径流长期预报的人工神经网络方法

提出径流长期预报的人工神经网络方法。运用神经网络的一典型模型──“反向传播”模型,以大伙房水库在补水期的径流状况作为研究对象,尝试了神经网络方法的效果。结果表明,该方法预报成功率较高,容错能力较强,可望成为径流长期预报的有效的辅助手段。     

基于BP网络的汉语普通话声调识别

研究了一种常用的模式分类器——BP神经网络,分析了BP网络的训练及识别过程,提取了能体现声调特性的特征数据组成分类特征向量,设计了具有一个隐含层的3层前馈网络作为分类器,对普通话声调样本库做了分类识别实验,分析了不同隐含层节点数的识别实验结果.实验结果表明,提取的音频特征基本有效,分类效果良好,具有一定的应用价值.     

Unsaturated resilient behavior of a natural compacted sand

Granular materials are generally used in unbound layers of road pavement structures. The mechanical behavior of these materials is widely studied with repeated load triaxial tests (RLTT) in which the elastic response is defined as the resilient behavior. Usually observed under total stress conditions, the effect of pore pressure changes during loading are not usually included in design. Further, the unbound layers frequently exist under partially saturated conditions. The influence of the unsaturated state, i.e., the suction, on the mechanical behavior, of unbound granular materials for roads has not been sufficiently studied and is generally not taken into account in models used for these materials.     

矿区岩溶地表塌陷神经网络预测研究

针对近年来某矿岩溶地表塌陷频繁发生的现象,分析确定了影响地表塌陷的主要因素,构建了矿区岩溶地表塌陷预测BP神经网络模型,以训练后的BP网络模型对矿山帷幕注浆三期工程完成后可能形成的地表塌陷区的空间分布进行预测。并针对矿山现实塌陷情况,结合各区预测塌陷危险分级结果,提出了相应的岩溶地表塌陷灾害防治措施。实践表明,所建模型的预测结果与矿区地表塌陷实际情况相符,可为矿山后续帷幕注浆工程的设计与施工提供有益借鉴,为岩溶矿区地表塌陷灾害提供预警支持。     

基于平均线性粒子群算法的人工神经网络在径流预报中的应用

人工神经网络具有很强的非线性处理能力,能够有效地模拟复杂的非线性径流预报过程。传统的基于BP训练算法的人工神经网络具有训练时间较长,容易陷于局部最优值等缺陷,本文对训练算法加以改进,分别使用平均线性粒子群,粒子群和BP算法来优化人工神经网络的各项参数,首先使用标准函数测试了3种算法的全局优化性能,然后用它们对三峡水库的入库径流进行预报,以比较它们的预报性能。结果表明,在3种算法中,平均线性粒子群算法全局寻优的速度最快,稳定性最高,基于平均线性粒子群算法的人工神经网络的径流预报的精度也最高。     

Dynamic factor analysis and artificial neural network for estimating pan evaporation at multiple stations in northern Taiwan

Abstract

Evaporation is an important reference for managers of water resources. This study proposes a hybrid model (BD) that combines back-propagation neural networks (BPNN) and dynamic factor analysis (DFA) to simultaneously precisely estimate pan evaporation at multiple meteorological stations in northern Taiwan through incorporating a large number of meteorological data sets into the estimation process. The DFA is first used to extract key meteorological factors that are highly related to pan evaporation and to establish the common trend of pan evaporation among meteorological stations. The BPNN is then trained to estimate pan evaporation with the inputs of the key meteorological factors and evaporation estimates given by the DFA. The BD model successfully inherits the advantages from the DFA and BPNN, and effectively enhances its generalization ability and estimation accuracy. The results demonstrate that the proposed BD model has good reliability and applicability in simultaneously estimating pan evaporation for multiple meteorological stations.

Citation Chang, F.J., Sun, W., and Chung, C.H., 2013. Dynamic factor analysis and artificial neural network for estimating pan evaporation at multiple stations in northern Taiwan. Hydrological Sciences Journal, 58 (4), 813–825.     

