全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

丘陵区土壤有机质空间分布预测的神经网络方法

Keywords: 土壤,植被,模型,地形因子,丘陵区,径向基函数神经网络,空间预测

Full-Text   Cite this paper   Add to My Lib

Abstract:

土壤性质空间分布信息的准确表达是土壤资源优化利用和土壤环境保护的需要。为模拟川中丘陵区县域尺度上土壤有机质的空间分布格局,构建了以地理坐标、地形和植被因子为网络输入的径向基函数神经网络模型(RBFNN_E),并将该方法与普通克里格法(OK)、多元回归模型(MLR)和仅以地理坐标为网络输入的神经网络模型(RBFNN_C)相比较。结果表明:RBFNN_E对479个验证点模拟结果的平均绝对误差(MAE)、平均相对误差(MRE)和均方根误差(RMSE)较MLR分别降低了1.74%、1.45%和2.64%,较OK分别降低了7.77%、12.76%和3.92%,较RBFNN_C分别降低了8.89%、9.81%和7.68%。从模拟的空间分布图来看,RBFNN_E能较好地刻画环境变化引起的土壤有机质空间变异的细节信息。因此,融合环境因子的神经网络模型(RBFNN_E)不仅具有较高的模拟精度,还能更好地揭示复杂地形下土壤有机质的空间变异,使模拟结果更符合区域地学规律与实际情况,可为复杂环境条件下土壤管理、精准农业的实施以及区域环境规划等提供科学依据。

References

[1]  Motaghian H R,Mohammadi J..Spatial estimation of saturated hydraulic conductivity from terrain attributes using regression,kriging,and artificial neural networks[J].Pedosphere,2011,(02):170-177.
[2]  Sculla P,Franklina J,Chadwickb O A,Predictive soil mapping:A review,Progress in Physical Geography,2003(2).
[3]  孟涛,周非,聂庆华..污灌条件下农田土壤重金属的空间变异与模拟[J].农业环境科学学报,2008,(03):867-872.doi:10.3321/j.issn:1672-2043.2008.03.006.
[4]  石淑芹,陈佑启,李正国..基于土壤类型和微量元素辅助信息的土壤属性空间模拟[J].农业工程学报,2010,(12):199-205.doi:10.3969/j.issn.1002-6819.2010.12.034.
[5]  李启权,岳天祥,范泽孟,中国表层土壤有机质空间分布模拟分析方法研究,自然资源学报,2010(8).
[6]  Grunwald S,Multi-criteria characterization of recent digital soil mapping and modeling approaches,Geoderma,2009(3/4).
[7]  Zhu AX ;Hudson B ;Burt J ;Lubich K ;Simonson D,Soil mapping using GIS, expert knowledge, and fuzzy logic,Soil Science Society of America Journal?,2001, 65(5).
[8]  刘兴权,许晶玉,江丽华..山东省种植区地下水硝酸盐污染空间变异及分布规律研究[J].农业环境科学学报,2010,(06):1172-1179.
[9]  McBratney A B,Mendonca Santos M L,Minasny B,On digital soil mapping,Geoderma,2003(1/2).
[10]  Yusuf Erzin ;B. Hanumantha Rao ;D. N. Singh,Artificial neural network models for predicting soil thermal resistivity,International Journal of Thermal Sciences?,2008, 47(10).
[11]  Zou P,Yang J S,Fu J R,Artificial neural network and time series models for predicting soil salt and water content,Agricultural Water Management,2010(12).
[12]  何勇,张淑娟,方慧..基于人工神经网络的田间信息插值方法研究[J].农业工程学报,2004,(03):120-123.doi:10.3321/j.issn:1002-6819.2004.03.029.
[13]  胡大伟,卞新民,李思米..基于神经网络的农田土壤重金属空间分布分析[J].农业环境科学学报,2007,(01):216-223.doi:10.3321/j.issn:1672-2043.2007.01.043.
[14]  雷能忠,王心源,蒋锦刚..基于BP神经网络插值的土壤全氮空间变异[J].农业工程学报,2008,(11):130-134.doi:10.3321/j.issn:1002-6819.2008.11.025.
[15]  李启权,王昌全,岳天祥..基于RBF神经网络的土壤有机质空间变异研究方法[J].农业工程学报,2010,(01):87-93.doi:10.3969/j.issn.1002-6819.2010.01.015.
[16]  李启权,王昌全,岳天祥..不同输入方式下RBF神经网络对土壤性质空间插值的误差分析[J].土壤学报,2008,(02):360-365.doi:10.3321/j.issn:0564-3929.2008.02.024.
[17]  Ziadat, F M,Analyzing digital terrain attributes to predict soil attributes for a relatively large area.,Soil Science Society of America Journal?,2005, 69(5).
[18]  Mishra U,Lal R,Liu D S,Predicting the Spatial variation of the soil organic carbon pool at a regional scale,Soil Science Society of America Journal,2010(3).
[19]  McSweeney K,Slater B K,Hammer R D,Towards a new framework for modeling the soil-landscape continuum,Madison,WI:Soil Science Society of America,1994.
[20]  张素梅,王宗明,张柏..利用地形和遥感数据预测土壤养分空间分布[J].农业工程学报,2010,(05):188-194.doi:10.3969/j.issn.1002-6819.2010.05.033.
[21]  Murat Alp ;H. Kerem Cigizoglu,Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data,Environmental Modelling & Software?,2007, 22(1).
[22]  Sharma V ;Negi SC ;Rudra RP ;Yang S,Neural networks for predicting nitrate-nitrogen in drainage water,Agricultural Water Management?,2003, 63(3).
[23]  Meersmans J,De Ridder F,Canters F,A multiple regression approach to assess the spatial distribution of soil organic carbon(SOC)at the regional scale(Flanders,Belgium),Geoderma,2008(1/2).
[24]  Burrough P A,Soil variability:A late 20th century view,Soils and Fertilizers,1993(5).
[25]  Kravchenko AN,Influence of spatial structure on accuracy of interpolation methods,Soil Science Society of America Journal?,2003, 67(5).
[26]  Webster K L,Creed I F,Beall F D,A topographic template for estimating soil carbon pools in forested catchments,Geoderma,2011(3/4).

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133