神经网络理论在河道洪水预报中的应用

本文将神经网络用于松花江干流河道汇流计算和河道洪峰水位的预报.对各种转移函数的效果进行了比较,线性函数和双正切函的精度较好超过传统的马斯京根法,其中线性转移函数最好,说明对于大江大河线性转移函数最好.由上游断面洪峰水位预报下游断面洪峰水位也取得了良好的效果.     

PNN网络在预测MCS移动中的应用

神经网络是空间数据挖掘的一种重要手段。本文运用概率神经网络(PNN网络)对1998年夏季影响青藏高原上中尺度对流系统(MCS)东移的环境物理量场的空间分布特征进行了研究，得到了高原上MCS移动方向与环境物理量场空间分布之间的关系。研究表明，使用概率神经网络预测中尺度对流系统的移动具有较好的效果，从而为研究高原上MCS东移与环境场之间的关系提供了一种新的方法和思路。     

融沉系数的人工神经网络预测方法

分析了前人关于融沉系数经验方法的研究结果,结果显示,与融沉系数关系最为密切的物性参数为液塑限、粉黏粒含量、干密度和含水量（含冰量）．为了能够综合描述诸因素与融沉系数的经验关系,以兰州黄土和青藏黏土为试验对象,得到了两种具有不同物性参数的土在不同含水量和干密度条件下的融沉系数．采用BP神经网络算法对试验数据进行学习训练,...     

三种基于神经网络的洪水实时预报方案的比较研究

在总结神经网络应用的基础上,归纳了3种基于神经网络的洪水实时预报方案。第一种是神经网络水文模型的模拟模式加模拟误差的自回归校正模型,第二种是权重系数固定的神经网络实时预报方案,第三种是权重系数自动更新的神经网络实时预报方案。采用10个不同流域的日流量资料对这3种方案进行率定和校核。比较这3种方案的实时预报精度。结果发现,第三种方案不仅预报精度要高于其他两种方案,而且比第一种方案少了一个自回归校正模型,结构简洁。本文建议采用第三种洪水实时预报方案。     

偏最小二乘回归神经网络的矿坑涌水量预测

影响矿坑充水的因素多且复杂,矿坑涌水量预测模型主要考虑降水、地表水、引水灌溉等影响因素,因变量和自变量的关系比较复杂。将偏最小二乘回归与神经网络耦合,建立了矿坑涌水预报模型。模型将自变量利用偏最小二乘回归处理,提取对因变量影响强的成分,既可以克服变量之间的相关性问题,又可以降低神经网络的输入维数,并能较好地解决非线性问题,提高了模型的学习能力和表达能力。以河南鹤壁八矿涌水量为例,建立了基于偏最小二乘回归和神经网络耦合的矿坑涌水量预测模型。计算验证表明,该类模型具有较高的预报精度和推广应用价值。     

基于改进的Elman神经网络的中长期径流预报

径流中长期预报长期以来一直都是人们关注的热点研究问题。现行的径流预报方法很多,传统的有时间序列法,多元回归分析法等,这些方法虽然简单易用,但是如果预报对象提供的样本容量偏小或者因子选择不够合理,都会造成预报精度偏差过大,难于有效的指导工程应用。鉴于此,本文提出一种改进的采用局部回归的Elman神经网络方法。并应用到凤滩水库优化调度的径流预报中。结果表明,与回归分析法、BP网络相比较,该方法不仅提高了算法的效率,而且提高了预报的精度,在径流预报中具有有效性和优越性。     

基于BP人工神经网络的枯水径流预报方案研究

介绍了BP人工神经网络的桔水径流预报方法,编制了锦屏一级水电站枯水径流预报方案.根据枯水径流预报方案的预报精度评定成果,总结了应用BP人工神经网络进行枯水径流预报的特点.研究表明基于BP人工神经网络的枯水径流预报方案能够满足水文情报预报规范,具有较好的实用性和可行性.     

