基于BP网络和RBF网络的河道浅滩演变预测模型

利用神经网络BP理论在处理非线性问题上的优势，在分析影响河道浅滩演变因素的基础上，建立了基于MATLAB的河道浅滩演变BP网络模型，实例结果表明，利用BP网络和RBF网络模型对浅滩变化进行预测是可行的，具有很好的应用价值，为河道浅滩演变预测研究提供了新方法。     

河道浅滩演变预测的人工神经网络模型

本文主要介绍利用人工神经网络对河道演变进行预测研究,并选取最佳模型对河道演变进行预测。通过对比分析发现RBF网络模型比BP神经网络模型的训练时间短,两模型的预测精度相差不多。结果证实人工神经网络在河道浅滩演变中具有较强的应用性,为河道浅滩演变预测开辟了一条新思路。     

基于BP网络的河道径流预报方法与应用

河道径流预报过程可以认为是一种复杂非线性函数关系的逼近过程。BP网络具有表达任意非线性映射的特性,因此建立了基于MATLAB神经网络工具箱的BP网络的径流预报模型。其中采用自相关函数确定网络输入层的神经元数,通过比较样本均方误差值来确定隐含层的神经元数。利用清江渔峡口以上流域1989~1995年的径流量资料对该模型进行了训练和检验,从而完成了该流域年径流量的预报,并且用多项精度评定指标对其进行了精度定量评价。结果表明:所建模型对所选流域的径流预报精度达到了乙等以上水平,具有一定的实用性。     

BP网络在大坝变形空间多测点监测模型中的应用

利用BP网络的较强函数非线性映射能力,对大坝多个测点的变形监测数据进行了仿真及预测,所建立的空间多测点BP网络模型以水位、温度、时间、测点坐标作为输入参数,以大坝变形值作为网络输出.结果表明,通过有代表性的学习样本对网络的训练,模型的拟合及预报结果能够满足精度要求,同时,与传统的统计建模方法相比,大坝变形多测点BP网络模型具有实施容易、运行速度快、误差修正方便、操作简单、运行灵活等优点.     

基于BP神经网络的降雨型滑坡预报研究

滑坡严重威胁着水库、大坝的安全运营.结合某区滑坡监测资料,采用BP神经网络数学模型,以46个强降雨诱发的滑坡点作为样本进行BP网络训练,用另外10个样本对BP网络模型进行检验.结果表明:1个检查样本的输出值与理想输出值有较大的差别,2个样本输出值与理想输出值有一定的差别,其余7个值与理想输出值吻合得非常好,总的来说,预测精度可以满足要求.     

支持向量机和BP神经网络在泥石流平均流速预测模型中的比较与应用

在综合分析多种泥石流研究方法的基础上,提出分别基于支持向量机和改进的BP神经网络模型的黏性泥石流平均流速预测方法,建立了相应的泥石流平均流速预测模型.以蒋家沟泥石流实时监测数据作为学习样本和测试样本,比较了两种模型的预测精度和适用范围.研究结果表明,泥石流样本训练阶段,支持向量机和BP神经网络均具有较高的模拟精度,BP神经网络较优于支持向量机模型,而在样本预测阶段,支持向量机的预测精度明显优于BP网络,表明支持向量机预测模型有较强的外推能力和预测计算的有效性,可以较好地描述泥石流复杂的非线性关系,为泥石流防治提供精确的科学依据.     

基于神经网络的支流入汇对干流水位变化影响研究

研究支流入汇对干流航道水位影响规律,对分析航道流态、水深变化及上、下游航运枢纽调水原则等都具有重要意义.支流入汇对干流航道水位影响是一个非线性动力学过程.以牡丹江入汇松花江为例,借助神经网络处理非线性问题的优势,在天然实测水文资料分析的基础上,建立了预测河口地区航道的BP数学模型.运用物理模型实测水文资料对BP网络模型进行学习和训练,并用训练好的模型对干流水位进行预测,计算结果表明:模型预测结果与实测值吻合良好.这为研究支流入汇对干流影响提供了新方法.     

