Evaporation estimation using artificial neural networks and adaptive neuro-fuzzy inference system techniques

Evaporation, as a major component of the hydrologic cycle, plays a key role in water resources development and management in arid and semi-arid climatic regions. Although there are empirical formulas available, their performances are not all satisfactory due to the complicated nature of the evaporation process and the data availability. This paper explores evaporation estimation methods based on artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS) techniques. It has been found that ANN and ANFIS techniques have much better performances than the empirical formulas (for the test data set, ANN R² = 0.97, ANFIS R² = 0.92 and Marciano R² = 0.54). Between ANN and ANFIS, ANN model is slightly better albeit the difference is small. Although ANN and ANFIS techniques seem to be powerful, their data input selection process is quite complicated. In this research, the Gamma test (GT) has been used to tackle the problem of the best input data combination and how many data points should be used in the model calibration. More studies are needed to gain wider experience about this data selection tool and how it could be used in assessing the validation data.     

Soil loss and displacement by heavy equipment in forest road subgrading projects

Forest soil is an important component of the natural environment, and is a primary medium for many biological activities. In this study, soil loss and displacement by excavator and bulldozer （heavy equipments） were measured on cut and fills slopes of forest roads located in Mazandaran province, lran. The volumes of soil losses were estimated by prismoidal analyses of cut and fill slopes deformation between two time treatments （under subgrading and two years later） in slope classes of 30-50% and 50-70%. Weights of soil losses were calculated by multiplying the volumes of soil losses （cm^3） to the general bulk density （1.3g/cm^3）. Soil displaced area by heavy equipment was evaluated according to earth working width. Results indicated that heavy equipment has significant effect on deformation of cut slope gradient and fill slope length （p〈0.0001）. During the two-year period, the cut （p〈0.0002） and fill （p〈0.0001） slope gradients were significantly deformed in different slope classes. The average soil loss by excavator and bulldozer were 160.35 t/ha·yr and 429.09 t/ha·yr, respectively. Moreover, the soil displaced area during the subgrading process by bulldozer was greater than excavator in both two slope classes （p〈0.05）. Soil loss and displacement in forest roads can be rednced by applying powerful excavators in subgrading project, especially in steep terrains.     

特长公路隧道集中排烟方式研究

纵向通风排烟是我国长大公路隧道发生火灾时通风的主要形式,目前开始应用一种新型的特长公路隧道纵向通风集中排烟方式。本文借助CFD三维数值模拟技术,对两种排烟方式在火灾时的烟气控制效果进行了对比分析,研究了顶部设排烟道时,不同排烟开口大小和排烟口间距对隧道火灾时排烟效果的影响。研究表明：顶部设排烟道排烟较纵向通风排烟有较好的烟气控制效果,排烟口的设置间距和开口大小将影响隧道火灾时的排烟特性。     

川藏公路四川段泥石流灾害研究与治理

大量现场调查和观测发现,川藏公路四川段的泥石流灾害集中分布在4个区域,即龙胆溪泥石流区、雅江泥石流区、波戈溪泥石流区和巴塘—金沙江泥石流区。波戈溪泥石流区和巴塘—金沙江泥石流区是境内泥石流灾害最严重的地区,流域面积超过20km^2的特大型泥石流有24条。自东向西,川藏公路四川段泥石流由水石流逐渐演变为稀性泥石流;复杂的地质构造环境、高山深谷地貌特征、强烈的地震活动、高强度的降雨和冰雪融水,构成泥石流灾害显著发育的环境条件。将公路沿线泥石流形成机理概括为4种,即降雨冲击机理、强度衰减机理、冲刷切割机理和沟床拖拽机理;2003年以来采用护岸结构、速流结构、抗冲击结构、拦渣坝、消能坎等技术实施了30余个大型泥石流灾害治理工程,治理效果显著。     

遥感影像中城市道路的提取

阐述了城市遥感影像中道路提取的特点,以及当今道路特征提取的一些研究成果。根据城市道路的特点,设计了根据植被指数先提取道路两旁的植被方法,通过面积阈值和形状指数阈值剔除图斑,以及应用数学形态学,对图像进行细化,可以提取道路目标。实验结果证明这一方法的正确性。     

基于多尺度卷积神经网络的结构损伤识别研究

为了利用结构振动响应的时间多尺度特征来提升卷积神经网络识别结构损伤的能力,给出了两种用于结构损伤识别的多尺度卷积神经网络,即多尺度输入和多尺度卷积核卷积神经网络.对于多尺度输入卷积神经网络,将通过下采样和滑动平均获取的具有不同时间尺度特征的振动信号输入固定尺寸卷积核的分支卷积神经网络;对于多尺度卷积核卷积神经网络,则将...     

路面气象数值预报模型及性能检验

该文基于通用陆面模式 (CoLM) 发展了精细化路面参数数值预报模型 (BJ-ROME)。该模型可以预报路面温度、积雪厚度、积冰厚度以及积水厚度。模型不仅考虑了路面的不透水性、相对较低反照率、低热容以及高热导率等特征,还考虑了城市人为热的影响。模型采用北京市气象局快速更新循环预报系统 (BJ-RUC) 产生的气象强迫场驱动,预报时间跨度为24 h,更新时间为3 h。采用北京地区芬兰Vaisala公司路面观测站2009年8月9—24日路面温度及2010年1月3—4日积雪厚度观测结果对模型预报结果进行验证,同时进行了敏感性试验。结果表明:无论是在晴空还是降水的气象条件下,BJ-ROME均能较准确地预报路面温度极值以及日变化。BJ-ROME还可以较准确地模拟积雪厚度的最大值以及随时间变化情况。     

利用位置服务信息的车用自组织网络有效路由

根据位置服务信息,采用道路内微观路由和道路间宏观路由相结合的路由方案(MiMa),引入Dijk-stra优化算法为节点间通信提供一条具有导向功能的最佳路由。实验结果表明,该路由协议提高了数据包投递率,降低了数据端到端的传输延迟。     

移动车载激光点云的道路标线自动识别与提取

对移动车载激光测量LandMark系统获取的路面激光点云数据进行研究,结合激光点云的回波反射率、扫描角,以及量测距离等特征信息与道路标线的属性信息,提出了一种基于车载激光点云的道路标线自动识别与提取算法。从点云中提取道路标线,采用最小二乘线性最优拟合算法对提取的标线点云进行拟合,生成道路标线的CAD轮廓线,实现道路标线的自动化识别。以移动车载LandMark系统的Sick激光扫描仪获取的路面激光点云为例进行实验,实验结果表明该方法的可行性和有效性。     

RTK技术在道路工程测量中的应用研究

在介绍RTK技术基本原理和特点的基础上,结合工程测量实例,详细阐述了采用RTK测量设备在道路初测、道路定测方面中控制测量、中线放样测量上的具体应用。进而说明RTK技术在道路工程测量中的应用、管理方面有着广阔的应用前景,可为国民经济发展带来可观的经济效益和社会效益。