GIS and ANN-based spatial prediction of DOC in river networks: a case study in Dongjiang, Southern China

GIS and ANN-based spatial prediction of DOC in river networks: a case study in Dongjiang, Southern China
复制标题

基于 GIS 和 ANN 的河网 DOC 空间预测:以华南东江地区为例

DOI:
10.1007/s12665-012-2177-y
复制
发表时间:
2013-03
影响因子:
2.8
通讯作者:
Chen, Jingyi
Chen, Jingyi
中科院分区:
环境科学与生态学4区
文献类型:
--
作者:
Fu, Yingchun;Zhao, Yaolong;Zhang, Yongrui;Guo, Taisheng;He, Ziwei;Chen, Jingyi

文献摘要

参考文献

被引文献

相似文献

本文研究了使用人工神经网络 (ANN) 模型来预测河网中溶解有机碳 (DOC),并评估流域特征对河流 DOC 的影响。样本和相关环境变量是通过 28 个水文响应单元 (HRU) 的现场采样和 MODIS/SRTM DEM 卫星图像获得的。 HRU 可以提供可靠的空间插值来填充数据间隙,并结合每个 ANN 神经元中观测值之间的潜在空间相关性。通过确定性和统计方法以及空间回归克里金法评估神经网络建模的过程和结果。空间预测结果表明,采用改进的7-15-1架构反向传播算法的ANN是最优网络,其预测保持了大部分原始空间变化并消除了RK的平滑效应。土壤有机碳密度、地理经度、地表径流和Chlain河水等四个敏感变量的相对贡献之和>75%。开放灌木丛的 HRU 的预测误差约为 6%,但城市和农田的 HRU 的误差为 24-30%。这种模式体现了城市地区人为对河流 DOC 和农田农业活动的影响。本研究中基于 ANN 建模的 GIS 的有用性通过描述河流 DOC 的空间变化得到了证明,并表明了了解流域影响评估的敏感因素的好处。
This paper investigates the use of an artificial neural network (ANN) model to predict dissolved organic carbon (DOC) in a river network and evaluates the impacts of watershed characteristics on stream DOC. Samples and relevant environmental variables were obtained from field sampling at 28 hydrological response units (HRUs) and a MODIS/SRTM DEM satellite image. HRUs can provide reliable spatial interpolation for filling data gaps and incorporate potential spatial correlation among observations in each ANN neuron. The process and results of neural network modeling were assessed by deterministic and statistical methods and spatial regression kriging. The spatial prediction results show that ANN, using improved back propagation algorithms of 7-15-1 architecture, was the optimal network, by which predictions maintained most of the original spatial variation and eliminated smoothing effects of RK. The sum of the relative contributions of four sensitive variables, including soil organic carbon density, geographic longitude, surface runoff and Chlain river water, was >75 %. A minor prediction error of ~6 % was found in HRUs of open shrublands, but HRUs of urban and croplands had an error of 24–30 %. This pattern exemplifies anthropogenic impacts in urban areas on stream DOC and agricultural activities in croplands. The usefulness of ANN modeling-based GIS in this study is demonstrated by depiction of spatial variation of stream DOC and indicates the benefits of understanding sensitive factors for watershed impact assessments.
DOI: 10.1007/bf02083653
发表时间: 1996-05
期刊: Mathematical Geology
影响因子: --
作者:
R. Olea;V. Pawlowsky
通讯作者: R. Olea;V. Pawlowsky
DOI: 10.1007/978-0-85729-299-5_8
发表时间: 2011
期刊: --
影响因子: --
作者:
W. Ertel
通讯作者: W. Ertel
DOI: 10.1109/is.2002.1044229
发表时间: 2002-12
期刊: Proceedings First International IEEE Symposium Intelligent Systems
影响因子: --
作者:
G. Dimirovski;Yuanwei Jing
通讯作者: G. Dimirovski;Yuanwei Jing
DOI: 10.1029/2006jf000493
发表时间: 2007-03
影响因子: --
作者:
Shurong Zhang;Xixi Lu;D. Higgitt;C. Chen;Huiguo Sun;Jingtai Han
通讯作者: Shurong Zhang;Xixi Lu;D. Higgitt;C. Chen;Huiguo Sun;Jingtai Han
DOI: 10.1016/j.marchem.2004.02.014
发表时间: 2004-10
期刊: Marine Chemistry
影响因子: 3
作者:
Xuchen Wang;Robert F. Chen;G. Gardner
通讯作者: Xuchen Wang;Robert F. Chen;G. Gardner