基于免疫进化算法的BP网络模型在径流预测中的应用

在BP网络模型基础上,引入免疫进化算法,建立了基于免疫进化算法的BP网络模型。该模型在一定范围内随机生成初始权值群体,用BP网络进行训练,选择群体中具有最大适应度值的权值个体作为最优个体,应用免疫进化算法生成下一代权值群体,再用BP网络对权值群体进行训练,此迭代过程反复进行,直至达到问题求解精度要求为止。将该模型应用于新疆伊犁河雅马渡站的径流预测,并将预测结果与基本BP网络模型和基于遗传算法的模糊优选BP网络模型的预测结果进行比较,结果表明,该模型不仅精度较高,而且稳定性较好。     

流域年径流时序分析的混沌网络模型研究

以混沌理论为基础,对三峡寸滩站月平均径流量时序曲线进行了相空间重构,确定了合理的饱和关联维数.与神经网络结合,用多维相空间建立了网络学习样本和教师值,构造了混沌神经网络分析模型.结果表明:流域年径流序列具有混沌性特征;混沌网络模型预测精度要高于标准BP网络模型,预测结果的绝对误差和相对误差均小于BP网络模型.     

基于遗传神经网络的城市用水量预测研究

介绍了BP(误差反向传播算法)和GA(遗传算法)及GA-BP 3种神经网络,并以此分别对城市用水量进行预测.实验结果表明,基于GA-BP算法的神经网络方法应用于城市用水量的预测问题,能采用遗传学习算法优化BP神经网络模型的初始权重,即先利用遗传学习算法进行全局训练,再用BP算法进行精确训练,使网络收敛速度加快和避免局部极小.GA-BP神经网络在收敛速度和预测精度等方面均优于BP和GA网络,从而为未来短期城市用水量负荷的准确预测提供了新的思路与方法.     

SPATIAL AND TEMPORAL WATER QUALITY VARIABILITY IN AQUATIC HABITATS OF A CULTIVATED FLOODPLAIN

The floodplains of lowland rivers contain diverse aquatic habitats that provide valuable ecosystem services but are perturbed when intensively cultivated. Hydrologic, water chemistry and biological (fish) conditions in five aquatic habitats along the Coldwater River, Mississippi, were measured for more than 4 years: the river, two severed meanders that functioned as backwaters, a managed wetland and an ephemeral channel draining cultivated fields. Off‐channel habitats were connected to downstream regions 0.10% to 32% of the dry season and 24% to 67% of the wet season. The median temperatures for the five monitored sites ranged from 18°C to 23°C, the median total solids concentration for all sites was 135 mg L^?1, the median total phosphorus was 0.29 mg L^?1 and the median total nitrogen was 1.56 mg L^?1. Chemical and physical water quality displayed strong seasonal differences between the wet winter/spring and the dry summer/fall periods so that temporal variation consisted of gradual seasonal trends superimposed on strong diurnal variations. All off‐channel habitats exhibited periods of hypoxia and temperatures >30°C during the dry season. Between‐site gradients of water and habitat quality were strongly coupled to water depth and runoff loading. The rehabilitation of one backwater by increasing water depth and diverting agricultural runoff was associated with improved water quality and fish species richness relative to an adjacent untreated backwater. The diversion of polluted runoff and the use of water control structures to maintain greater water depth were observed to be effective management tools, but the former reduces the water supply to habitats that tend to dry up and the latter reduces connectivity. Published in 2011 by John Wiley & Sons, Ltd.     

