上海市大气污染物排放现状评价、预测及对策研究

通过对1985-2001年间上海市大气污染物排放情况的考察,分析了SO2排放强度和人均SO2排放量等大气污染物排放指标变化的原因;与国内主要城市和美国的大气污染物排放指标对比情况表明,上海市大气污染物排放强度在国内处于较低的水平,但与发达国家相比还有较大差距;采用Sigmoid模型对上海市大气污染物排放进行了预测;提出了降低大气污染物排放的几点对策.     

中国高等环保人才需求预测

通过我国社会、经济发展对环境保护要求的分析，用时序分析等数学方法，预测目标年各类高等环保人才的拥有量、需补充量及其专业结构．对于预测的结果作了补充说明     

HCl emission characteristics and BP neural networks prediction in MSW/coal co-fired fluidized beds

IntroductionWiththedepletionofspaceforlandfillingofmunicipalsolidwasteandtherisingpricesforrawmaterials ,moreandmorefluidizedbedincineratorshavebeenusedtotreatMSWduetotheprimaryadvantagesofhygieniccontrol,volumereductionandenergyrecovery .BecausetheMSWhas…     

一种移动通信基站发射天线非轴向功率密度预测模式

以移动通信基站轴向功率密度计算公式为基础,根据非轴向方向上实际监测点位和轴向方向的相对位置,对轴向功率密度计算公式参数进行系列修正,从而建立一种简单适用的移动通信基站非轴向方向上功率密度预测模式.     

基于LS-SVR、BP-ANN和MLR模型的PM10浓度预测

利用宁东能源化工基地PM10和气象监测数据,分别采用LS-SVR、BP-ANN和传统MLR模型预测PM10浓度变化。结果表明,较BP-ANN模型、MLR模型,LS-SVR模型能更好地刻画PM10浓度与各气象因素间的非线性相依关系,更准确地预测PM10浓度。     

系统安全预测的本质与组合预测

详细分析了系统安全预测的内在规律性、有效时间长度及有效性等方面的问题 ,提出了安全预测的本质就是建立系统安全可预测的思想。并针对目前的安全预测方法 ,提出了组合预测法 ,以提高安全预测的精度和准确性     

改进的BP算法在黄河下游枯季径流预测中的应用

本在黄河下游地区应用多层前向人工神经网络理论,通过改进BP算法,建立下游枯季径流预测的BP神经网络模型,使用花园口-利津水站26年的完整序列测流资料训练和检验网络并用于预测,结果表明,通过本次研究建立的BP网络模型是合理的,可靠的,它较好地反映了黄河下游的枯季径流规律,可为今后黄河流域水资源的统一调度,管理,尤其是预防黄河下游再次出现断流提供科学依据。     

机械装备故障预测系统分析

针对机械装备复杂多变的服役状态,分析了机械装备的故障预测系统,了机械装备故障预测系统的研制目的,系统特性,提出了系统的设计原则,建立了系统的总体功能结构及系统的预测模型,并探讨了故障预测系统的评价指标。     

天堂河河道治理工程水质改善预测分析

河道治理工程重在改善河道的水质,以恢复河流生态系统。本文以北京市大兴区天堂河河道治理工程为例,介绍了河道治理工程环境影响评价中的水质改善预测分析,首先分析生态需水量和供氧量是否满足河流生态需水要求,后又利用地面水环评助手软件预测了河流水质,预测分析了天堂河水质目标的可达性,旨在为以后的河道治理类工程环境影响评价提供参考。     

Prediction of Streamflow Regime and Annual Runoff for Ungauged Basins Using a Distributed Monthly Water Balance Model1

Moore, R.D. (Dan), J.W. Trubilowicz, and J.M. Buttle, 2011. Prediction of Streamflow Regime and Annual Runoff for Ungauged Basins Using a Distributed Monthly Water Balance Model. Journal of the American Water Resources Association (JAWRA) 48(1): 32‐42. DOI: 10.1111/j.1752‐1688.2011.00595.x Abstract: Prediction of streamflow in ungauged basins is a global challenge, but is particularly an issue in physiographically complex regions like British Columbia (BC), Canada. The objective of this study was to assess the accuracy of a simple water balance model that can be run using existing spatial datasets. The model was developed by modifying an existing monthly water balance model to account for interception loss from forest canopy, glacier melt, and evaporation from lakes. The model was run using monthly climate normals from the ClimateBC application, which have a horizontal resolution of 400 m. Each ClimateBC grid cell was classified as forest, open land, glacier or water surface based on provincial scale digital maps of biogeoclimatic zones, glaciers, and water. The output was monthly mean runoff from each grid cell. These values were integrated within the catchment boundaries for streams gauged by the Water Survey of Canada. Annual runoff was predicted with modest accuracy: after updating the predicted runoff by interpolating errors from neighboring gauged streams, the mean absolute error was 25.4% of the gauged value, and 52% of the streams had errors less than 20%. However, the model appears to be quite robust in distinguishing between pluvial, hybrid, and melt‐dominated hydroclimatic regimes, and therefore has promise as a tool for catchment classification.