A neural network ensemble method for precision fertilization modeling

摘要：

There exists nonlinear relationship between fertilizer input and soil nutrient. To calculate the fertilization rate more precisely, a novel neural network ensemble method has been proposed, in which the K-means clustering method is used to select an optimal network individual and Lagrange multiplier is used to combine these selected networks. Based on the above neural network ensemble method, a fertilization model is constructed. In this model, the soil nutrient and the fertilization rate are taken as neural network inputs and yield is taken as output. This model transforms the calculation of fertilization rate into solving a programming problem, which can calculate the fertilization rate with maximum yield and maximum profit as well as forecast the yield. Furthermore, this fertilization model has been tested on the fertilizer effect data. The results show that the forecasting value of neural network ensemble is more accurate than individual neural network. The fertilization model constructed in this paper not only can precisely simulate the nonlinear relationship between yield and soil nutrient but also can adequately make use of the existing fertilizer effect data.

关键词： neural network ensemble precision fertilization clustering algorithm Lagrange Multiplier method

作者: Helong yu Dayou Liu Guifen Chen Baocheng Wan Shengsheng Wang Bo Yanga

作者单位: College of Computer Science and Technology ,Jilin University ,Changchun ,Jilin Province,P. R. China, College of Computer Science and Technology ,Jilin University ,Changchun ,Jilin Province,P. R. China, College of Information Technology ,Jilin Agricultural University ,Changchun ,Jilin Province,P. R. Ch

会议类型: 国际会议

会议名称: 第三届亚洲精细农业会议暨第五届智能化农业信息技术国际会议

会议地点: 北京

会议语种:英文

页码: 1-8

在线出版日期: 2009-10-14（万方平台首次上网日期，不代表论文的发表时间）