Spatio‐temporal variation of gross CO2 and CH4 diffusive emissions from Australian reservoirs and natural aquatic ecosystems,and estimation of net reservoir emissions

Carbon dioxide (CO₂) and methane (CH₄) diffusive emissions were measured during two field surveys in Queensland and Tasmania, Australia, using the floating chamber method. Bubbling and degassing emissions in 2010 were estimated in Koombooloomba Dam reservoir using only inverted funnels and gas concentrations, respectively. A total of 14 reservoirs and 16 rivers and lakes were sampled from 2006 to 2010. Spatial variation was substantial within each water body, as well as between them. The main drivers of diffusive emission variation were physiographic region and climate, with a clear demarcation being observed between diffusive emissions from tropical Queensland and temperate Tasmania, and between the humid West Coast Range (Tasmania) and dry Central Plateau (Tasmania). Higher CO₂ and CH₄ diffusive emissions were observed during the dry season, when long water residence times would promote organic matter degradation. Estimated total gross emissions, including diffusive, bubbling and degassing emissions, for Koombooloomba Dam reservoir were about 1.5 × 10⁶ t CO₂eq km² per year, or 24 × 10⁶ t CO₂eq per year. This corresponds to a plant emission factor of 3.18 kg CO₂eq MWh^?1. Using an estimate of terrestrial emissions derived from literature data for the Tully River catchment area, rough estimated net emissions from the catchment area are about 44 kt CO₂eq per year, or 5.83 kg CO₂eq MWh^?1, which is in the lower range of the studied reservoirs.     

Call for Papers

正As the eldest and most distributed professional journal of water industry,Water Wastewater Engineering(W WE)gained very wide acceptance from the colleagues working in this field in this country since start publication in 1964.Now it is administrated by the Ministry of Construction of the People’s Republic of China and sponsored by the China Civil Engineering Society etc.     

Serial discontinuities in a Rocky mountain river. II. Distribution and abundance of trichoptera

River regulation in the headwaters and middle reaches of the Gunnison River, Colorado, significantly altered distributions and abundances of Trichoptera fauna. Twenty-five species were collected from mainstream samples, with the greatest species richness occurring at an unregulated, rhithron segment above the central reach dams. At sites immediately below the three hypolimnial-release dams and a reregulation dam, species richness was reduced 35–90 per cent and abundance > 95 per cent. Net-spinning caddisflies were the dominant trichopterans at unregulated sites; Arctopsyche grandis in the upper reaches (218 organisms, 586 mg dry mass m^?2) and Hydropsyche cockerelli, H. occidentalis and Cheumatopsyche pettiti in the lower river (9041 total organisms, 6621 mg m^?2), downstream from the last dam. The observed distributional pattern of low trichopteran densities in dam tailwaters and high hydropsychid densities at sites 60–80 km below the central reach dams is a classic expression of continuum resets and adjustments in response to stream regulation as predicted by the Serial Discontinuity Concept.     

Surveying for Water Resources

Abstract

A professional Land Surveyor (Geomatician) describes the Hydrogeologists' survey requirements of a major water resources assessment for the government of The Sultanate of Oman (1992 to 1996). The need for objective specifications is stated. Specialist terms like geoid, spheroid, Mean Sea Level are explained and how to relate spheroidal levels to the geoid. Methods like traditional survey, satellite survey, and photogrammetry are introduced. The paper encourages coordinated working for the benefit of water resource assessment and recommends employment of the professional land surveyor for major studies.     

库水波动下库岸边坡地下水浸润线解析解及误差分析

解析法是库岸边坡地下水浸润线计算中便于实际应用的方法,但该方法须基于若干假定并对潜水运动基本方程线性化后才能求解。针对各假定和线性化过程建立不同的地下水渗流数学模型,用解析法和有限元法解答上述数学模型,分析各误差大小及其规律。结果表明：库岸垂直处理带来的误差要小于方程线性化处理和不考虑非饱和渗流带来的误差,而且它们都随渗透系数变大而减小;在三峡库区库水调度情况下,假定库水位等速变化带来的误差对大多岸坡而言可以忽略;计算库岸边坡地下水浸润线时,解析法只适用于水位变化幅度相比含水层厚度较小,且几何边界规则、岩土结构简单、岩土体渗透性较好时的情况。     

