| 基于RBF神经网络耕地土壤全氮插值方法的研究 |
| |
| 引用本文： | 宋兆璞,刘畅,赵凯,徐剑波.基于RBF神经网络耕地土壤全氮插值方法的研究[J].安徽农业科学,2012,40(20):10424-10425,10548. |
| |
| 作者姓名： | 宋兆璞 刘畅 赵凯 徐剑波 |
| |
| 作者单位： | 华南农业大学信息学院,广东广州,510642;华南农业大学信息学院,广东广州,510642;华南农业大学信息学院,广东广州,510642;华南农业大学信息学院,广东广州,510642 |
| |
| 基金项目： | 广东省教育部产学研结合项目，广东省科技计划项目 |
| |
| 摘 要： | 目的]通过耕地土壤全氮的空间变异特性研究,可以更好地调整耕地管理措施、合理施用氮肥、减少资源浪费。方法]利用RBF(Radial Basis Function,径向基函数)神经网络插值法对区域土壤全氮进行空间插值,同时与普通克里格法进行比较。结果]RBF神经网络插值法在拟合能力和插值能力方面要明显优于普通克里格法。结论]RBF神经网络法具有很好的应用前景。
|
| 关 键 词： | RBF神经网络 Matlab ArcGIS 全氮 插值 |
Study of Soil Total Nitrogen based on RBF Neural Network Interpolation Method |
| |
| Institution: | SONG Zhao-pu et al(Institute of information,South China Agricultural University,Guangzhou,Guangdong 510642) |
| |
| Abstract: | Objective] The study of spatial variability of total nitrogen in farmland soil could provide the basis for the adjustment of the cultivated land management,the application of the nitrogen fertilizer reasonably,the reduction of the resources waste.Method] RBF(Radial Basis Function) neural network interpolation method was used for the spatial interpolation on region soil total nitrogen,and was compared with ordinary kriging method.Result] RBF neural network interpolation method had a greater advantage than ordinary kriging method on the fitting and interpolation ability.Conclusion] RBF neural network method has good application prospects. |
| |
| Keywords: | RBF neural network Matlab ArcGIS Total nitrogen Interpolation |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
