[1]江叶枫,郭熙,叶英聪,等.应用集成BP神经网络模型预测土壤有机质空间分布[J].江苏农业学报,2017,(05):1044-1050.[doi:doi:10.3969/j.issn.1000-4440.2017.05.013]
 JIANG Ye-feng,GUO Xi,YE Ying-cong,et al.Spatial distribution of soil organic matter predicted by BP neural network ensemble model[J].,2017,(05):1044-1050.[doi:doi:10.3969/j.issn.1000-4440.2017.05.013]
点击复制

应用集成BP神经网络模型预测土壤有机质空间分布()
分享到:

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2017年05期
页码:
1044-1050
栏目:
耕作栽培·资源环境
出版日期:
2017-10-30

文章信息/Info

Title:
Spatial distribution of soil organic matter predicted by BP neural network ensemble model
作者:
江叶枫12郭熙12叶英聪1孙凯1饶磊1
(1.江西农业大学国土资源与环境学院/江西省鄱阳湖流域农业资源与生态重点实验室,江西南昌330045;2.南方粮油作物协同创新中心,湖南长沙410000)
Author(s):
JIANG Ye-feng12GUO Xi12YE Ying-cong1SUN Kai1RAO Lei1
(1.College of Land Resource and Environment, Jiangxi Agricultural University/ Key laboratory of Poyang Lake Watershed Agricultural Resources and Ecology, Nanchang 330045, China;2.Southern Regional Collaborative Innovation Center for Grain and Oil Crops in China, Changsha 410000, China)
关键词:
土壤有机质Adaboost算法BP神经网络空间分布预测
Keywords:
soil organic matteradaptive boosting methodback propagation neural networkprediction of spatial distribution
分类号:
S126
DOI:
doi:10.3969/j.issn.1000-4440.2017.05.013
文献标志码:
A
摘要:
基于2014年江西省万年县测土配方施肥数据,以地理坐标、高程和坡度以及邻近样点信息作为网络的输入变量,采用集成BP神经网络模型(BPNN-Ada模型) 预测土壤有机质的空间分布,并与未集成的BP神经网络模型(BPNN模型)和普通克里金模型(OK模型)进行比较。结果表明,3种模型的预测精度大小顺序为BPNN-Ada模型>BPNN模型>OK模型。集成BP神经网络模型预测精度最高,效果最好,比较符合土壤有机质地学分布规律及实际情况。BPNN-Ada模型克服了BP神经网络局部搜索能力差和易陷入全局最优的缺点,提高了BP神经网络的泛化能力。
Abstract:
Based on the data collected from the project of soiltest-based formulated fertilization in Wannian county, Jiangxi province in 2014, a back propagation neural network ensemble model (BPNN-Ada) was used to predict the spatial distribution of soil organic matter (SOM) which was then compared to those by back propagation neural network model (BPNN) and ordinary Kriging model (OK). The BPNN-Ada and BPNN model were trained using the geographical coordinates, elevation, slope and adjacent sampling points information as inputs. The prediction accuracy of three models followed the order of BPNN-Ada>BPNN>OK. BPNN-Ada model could help to produce the SOM map with higher accuracy and better effect, which was consistent with the true geographical information and actual situation of SOM. By overcoming the shortcomings of poor local search ability and easiness to fall into global optimum, BPNN-Ada improved the generalization ability of BPNN.

参考文献/References:

[1]刘二永,刘健,余坤勇,等.基于环境因子和R-STPS的林地土壤有机质预测模型[J].农业机械学报,2015,46(1):133-137.
[2]李启权,岳天祥,范泽孟,等.中国表层土壤有机质空间分布模拟分析方法研究[J].自然资源学报, 2010, 25(8):1385-1399.
[3]马泉来,高凤杰,张志民,等.我国东北黑土丘陵区小流域土壤有机质空间分布模拟[J].环境科学研究, 2016, 29(3):382-390.
[4]李启权,王昌全,岳天祥,等.基于定性和定量辅助变量的土壤有机质空间分布预测——以四川三台县为例[J].地理科学进展, 2014, 33(2):259-269.
[5]史舟,李艳.地统计学在土壤学中的应用[M].北京:中国农业出版社,2006.
[6]沈掌泉,施洁斌,王珂,等.应用集成BP神经网络进行田间土壤空间变异研究[J].农业工程学报, 2004,20(3):35-39.
[7]董敏,王昌全,李冰,等.基于GARBF神经网络的土壤有效锌空间插值方法研究[J].土壤学报,2010,47(1): 42-50.
[8]李启权,王昌全,岳天祥,等.基于神经网络模型的中国表层土壤有机质空间分布模拟方法[J].地球科学进展,2012,27(2): 175-184.
[9]沈润平,丁国香,魏国栓,等.基于人工神经网络的土壤有机质含量高光谱反演[J].土壤学报, 2009, 46(3): 391-397.
[10]李启权,王昌全,岳天祥,等.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,2010,26(1): 87-93.
[11]陈明.MATLAB神经网络原理与实例精解[M].北京:清华大学出版社, 2013.
[12]HANSEN L K, SALSMON P. Neural network ensembles[J]. IEEE Trans Pattern Analysis and Machine Intelligence, 1990,12(10): 993-1001.
[13]SCHAPIRE R E. The strength of weak learnability[J]. Machine Learning, 1990, 5(2): 197-227.
[14]FREUND Y, SCHAPIRE R E. Adecision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences, 1997, 55(1): 119-139.
[15]沈掌泉.神经网络集成技术及其在土壤学中应用的研究[D].杭州:浙江大学, 2005.
[16]徐剑波,宋立生,夏振,等.基于GARBF神经网络的耕地土壤有效磷空间变异分析[J].农业工程学报, 2012,28(16): 158-165.
[17]李启权,王昌全,岳天祥,等.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,2008,45(2):360-365.
[18]王玉璟.空间插值算法的研究及其在空气质量监测中的应用[D].郑州:河南大学, 2010.
[19]张甘霖,龚子同.土壤调查实验室分析方法[M].北京:科学出版社, 2012.
[20]王丹丹,史学正,于东升,等.东北地区旱地土壤有机碳密度的主控自然因素研究[J].生态环境学报,2009,18(3):1049-1053.
[21]吴俊利,张步涵,王魁. 基于Adaboost的BP神经网络改进算法在短期风速预测中的应用[J].电网技术,2012,36(9):221-225.
[22]朱会义,刘述林,贾绍凤.自然地理要素空间插值的几个问题[J].地理研究,2004,23(4): 425-432.

相似文献/References:

[1]郑曼迪,熊黑钢,乔娟峰,等.基于综合光谱指数的不同程度人类干扰下土壤有机质含量预测[J].江苏农业学报,2018,(05):1048.[doi:doi:10.3969/j.issn.1000-4440.2018.05.012]
 ZHENG Man-di,XIONG Hei-gang,QIAO Juan-feng,et al.Prediction of soil organic matter content based on comprehensive spectral index at different levels of human disturbance[J].,2018,(05):1048.[doi:doi:10.3969/j.issn.1000-4440.2018.05.012]
[2]徐丽华,谢德体.土壤有机质含量预测精度对光谱预处理和特征波段的响应[J].江苏农业学报,2019,(06):1340.[doi:doi:10.3969/j.issn.1000-4440.2019.06.010]
 XU Li-hua,XIE De-ti.Response of soil organic matter content prediction accuracy to preprocessing of spectra and feature bands[J].,2019,(05):1340.[doi:doi:10.3969/j.issn.1000-4440.2019.06.010]
[3]赵懿,杜建军,张振华,等.秸秆还田方式对土壤有机质积累与转化影响的研究进展[J].江苏农业学报,2021,(06):1614.[doi:doi:10.3969/j.issn.1000-4440.2021.05.032]
 ZHAO Yi,DU Jian-jun,ZHANG Zhen-hua,et al.Research progress on the effects of straw returning on soil organic matter accumulation and transformation[J].,2021,(05):1614.[doi:doi:10.3969/j.issn.1000-4440.2021.05.032]
[4]张永亮,汪泓,肖玖军,等.基于高光谱的山区耕地土壤有机质含量估测[J].江苏农业学报,2024,(01):112.[doi:doi:10.3969/j.issn.1000-4440.2024.01.012]
 ZHANG Yong-liang,WANG Hong,XIAO Jiu-jun,et al.Estimation of soil organic matter content in mountain farmland based on hyperspectral data[J].,2024,(05):112.[doi:doi:10.3969/j.issn.1000-4440.2024.01.012]

备注/Memo

备注/Memo:
收稿日期:2017-01-05 基金项目:国家自然科学基金项目(41361049);江西省自然科学基金项目(20122BAB204012);江西省赣鄱英才“555”领军人才项目(201295) 作者简介:江叶枫(1994-),男,江西余干人,硕士,主要从事土壤环境与系统模拟方面研究。(E-mail)jiangyf0308@163.com 通讯作者:郭熙,(E-mail)xig435@163.com
更新日期/Last Update: 2017-11-03