Changes in Summer Irrigated Crop Area and Water Use in Southeastern Turkey from 1993 to 2002: Implications for Current and Future Water Resources

Changes in summer irrigated cropland acreage and related water use are estimated from satellite remote sensing and ancillary data in semi-arid Southeastern Turkey where traditionally dry agricultural lands are being rapidly transformed into irrigated fields with the help of water from the Euphrates-Tigris Rivers. An image classification methodology based on thresholding of Landsat NDVI images from the peak summer period reveals that the total area of summer irrigated crops has increased three-fold (from 35,000 ha to over 100,000) in the Harran Plain between 1993 and 2002. Coupled analysis of annual irrigated crop area from remote sensing and potential evapotranspiration based estimates of irrigation water requirements for cotton indicate a corresponding increase in agricultural water use from about 370 million cubic meters to over one billion cubic meters, a volume in accordance with the state estimates. These estimates have important implications for understanding the rapid changes in current agricultural withdrawals in Southeastern Turkey and form a quantitative basis for exploring the changes in future water demands in the region. For example, expansion of irrigated lands have led to a steady decrease in potential evaporation due to increased roughness and decreased humidity deficit in the Harran Plain. Assuming that the changes in future evaporation conditions will be of similar nature, water use for irrigation is expected to decrease over 40 percent in future irrigation sites. Incorporating this decrease in overall planning of the irrigation projects currently under construction should lead to improved management, and by extension, sustainability of water resources in the region.     

The Impact of Economic Development on Water Pollution: Trends and Policy Actions in Malaysia

The paper examines the impact of development activities on water pollution in Malaysia. Hence, the main objective of this paper is not just to examine the trends of development-induced water pollution around the region of the country but to know where the problems are and the policy measures taken by the government. It evaluates the probable causative relationship between problems introduced due to technology employed in water pollution control and governmental policy measures. It examines the relationship between development indicators as sources of pollution and polluted rivers over a period of 12 years. The findings of the paper have shown that despite the policy enforcement actions against the identified sources of water pollution, all the three development indicators (chosen based on those identified sources) still accounted for high percentage of river pollution in Malaysia. The findings of the paper were used to identify the central fact of the location of the problem. Some crucial conclusions of where the problems likely to be, as reflected in the findings, are: (a) the issue of interactive-effects between pollutants that many policy-makers are not aware of. This is when policy measures concentrate only on one source of water pollution; (b) the enforcement strength and/or effectiveness of policy measures themselves; (c) financial constraints to invest in appropriate technology especially sewerage systems for controlling human source of water pollution in the country; as well as those confronting small polluting industries (d) finally, lack of cooperation between government and private business firms to comply with regulatory policies for water pollution control.     

浅淡溢洪道改扩建方案与选择

溢洪道改扩建和进行溢洪道方案布置，要择优选取溢洪道进口型式、防冲消能工，以使其工程量省、施工快、运行管理方便     

Intangible Flood Damage Quantification

Flooding is a natural disaster that may cause tremendous tangibleand intangible damage to the national economy. The tangible damage assessment, i.e. the monetary value of all direct and indirect physical damages, has already been studied, whileintangible damages have not yet been taken into account. Thisarticle, therefore, is the first systematic attempt to assess bothtangible and intangible damages. The new proposed Anxiety-Productivity and Income Interrelationgship Approach (API) has been developed to quantify the intangible damage in monetary terms. The Bangkok area has been selected as the research area because several severe flood events have occurredthere over the last two decades. The 1983 Bangkok flood caused 6600 million baht in damage, according to estimates by the National Statistical Office (NSO). This article examines the totalflood damage (including the intangible damage) at different flood magnitudes. Case studies with and without flood mitigation projects are studied and compared. Furthermore, thisarticle also discusses the improvements over the conventional approach offered by the new API methodology.