期刊文献+

农作区净灌溉需水量模拟及不确定性分析 被引量:23

Simulation and uncertainty analysis of net irrigation requirement in agricultural area
下载PDF
导出
摘要 净灌溉需水量是估算农业灌溉用水量的参考依据。该文以西北干旱内陆区石羊河流域上中下游的古浪县,凉州区,民勤县为研究对象,在分析农业净灌溉需水量宏观驱动力因子(1959-2005)的基础上,以关键因子作为输入项,区域农业净灌溉量为输出项,分别建立农业净灌溉需水量的多元线性回归模型、人工神经网络BP模型以及人工神经网络集成模型。并对不同模型的模拟效果进行比较;通过对时间序列的离散化蒙特卡洛(MC)设计,采用不确定性评价指数(d-factor)对3种模型模拟的不确定性进行分析。结果表明:与多元线性回归模型和神经网络BP模型相比,神经网络集成模型具有较高的模拟精度,并能合理地指示影响因素与净灌溉需水量的不确定性变化。 Net irrigation requirement is the major component of agricultural water use.In this study,the regional net irrigation requirement of agricultural area in Shiyang river basin in semi-arid region of Northwest China was analyzed.Based on the zones of local agricultural water use,the key factors are chosen by driving factor analysis(1959-2005),and then regional net irrigation requirement was simulated using multiple-linear regression(MLR),artificial neural network(ANN) and Ensemble ANN models.Then discrimination time-series Monte-Carlo(MC) simulation is used for inputs uncertainty analysis of these models.Results suggest that compared with MLR and ANN,the Ensemble ANN model show better ability in the simulation of regional net irrigation requirement with smallest error and lowest uncertainty index.
出处 《农业工程学报》 EI CAS CSCD 北大核心 2012年第8期11-18,F0004,共9页 Transactions of the Chinese Society of Agricultural Engineering
基金 国家高技术研究发展计划(863计划)(2011AA100502) 国家自然科学青年基金项目(51109211) 西北农林科技大学基本科研业务费科技创新重点项目(编号QN201168)
关键词 灌溉 不确定性分析 蒙特卡洛模拟 多元线性回归模型 人工神经网络集成模型 irrigation uncertainty analysis Monte Carlo methods multiple-linear regression ensemble artificial neural networks
  • 相关文献

参考文献27

  • 1Deng X P,Shan L,Zhang H,et al.Improving agriculturalwater use efficiency in arid and semiarid areas of China[J].Agricultural Water Management,2006,80(1/3):23-40.
  • 2Kang S,Su X,Tong L,et al.The impacts of human activitieson the water–land environment of the Shiyang River basin,an arid region in northwest China[J].Hydrological Sciencesjournal,2004,49(3):1-427.
  • 3Leenhardt D,Trouvat J L,Gonzalès G,et al.Estimatingirrigation demand for water management on a regional scale:I.ADEAUMIS,a simulation platform based onbio-decisional modelling and spatial information[J].Agricultural Water Management,2004,68(3):207-232.
  • 4V?r?smarty C J,Green P,Salisbury J,et al.Global waterresources:vulnerability from climate change and populationgrowth[J].Science,2000,289(5477):284-288.
  • 5D?ll P.Impact of climate change and variability on irrigationrequirements:a global perspective[J].Climatic Change,2002,54(3):269-293.
  • 6Gómez‐Limón J A,Riesgo L.Irrigation water pricing:differential impacts on irrigated farms[J].AgriculturalEconomics,2004,31(1):47-66.
  • 7Sousa S,Martins F G,Alvim-Ferraz M,et al.Multiple linearregression and artificial neural networks based on principalcomponents to predict ozone concentrations[J].EnvironmentalModelling and Software,2007,22(1):97-103.
  • 8Ramos Nino M E,Ramirez Rodriguez C A,Clifford M N,etal.A comparison of quantitative structure activityrelationships for the effect of benzoic and cinnamic acids onListeria monocytogenes using multiple linear regression,artificial neural network and fuzzy systems[J].Journal ofApplied Microbiology,1997,82(2):168-176.
  • 9Perrone M P,Cooper L N.When network archirectures:equilibrium systems that pay attention[C]//Artificial NeuralNetworks for Speech and Vision.Chapman and Hall,NewYork,1993:126-142.
  • 10Optize D,Shaclik J.Actively searching for an effectiveneural network ensemble[J].Connection Science,1996,8(3/4):337-353.

共引文献1

同被引文献385

引证文献23

二级引证文献172

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部