面向野外地质调查工作的道路提取方法研究

为弥补传统的依靠管理组织、法律、经济、教育等进行对野外地质工作安全管理工作的不足,通过百度SDK采集GPS步行轨迹数据,基于单向GPS轨迹数据的特点,进行轨迹的分割分段处理.最后利用BP神经网络算法拟合道路,通过反复实验确定BP网络的参数配置信息.并以中国地质大学西区为研究区域,提取路网信息,验证算法的有效性和实用性....     

一种基于GA-BP-MC神经网络的高铁桥墩沉降预测模型

提出一种基于马尔科夫链修正的遗传BP神经网络预测模型（GA-BP-MC）,利用遗传算法的全局寻优能力初始化BP神经网络权值和阈值,初步建立GA-BP神经网络预测模型,结合马尔科夫链的无后效性修正模型预测值,形成高精度GA-BP-MC神经网络变形预测模型。结合高铁桥墩沉降数据,分别与BP神经网络、GA-BP神经网络预测模型进行对比,结果表明,该预测模型精度最高。     

2017年江西汛期设区市城区暴雨回波特征分析

使用江西WebGIS雷达拼图和自动站雨量、雷电监测、强天气监测等数据,以及MICAPS常规天气图资料,对2017年3—7月江西汛期11个设区市26次城区暴雨过程的雷达回波特征进行分析。结果表明:2017年江西汛期共出现52日暴雨过程,其中江西11个设区市所在地城区出现26次暴雨。在这26次城区暴雨个例中,有23次伴随出现短时强降水,有3次降水比较均匀。暴雨维持时间长短不一,最长的有15 h,最短只有3 h,平均是10 h。有5次出现大风天气,21次没有大风出现。雷达回波特征主要有3种:块状(强单体、超级单体)、带状(飑线、回波带)、絮状(絮带、絮团)。这3种回波形态特征,出现率最高的是絮状回波,即比较宽、嵌有中等强度的对流单体絮带状回波带,强度40～55 dBz,出现16次,概率62%;其次是窄而长、紧密排列由强单体组成的飑线回波带,强度50～60 dBz,出现8次,概率30%;块状(强单体、超级单体)回波强度最强,中心强度达到60～70 dBz,出现2次,概率8%。     

自由测站边角交会网在工程中的应用

鉴于自由测站边角交会网具有网形规则、可靠性高、多余观测数多和观测时无需对中等优点,提出将自由测站边角交会网应用于长大隧道洞内平面控制、基坑水平位移监测和有砟轨道CPⅢ平面网建网中。研究结果表明,将自由测站边角交会网应用于上述工程中都能在一定程度上克服传统方法的不足,提高测量效率和精度,值得推广使用。     

基于人工蜂群CA模型的南京市土地利用变化模拟与预测

以南京市为例,构建人工蜂群元胞自动机（CA_ABC）模型,对2000—2007年的土地利用变化进行模拟以实现CA_ABC模型的校正,并以2007—2015年的土地利用变化为案例,验证该模型的有效性。模拟结果总体精度（OA）2007年为87.79%,2015年为80.61%;模拟结果的品质因数（FOM）2007年为21.23%,2015年为19.25%。基于CA_ABC模型和马尔可夫链预测未来城市土地总量,对南京市2025和2035年的土地利用格局进行了预测,对城市扩张和生态用地被侵占现象进行分析。模型预测结果表明,未来20年的城市扩张主要以牺牲耕地和林地为代价,2025和2035年80%的城市扩张面积来源于对耕地面积的侵占,17%的城市面积扩张是由2015年的林地转换得到的。研究表明,准确模拟、预测未来城市格局及评估城市扩张能够对生态用地侵占,以及为决策者合理规划城市、推动城市可持续发展提供帮助。     

An inter‐basin backwater overflow (the Buhai Brook and the Ezer reservoir on the Jijia River,Romania)

During the last few years, the north‐western part of Romania has been affected by catastrophic floods with most of the watercourses reaching their highest recorded discharges. This study reports the generation of a numerical terrain model and the simulation of a backwater phenomenon at elevation steps according to the volume of water accumulated at the confluence of the Buhai Brook with the Jijia River. The hydrological data are complemented by rainfall data and the careful recording of the flood behaviour during the entire period of its development. The main aim of the study is to identify the causes of the backwater phenomenon and to highlight the material damage inflicted on the town of Dorohoi. At the same time, the study uses cartographic model that was developed to establish which areas are at risk of flooding at various levels of probability. The catastrophic flood began on the Buhai Brook, a slow‐flowing stream that drains the areas to the west of the town of Dorohoi and discharged into the upstream sector of the Jijia confluence. The flood caused two types of backwater waves: one behind the bridges and the houses built on the floodplain and a second that followed the course of the main stem (Jijia) upstream from the confluence, flooding the Ezer Lake, which was created specifically to attenuate such floods. The spillway backwater phenomenon was inter‐basin as it did not occur in a single hydrographic basin. The causes of the catastrophic flash flood and of the inter‐basin backwater overflow are natural but also reflect anthropogenic influence. After the lake filled, the discharge into the Jijia was controlled and the flooding downstream was thus greatly diminished. Though fortuitous, the backwater flooding was important in mitigating the impact of the flood wave from the Jijia River. Copyright © 2013 John Wiley & Sons, Ltd.     

特大型桥梁施工GPS高程控制网技术研究

探索了采用GPS技术建立桥梁施工高程控制网的难点及关键问题,分析了GPS跨河高程传递测量方法的技术要点,结合工程实例得出了一些结论和建议。     

城市基础地理信息系统中大比例尺地形图分幅与编号

结合城市基础地理信息系统的特点和要求,在原有的地图分幅与编号方法的基础上,提出了一种新的城市基础地理信息系统的地图分幅与编号方法即数字编码法。详细介绍了该方法的规则、特点及其在计算机上的实现。     

Application of probabilistic neural network to design breakwater armor blocks

This study presents a probabilistic neural network (PNN) technique for predicting the stability number of armor blocks of breakwaters. The PNN is prepared using the experimental data of Van der Meer. The predicted stability numbers of the PNN are compared with those of previous studies, i.e. by an empirical formula and a previous neural network model. The agreement index between the measured and predicted stability numbers by PNN are better than those by the previous studies. The PNN offers a way to interpret the network's structure in the form of a probability density function and it is easy to implement. Therefore, it can be an effective tool for designers of rubble mound breakwaters.     

Matlab在矿区GPS网间接平差中的应用

针对矿区GPS网间接平差,首先,详细地分析了GPS网间接平差原理,按一定格式将GPS网中的观测数据编制成观测文件,其次,按观测文件的格式编制算法将数据读入并存储,然后用间接平差原理处理得到平差结果,最后绘制网形和误差椭圆并生成平差报告,为矿区控制网的建立和矿区生产管理提供了便利。实验验证了本文程序的实用性。