Simulation of phytoplankton biomass in Quanzhou Bay using a back propagation network model and sensitivity analysis for environmental variables

Prediction and sensitivity models,to elucidate the response of phytoplankton biomass to environmental factors in Quanzhou Bay,Fujian,China,were developed using a back propagation(BP) network.The environmental indicators of coastal phytoplankton biomass were determined and monitoring data for the bay from 2008 was used to train,test and build a three-layer BP artificial neural network with multi-input and single-output.Ten water quality parameters were used to forecast phytoplankton biomass(measured as chlorophyll-a concentration).Correlation coefficient between biomass values predicted by the model and those observed was 0.964,whilst the average relative error of the network was-3.46% and average absolute error was 10.53%.The model thus has high level of accuracy and is suitable for analysis of the influence of aquatic environmental factors on phytoplankton biomass.A global sensitivity analysis was performed to determine the influence of different environmental indicators on phytoplankton biomass.Indicators were classified according to the sensitivity of response and its risk degree.The results indicate that the parameters most relevant to phytoplankton biomass are estuary-related and include pH,sea surface temperature,sea surface salinity,chemical oxygen demand and ammonium.     

吸力内摩擦角的确定方法研究

吸力内摩擦角在非饱和土抗剪强度理论中是一个关键参数,因受设备、测试技术以及试验方法等的限制,对于其值的确定难度较大。详细地分析了土的基本物理力学性质、测试方法对吸力内摩擦角数值的影响,并通过定性分析和定量计算结合,认为干密度、含水率、内摩擦角、黏聚力与吸力内摩擦角之间存在着一定的非线性关系,因而借用人工智能--BP神经网络的方法构建了4:9:1的网络结构模型,实现了对吸力内摩擦角 的预测和计算。通过预测结果的分析可知,该模型模拟和预测的精度均较高,因此,该种方法可以应用到非饱和土吸力内摩擦角值的预测之中去。     

锦45块储层流动单元

正确地划分储层流动单元,对预测剩余油分布、调整开发方案、提高采收率都具有重要意义。采用多参数的聚类分析和模糊综合评价相结合的方法进行储层流动单元的划分,在此基础上应用BP网络技术对流动单元进行预测。研究表明,本区储层可以划分为Ⅰ、Ⅱ、Ⅲ、Ⅳ 4类流动单元:其中Ⅰ类是该区储集性能最好的储层流动单元,虽然开发程度较高,大部分井已经关闭,但个别井目前仍具有一定的生产能力;Ⅱ类是该区储集性能较好的储层流动单元,水淹的程度较低,还存有一定的剩余油,是目前油田生产的主要区域;Ⅲ类是该区储集性能较差的流动单元,开发效果一般,动用程度较差,所以是油田进一步挖潜的区域;Ⅳ类是该区储集性能最差的流动单元,原始含油性很差,因此不是剩余油分布的主要区域。对各类流动单元特征进行了精细的分析,为油田综合治理提供了详细的地质依据。     

基于神经网络对有限元强度折减法分析

基于改进BP神经网络方法对目前较为流行的强度折减法的理论进行分析。人工神经网络可以模拟人脑的思维,可以在完全不知道数据分布形式和变量之间确切关系的的情况下处理边坡各参数之间的复杂非线性映射,利用这一优势预测分析不同的理论在实际应用中的准确性。将已经通过工程手段计算出结果的数据以输入单元、隐含层和输出单元的形式代入系统进行神经网络训练,不同的屈服准则对应训练出不同的网络系统。用训练好的网络对检验数据进行预测分析,还使用这一方法预测了不同剪胀角对边坡破坏的影响程度及趋势,结果显示,对于平面应变问题,在有限元强度折减法中使用DP4和DP5准则所得到的效果较好,DP1准则的误差最大。     

BP神经网络在图像字符识别中的改进和应用

传统BP神经网络算法虽然具有良好的学习能力和容错能力,但是收敛速度慢,易陷入局部极小点等缺点制约了它的进一步发展和应用.针对这些不足,采用自适应学习率结合附加动量因子的方法可以有效缩短训练时间,加快收敛速度,同时抑制寻优算法陷入局部极小点.将该算法应用于图像字符识别系统中,通过一系列实验优化系统参数之后给出系统识别结果,表明该系统识别具有较高的准确性和鲁棒性.     