BP神经网络在贵州喀斯特山区径流预报中的应用

以贵州六冲河、倒天河流域为例建立喀斯特山区径流预报BP神经网络模型。六冲河流域以七星关站丰水期流量过程为输出数据,以丰水期降雨过程、出口断面前期流量过程、蒸发量作为输入数据,倒天河流域以徐家屯站丰水期流量过程为输出因子,丰水期降雨过程、前期流量过程作为输入因子。预报结果确定性系数DC值分别为0.538、0.420。结果表明将蒸发量作为输入数据、流域面积比较大模型预报精度较大。     

改进的前馈型神经网络模型在承压水漏斗水位预报中的应用

建立了以改进Powell法优化的前馈型神经网络模型，模型既具有强大的函数逼近功能，又克服了传统神经网络优化方法的缺点。将神经网络模型用于承压水漏斗的动态水位预报，实例表明：模型预报效果较好。     

Artificial Neural Network Prediction Models for Soil Compaction and Permeability

This paper presents Artificial Neural Network (ANN) prediction models which relate permeability, maximum dry density (MDD) and optimum moisture content with classification properties of the soils. The ANN prediction models were developed from the results of classification, compaction and permeability tests, and statistical analyses. The test soils were prepared from four soil components, namely, bentonite, limestone dust, sand and gravel. These four components were blended in different proportions to form 55 different mixes. The standard Proctor compaction tests were adopted, and both the falling and constant head test methods were used in the permeability tests. The permeability, MDD and optimum moisture content (OMC) data were trained with the soil’s classification properties by using an available ANN software package. Three sets of ANN prediction models are developed, one each for the MDD, OMC and permeability (PMC). A combined ANN model is also developed to predict the values of MDD, OMC, and PMC. A comparison with the test data indicates that predictions within 95% confidence interval can be obtained from the ANN models developed. Practical applications of these prediction models and the necessary precautions for using these models are discussed in detail in this paper.     

Using and Improving Neural Network Models for Ground Settlement Prediction

Earth-fill structures such as embankments, which are constructed for the preservation of land and infrastructure, show significant amount of settlement during and after construction in lowland areas with soft grounds. Settlements are often still predicted with large uncertainty and frequently observational methods are applied using settlement monitoring results in the early stage after construction to predict the long term settlement. Most of these methods require a significant amount of measurements to enable accurate predictions. In this paper, an artificial neural network model for settlement prediction is evaluated and improved using measurement records from a test embankment in The Netherlands. Based on a learning pattern that focuses on convergence of the settlement rate, the basic model predicted settlements which were in good agreement with the measurements, when the amount of measured data used as teach data for the model exceeded a degree of consolidation of 69 %. For lower amounts of teach data the accuracy of settlement prediction was limited. To improve the accuracy of settlement prediction, it is proposed to add short-term predicted values that satisfy predefined statistical criteria of low coefficient of variance or low standard deviation to the teach data, after which the model is allowed to relearn and repredict the settlement. This procedure is repeated until all predicted values satisfy the criterion. Using the improved network model resulted in significantly better predictions. Predicted settlements were in good agreement with the measurements, even when only the measurements up to a consolidation stage of 35 % were used as initial teach data.     

应用人工神经网络BP模型预测乌江流域年平均含沙量

引入人工神经网络BP模型对流域产沙进行了定量预测。根据石坝子水文站断面以上乌江流域的土壤、地质、地貌在一定时间范围内具有相当稳定的特性，选取植被覆盖率、年降雨量、年平均流量和年汛期径流量共4个代表植被、气候和水流特性的主要因子对流域年平均含沙量进行了建模预测。优化得出的BP网络模型不仅拟合精度高，而且预测效果好，这为泥沙方面的定量研究提供了一条新的途径，也为石坝子水文站停测泥沙测验项目提供了科学依据。     

基于改进型前馈神经网络的流域产流预报模型的研究

在分析流域产流机制、影响因素和现行产流计算方法的基础上,首次取前期影响雨量、主产流历时、全过程面平均雨量和４个代表雨强计７个因子作为神经网络输入,直接以流域产流深作为神经网络输出,并针对传统ＢＰ算法的固有缺陷,采用混合ＧＮ－ＢＦＧＳ算法训练网络。实例验证了所建模型及算法的有效性和可行性。还对神经网络隐层单位数等进行了初步研究。     

基于相空间重构理论的时延神经网络应用于降雨径流预报

本文运用时延神经网络模型来模拟降雨径流过程,根据Takens相空间重构理论对前期影响雨量进行重构,并将其作为神经网络降雨输入结点.该方法可以有效改变以往神经网络输入结点主观性的问题,为正确确定神经网络输入结点提供了理论依据.通过计算实例表明,该方法的降雨径流预测精度较高.     

