基于改进BP网络算法的隧洞围岩分类

围岩分类对指导地下工程的设计和施工具有非常重要的意义.引入人工神经网络的方法, 进行隧洞围岩分类, 在传统BP算法的基础上, 通过改进学习算法、优化传递函数和网络结构进行神经网络方法优化.采用附加动量法和学习速率自适应调整的策略改进学习算法, 使得当误差大于上临界值时, 则降低学习率, 当误差小于下临界值时, 则适当提高学习率, 这样可加快网络的训练速度, 确保网络的稳定性; 通过引入调整学习率参数, 使得传递过程更加敏感, 加快了传递函数的收敛速度, 提高了训练函数的计算精度; 通过给定隐含层节点模型的取值范围, 对网络结构进行优化, 提高了泛化精度.将改进的BP网络模型应用于广东省东深供水改造工程的隧洞围岩分类中, 分类结果与根据《水工隧洞设计规范(SL279-2002) 》的分类结果完全一致, 表明该方法具有良好的工程实用性.      

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。     

应用Kriging方法研究格尔木河流域地下水位动态观测网的优化配置

地下水动态是水文地质研究的一个重要方面，如何获满足一定精度要求全面而合理的地下水位动态资料具有现实经济效益。本文研究格尔木河流域地下水位动态测网，通过选取理想的变差函，运有Ｋｒｉｇｉｎｇ方法进行地下水位的线性无偏最优估计和计算估计误差的标准差，结合给定的允许误差限评判地下水位动态观测网的配置是否合适，并提出调整现有观测网的方案     

水库群优化调度函数的人工神经网络方法研究

提出了研究水库群优化调度函数的人工神经网络方法,并探讨了神经网络的训练参数、训练方法和训练样本的改变对网络训练和应用效果的影响。实例研究表明,模型及其算法是可行的、有效的。     

Retrieving atmospheric temperature profiles from AMSU-A data with neural networks

Back propagation neural networks are used to retrieve atmospheric temperature profiles from NOAA-16 Advanced Microwave Sounding Unit-A (AMSU-A) measurements over East Asia. The collocated radiosonde observation and AMSU-A data over land in 2002-2003 are used to train the network, and the data over land in 2004 are used to test the network. A comparison with the multi-linear regression method shows that the neural network retrieval method can significantly improve the results in all weather conditions. When an offset of 0.5 K or a noise level of ±0.2 K is added to all channels simultaneously, the increase in the overall root mean square (RMS) error is less than 0.1 K. Furthermore, an experiment is conducted to investigate the effects of the window channels on the retrieval. The results indicate that the brightness temperatures of window channels can provide significantly useful information on the temperature retrieval near the surface. Additionally, the RMS errors of the profiles retrieved with the trained neural network are compared with the errors from the International Advanced TOVS (ATOVS) Processing Package (IAPP). It is shown that the network-based algorithm can provide much better results in the experiment region and comparable results in other regions. It is also noted that the network can yield remarkably better results than IAPP at the low levels and at about the 250-hPa level in summer skies over ocean. Finally, the network-based retrieval algorithm developed herein is applied in retrieving the temperature anomalies of Typhoon Rananim from AMSU-A data.     

Reductions of PM<Subscript>2.5</Subscript> in Beijing-Tianjin-Hebei urban agglomerations during the 2008 Olympic Games

The Atmospheric Environmental Monitoring Network successfully undertook the task of monitoring the atmospheric quality of Beijing and its surrounding area during the 2008 Olympics.The results of this monitoring show that high concentrations of PM2.5 pollution exhibited a regional pattern during the monitoring period(1 June-30 October 2008).The PM2.5 mass concentrations were 53 μg m 3,66 μg m 3,and 82 μg m 3 at the background site,in Beijing,and in the Beijing-Tianjin-Hebei urban agglomerations,respectively.The PM2.5 levels were lowest during the 2008 Olympic Games(8-24 August):35 μg m 3 at the background site,42 μg m 3 in Beijing and 57 μg m 3 in the region.These levels represent decreases of 49%,48%,and 56%,respectively,compared to the prophase mean concentration before the Olympic Games.Emission control measures contributed 62%-82% of the declines observed in Beijing,and meteorological conditions represented 18%-38%.The concentration of fine particles met the goals set for a "Green Olympics."     

Statistical prediction of heavy rain in South Korea

1. Introduction In recent decades, extreme weather events seem to be growing in frequency and risk due to water-related disasters. According to the World Meteorological Or- ganization report (ISDR and WMO, 2004) on World Water Day, 22 March 2004, the economic losses caused by water-related disasters, including floods, droughts and tropical cyclones, are on an increasing trend as follows: the yearly mean in the 1970s was about 131 billion US dollars, 204 billion dollars in the 1980s, and …     

环境WiFi能量采集系统的匹配网络与整流电路设计

设计了一款针对WiFi信号的环境能量采集系统,工作频率范围从2.4 GHz到2.485 GHz.该系统采用了4倍压整流电路,并设计了从天线到整流电路的宽带匹配电路,提升了能量采集的效率.设计的宽带匹配电路在WiFi工作频率范围内,S₁₁均小于-10 dB.整流电路可将采集信号增加4倍,能有效提高RF-DC转换效率.测试结果表明,所设计的电路达到了设计要求,在-10 dBm的输入功率下,达到了40%的RF-DC转换效率,并使超级电容在30 min内采集到了257 mV的电压.     

循环神经网络在雷达临近预报中的应用

该文将循环神经网络（recurrent neural network,RNN）应用于雷达临近预报。使用预测循环神经网络（predictive RNN）架构,利用雷达历史组合反射率因子建模,给出雷达组合反射率因子未来1 h的预报结果。预测循环神经网络的核心是在长短时记忆单元（long short-term memory,LSTM）中增加时空记忆模块,能够提取雷达回波不同尺度的空间特征,配合循环神经网络架构,可以有效解决反射率因子预测问题。北京大兴雷达和广州雷达长时间序列的独立检验结果和2个强对流天气个例检验结果表明:该方法和传统的基于交叉相关法的1 h雷达外推临近预报相比,在20 dBZ和30 dBZ检验项目内,临界成功指数（CSI）可以提升0.15~0.30,命中率（POD）提高0.15~0.25,虚警率（FAR）降低0.15~0.20,该方法对反射率因子强度变化有一定预报能力。     

BP模型双样本训练方法

根据气象预报应用情况，分析ＢＰ模型训练人工神经元网络中存在的问题，并提出双样本训练方案。试验表明，采用双样本训练的网络，实际预报能力较高。