IPCC AR6报告关于气候恢复力发展的解读

文中对IPCC第六次评估报告（AR6）第二工作组（WGII）报告关于气候恢复力发展（CRD）相关内容进行解读。CRD的概念最初由IPCC第五次评估报告（AR5）引入,AR6在AR5的基础上进行了更新,正式将CRD定义为实施温室气体减缓和适应措施的过程,以支持所有人的可持续发展。新的定义更加强调了公平性原则,并且在评估内容中对不同社会选择进行了细致的描述,增强了CRD的可操作性,也强调了其紧迫性与不可逆性。报告主要从适应的角度阐述了如何在人类系统和自然系统中促成CRD的实现：城市化趋势为CRD同时带来了机遇与挑战,城市化在加剧气候变化风险的同时也会通过带动周边乡村地区的适应行动来推动CRD;保护生态系统多样性有助于保护生态系统也有助于提高其自身的恢复力,但在较高温升水平下部分适应行动将会无法实施。AR6 WGII报告评估显示,比起AR5报告的时间节点（2014年）的评估结论,当前全球CRD行动更紧迫,实行有效的、公平的应对气候变化措施迫在眉睫。     

Applying Artificial Neural Networks to Modeling the Middle Atmosphere

An artificial neural network (ANN) is used to model the middle atmosphere using a large number of TIMED/SABER limb sounding temperature profiles. A three-layer feed-forward network is chosen based on the back-propagation (BP) algorithm. Latitude, longitude, and height are chosen as the input vectors of the network while temperature is the output vector. The temperature observations during the period from 13 January through 16 March 2007, which are in the same satellite yaw, are taken as samples to train an ANN. Results suggest that the network has high quality for modeling spatial variations of temperature. Quantitative comparisons between the ANN outputs and those from the popular empirical NRLMSISE-00 model illustrate their generally consistent features and some specific differences. The NRLMSISE-00 models zonal mean temperatures are too high by ～6 K--10 K near the stratopause, and the amplitude and phase of the planetary wave number 1 activity are different in some respects from the ANN simulations above 45--50 km, suggesting improvement is needed in the NRLMSISE-00 model for more accurate simulation near and above the stratopause.     

The Impact of Grain Crushing on Road Performance

This paper presents the results of a study of grain crushing in road construction and its effect on road behaviour. Sieve analyses of field samples confirmed that grain crushing occurs during compaction of the base layer despite the good quality of aggregates used. Laboratory testing indicated that grain crushing reduces the resilient modulus of the aggregate material by half and increases the permanent deformations by onefold to threefold depending on the state of density and stresses considered. Road design and analyses undertaken to delineate the effect of grain crushing on performance showed that particle breakage yields a significant increase in rutting and longitudinal and alligator cracking of roads.     

Non-linear predictions ofAp by activity class and numerical value

Two neural network algorithms are applied to the short-term,1 to 3 days, prediction of theAp geomagnetic index. A multi-layer, back-propagation (MBP) network is used to implement a self-prediction filter forAp and this provides a forecast of the numerical value of the index. A probabilistic neural network (PNN) is used to estimate the probability distribution of theAp index, in six activity classes, and to provide a forecast of the single most likely activity class for each day. BothAp and an index of solar activity, based on the daily reports issued by the Space Environment Services Centre (Boulder), are input to the probabilistic net. It is found that the numerical forecasts of the MBP filter are most accurate at low, non-storm, levels of activity. This non-linear method provides quantitatively better estimates of activity than are produced by an existing linear prediction filter, particularly with increasing forward forecasting lag. At high levels of the solar activity index the PNN is found to anticipate storm classAp with around 60% accuracy in 1992 and 1993. Some details of the algorithms and implementation issues are described. It is concluded that interplanetary field and solar wind data will be significant components of any of the possible future developments which are discussed.