Natural radionuclide concentrations in thermal springs of east Algeria

The variation of the natural radionuclide concentrations depends on the chemical composition of each site. In this work, two thermal springs in the east of Algeria have been chosen to assess the activity concentration of natural radionuclide, mainly the three natural radioactive series ²³⁸U, ²³⁵U and ²³²Th, and ⁴⁰K. The high-resolution gamma ray spectroscopy was used to determine these concentrations. In these water samples, ²³⁵U, ²³⁴Th, ²¹⁰Pb, ²²⁶Ra radionuclides are less than the minimum detectable activity. The activity of ²³⁸U is dominant. The ²³⁸U activity was determined by taking the mean activity of two separate photo-peaks of daughter nuclides ²¹⁴Pb at 351.92 (37.2%) keV and ²¹⁴Bi at 609.31 (45%) keV. The measured activity concentrations of ²³⁸U in water samples obtained from the concentrations of ²¹⁴Bi and ²¹⁴Pb ranged from 0.56 ± 0.20 to 1.13 ± 0.20 Bq/L. The annual effective dose value due to the ingestion of the measured radionuclide ²³⁸U in 1 L of water, for an adult, ranged from 9.20 to 18.56 µSv.     

基于互信息量与BP神经网络的中长期径流预报方法研究

针对中长期径流预报因子的选择问题,采用互信息量方法筛选预报模型输入因子,在BP神经网络模型中,分别用均方误差和互信息量作为目标函数,衡量因子复合相关关系,优化选择最终预报因子并应用于碧流河汛期径流预报中。结果表明,基于互信息量筛选的预报因子与BP神经网络模型相结合,可有效识别多个预报因子与预报量间的复合相关性,对中长期径流预报因子的选择有很好参考价值。     

BP神经网络在灌区需水量预测中的应用

随着塔里木河下游水量逐年减少的趋势,铁千里克灌区水资源危机显的越来越严重。运用BP神经网络方法预测需水量,对灌区适时调整产业结构,保护生存和生态环境,促进区域社会经济和谐发展有重要意义。     

基于OSR-BP神经网络的丹江口秋汛期径流长期预报研究

针对丹江口流域秋汛期(9、10月)径流长期预报,为了消除网络输入的复共线性与网络训练的过拟合现象,将最优子集回归(OSR)和BP神经网络进行耦合,综合考虑训练误差和检验误差,来确定网络训练的最佳训练次数和终止务件,在此基础上提出基于OSR-BP神经网络的径流长期预报技术,并对丹江口秋汛期入库径流量进行了模拟和试报,结果表明:建立的模型稳定性良好,不论模拟还是试报精度均令人满意,特别是对预报年份中的丰枯特征均具有较好的体现.     

Geochemical characterization of oceanic basalts using Artificial Neural Network

The geochemical discriminate diagrams help to distinguish the volcanics recovered from different tectonic settings but these diagrams tend to group the ocean floor basalts (OFB) under one class i.e., as mid-oceanic ridge basalts (MORB). Hence, a method is specifically needed to identify the OFB as normal (N-MORB), enriched (E-MORB) and ocean island basalts (OIB).     

Rocket measurements of ozone concentrations in the stratosphere and mesosphere over Thumba

A rocket-borne solar middle ultraviolet photometer has been developed at the Physical Research Laboratory, Ahmedabad for the measurement of ozone concentrations at stratospheric and mesospheric heights. The instrument has now been flown successfully several times from thumba and ozone concentrations determined over an altitude range of 15 to 80 km. This paper describes the instrumentation, data analysis technique as well as the laboratory calibration procedures. Also presented are the results from four successful rocket experiments conducted during equinoctial months under an Indo-USSR collaborative programme for strato-mesospheric studies. The results show that at Thumba peak ozone concentrations vary between 2·2 and 3·1×10¹² molecules per cc and the peak altitude varies from 25 to 29 km from flight to flight. In the altitude region above about 40 km the ozone concentrations over Thumba are lower than the standard mid-latitude model values, by a factor lying between 1·5 and 2·5.