2018(66):6863-6866.
[5]邱才飞,邵彩虹,关贤交,等.节水灌溉对双季晚稻农田生态及水肥利用的影响[J].西北农业学报,2018(4):509-517.
[6]张倩.基于天气预报信息解析的冬小麦灌溉预报研究[D].杨凌:西北农林科技大学,2015.
[7]沈花玉,王兆霞,高成耀,等.BP神经网络隐含层单元数的确定[J].天津理工大学学报,2008(5):13-15.
[8]张清良,李先明.一种确定神经网络隐层节点数的新方法[J].吉首大学学报(自然科学版),2002(1):89-91.
[9]DAYHOFF J E,DELEO J M.Artificial neural networks[J].Cancer,2001(8):1615-1634.
[10]高大文,王鹏,蔡臻超.人工神经网络中隐含层节点与训练次数的优化[J].哈尔滨工业大学学报,2003(2):85-87.
[11]冯艳,付强,李国良,等.水稻需水量预测的小波BP网络模型[J].农业工程学报,2007(4):66-69.
[12]庄德续.不同栽培、灌溉模式对水稻需水规律和产量的影响研究[D].哈尔滨:东北农业大学,2015.
[13]朱士江,孙爱华,张忠学,等.不同节水灌溉模式对水稻分蘖、株高及产量的影响[J].节水灌溉,2013(12):16-19.
[14]HOU,ZHAO Y X,ZHANG H F,et al.A novel method for predicting cadmium concentration in rice grain using genetic algorithm and back-propagation neural network based on soil properties[J].Environmental Science and Pollution Research International,2018(35):35682-35692.
[15]YASEEN Z M,FU M,WANG C,et al.Application of the hybrid artificial neural network coupled with rolling mechanism and grey model algorithms for streamflow forecasting over multiple time horizons[J].Water Resources Management,2018(5):1883-1899.