基于BP神经网络的GPS高程异常拟合研究

分析了GPS高程异常求解的常用方法,结合GPS测量和水准测量资料,用神经网络方法和二次多项式曲面拟合方法拟合高程异常,对拟合精度进行了分析比较,得出了有实用价值的结论。     

成都金沙遗址距今3000年的古气候探讨

成都金沙遗址位于成都西郊金沙村,可能是商代晚期至西周时期（约公元前11世纪–前770年）古蜀国的都邑所在地。本文分析了金沙遗址两个探方WT7908和IT8305的31个孢粉样品,探方IT8305孢粉组合表明：蕨类植物孢子占60.3%,草本被子植物花粉占24.8%,木本裸子和被子植物花粉占14.2%,水生植物花粉相对较少,仅占0.7%。蕨类植物主要以蹄盖蕨科、水龙骨科和凤尾蕨属为主,草本植物中野牡丹科占绝对优势,木本裸子和被子植物中主要以松属和桦木属为主,水生植物主要包括双星藻、鸭跖草科和香蒲属。成都平原在这个时期的气候分为两个阶段,前期阶段的气候属于亚热带温暖湿润气候,平原上生长着茂盛的草本植物和蕨类植物;后期阶段的气候虽然还属于亚热带气候,但较前期更加湿热,气温和降雨量都比前期要高。定量分析和重建了金沙遗址距今3000年的古气候：年均温17.7–19.8ºC、最热月均温21.7–28.6ºC、最冷月均温11.5–11.9ºC、年较差12.1–14.9ºC、年降雨量993.3–1113.3 mm、最大月降雨量224.6–268.1 mm、最小月降雨量6.9–14.1 mm。成都地区3000年前的年均温比现在要高1.7–2.8ºC,而年降雨量基本和现在一致。     

用BP网络预测GPS最佳外业观测时间

本文在简述影响GPS外业观测时间的因素和BP网络误差反向传播算法后,着重讲述了如何建立预测GPS外业观测时间的BP网络模型。实际数据表明该网络在实践中具有一定的可行性,能提高工作效率。     

Studies on Construction Pre-control of a Connection Aisle Between Two Neighbouring Tunnels in Shanghai by Means of 3D FEM,Neural Networks and Fuzzy Logic

The ground freezing construction technique is one of the most effective and widely applied site construction methods in soft soil areas, like Shanghai. Some elevation-inclined refrigeration pipes are arranged for the artificial freezing excavation of the Pudong-side first-storey connection aisle, which is designed to connect two adjacent tunnel lanes of Shanghai East-Fuxing-Road tunnel project. No advanced research results could be found for computing the temperature field of tunnels and aisles frozen with inclined refrigeration pipes. Anyhow the computation of the relevant temperature field is of high importance for the safe and economical excavation of the above-mentioned aisle. In this paper, a method for computing the aisle temperature field using 3D FEM is given, and the computation accuracy is verified by contrasting the computed and site measured results. The back propagation neural networks are also applied to the temperature prediction using self-developed Neural Network-Expert System software, the predicted results are also very satisfactory. The mechanism during freezing and aisle excavation will be discussed on the basis of 3D FEM simulation. The authors believe that studying the parameter-sensitivity of temperature field is very important for the optimum selection of parameter values. So, in this paper, the parameter-sensitivity of temperature field is also discussed. In order to obtain the optimum frozen wall thickness, the relation between the frozen wall thickness and the initial freezing brine temperature is studied. At the end, an excavation pre-control plan is proposed by means of fuzzy logic theory for improving the excavation safety. The research result of the current paper is very helpful for projects that will be excavated by freezing construction technique.     

40～30 ka BP中国特殊暖湿气候与环境的发现与研究过程的回顾

40～30 ka BP在过去被认为是末次冰期的间冰阶,温度稍高,但仍在冰期内.20世纪90年代西昆仑山古里雅冰芯记录研究首次指出,当时气温可能高出现代4℃,即为以前所不知的间冰期.追踪同期湖泊沉积,孢粉与古生物,黄土与沙漠地区古土壤,石灰岩洞穴中石笋,古河道,滨海地区海相沉积等多种记录,集成研究表明,当时青藏高原与西北干旱区有许多淡水大湖,降水量远比现代丰沛,导致外流水系扩大,如青海境内的黄河上游水系形成.暖湿的气候条下,森林分布区向北向西大范围扩展,华南热带喜湿热的陆均松(Dacrydium sp.)北界移至22°～24°N,表明当时热带气温高于现代2℃左右,降水量也有较大增加.长江下游石笋资料和北方半干旱、半湿润区的植物、古土壤、河道沉积资料均表示降水增加,森林覆盖度大.由于冰川和极地冰盖萎缩,海平面上升,给合若干地区地面沉降,海河下游、长江三角洲和珠江三角洲均出现相当规模的海侵.上述涉及全中国的特殊暖湿环境的形成与地球轨道运行岁差周期变化导致中低纬度日射增强,致使温度升高,季风区与西风带降水量都有显著增加关系密切,而植被改善又对温度和湿度有正反馈作用.