Deep spatio-temporal residual neural networks for road-network-based data modeling

Recently, researchers have introduced deep learning methods such as convolutional neural networks (CNN) to model spatio-temporal data and achieved better results than those with conventional methods. However, these CNN-based models employ a grid map to represent spatial data, which is unsuitable for road-network-based data. To address this problem, we propose a deep spatio-temporal residual neural network for road-network-based data modeling (DSTR-RNet). The proposed model constructs locally-connected neural network layers (LCNR) to model road network topology and integrates residual learning to model the spatio-temporal dependency. We test the DSTR-RNet by predicting the traffic flow of Didi cab service, in an 8-km² region with 2,616 road segments in Chengdu, China. The results demonstrate that the DSTR-RNet maintains the spatial precision and topology of the road network as well as improves the prediction accuracy. We discuss the prediction errors and compare the prediction results to those of grid-based CNN models. We also explore the sensitivity of the model to its parameters; this will aid the application of this model to network-based data modeling.     

山区耕地细碎化对土地利用集约度影响——以贵州省亚鱼村为例

为探索耕地细碎化与土地利用集约度之间的关系,论文以贵州省亚鱼村为例,利用无人机高分辨率影像和农户调查数据,在对比不同通勤距离情景耕地细碎化测度模型准确性的基础上,计算农户耕地细碎化指数,并定量分析不同农户耕地细碎化水平对土地利用集约度的影响。结果表明：对比分析6种通勤距离情景耕地细碎化测度结果,发现农户耕作地块到其宅基地的道路网络距离情景下测度耕地细碎化水平准确度更高;这一情景下亚鱼村平均农户耕地细碎化指数是187.98,该村农户耕作通勤时间成本高;随着农户耕地细碎化程度加剧,农业经营中劳动力投入、资本投入和作物产值呈不同程度的下降趋势,其中资本投入中,耕地细碎化对省工性投入的影响最为显著;山区农业人口乡城迁移背景下农村细碎的耕地资源促使农户加快退出农业生产,导致耕地低效利用,甚至撂荒。     

A Trajectory-Oriented Carriageway-Based Road Network Data Model, Part 3: Implementation

IntroductionThe LRM based on the CRNMis a kind oflink-and-node LRM. As introduced in the firstpaper of the series ,the link-and-node LRMdoesnot designate any fixed reference point along aroad segment in advance but employs the nodesin the node-arc model d…     

应用KINEROS2模型对土质道路侵蚀过程的模拟

土质道路在三峡库区分布广泛,是库区泥沙重要来源地之一。在考虑道路的水沙效应基础上,结合野外调查和相关研究将三峡库区土质道路分为3级,Ⅰ级车流量大,主要为集镇之间的道路;Ⅱ级是Ⅰ级与大型村落间的道路;Ⅲ级多见于Ⅰ或Ⅱ级至农户的道路。为了有效评估其侵蚀风险、预测径流和侵蚀速率,以3级土质道路的人工降雨资料为基础,应用KINEROS2模型对土质道路的侵蚀过程进行了模拟。结果表明,径流量误差在3.6%~14.7%,侵蚀量的误差在4.5%~31.8%,对人为干扰相对较小的Ⅲ级道路模拟效果要好于Ⅰ级或Ⅱ级道路。土壤流失过程的模拟效果相对较差,初期明显低于实测值,而后期则高于实测值。     

Assessing impacts of cemeteries on water quality in an urban headwater watershed with mixed human-built infrastructure

Cemeteries are understudied integral components to urban watersheds, which provide ecosystem services but can also export nutrients, trace elements, and other contaminants to nearby water bodies. In this study, we focus on Meadowbrook Creek, an urban headwater stream in Syracuse, New York (USA), which has shown significant nitrate contributions from a local cemetery. We collected biweekly surface water samples over the course of 1 year from 2022 to 2023 for analysis of major and trace elemental concentrations including Na, Ca, Mg, K, F, Cl, sulfate, and nitrate. Here, we aim to assess the impact of various human infrastructures on urban stream water quality with a particular focus on the cemetery and nitrate. A comparison between the new dataset in this study and previously reported water chemistry data in Meadowbrook in 2012 suggests a decade-long impact of road salting and the cemetery on water quality particularly with respect to Na, Cl, and nitrate. Sulfate, Mg, Ca, and K are likely mainly geogenic. Stable nitrogen isotope data, the usage of concrete or steel vaults in the cemetery in the past 50 years, and the lack of correlation between nitrate and fluoride concentrations in stream water argue against burial decay products being a major source of nitrate to the stream. Instead, other nitrate sources that exist in the cemetery such as, fertilizer, decaying plant material, and wastewater, are more viable dominant nitrate sources. In addition, nitrate loading calculations indicate that the groundwater-connected reach, including the cemetery, acts as an annual net sink for nitrate despite the seasonally varying sink-source patterns.     

车载GPS道路信息采集和更新系统研究

介绍了车载道路信息采集和更新系统 (CRICUS)的设计和研究进展。该系统利用 3S集成技术采集道路信息并生成数字道路网数据库。初步实验表明 ,该系统的定位精度可达 1m。     

沙漠地区水泥砼路面温度梯度数学模型与仿真分析

为探讨沙漠地区水泥混凝土路面温度梯度分布,提供最大温度梯度设计参数,根据气象学和传热学原理建立了层状路面结构体温度场数学模型,采用解析理论和Newton-Naphson迭代法推导出完全依赖于气候条件下非线性边界条件路面温度场计算方法。用该方法模拟了位于内蒙古锡林浩特沙漠地区试验路温度,温度最大误差不超过2℃,计算结果和实测值基本符合。在此基础上,研究了水泥混凝土路面温度梯度分布规律及其影响因素,结果表明:路面温度梯度沿深度非线性分布,板内温度梯度变化明显。最大温度梯度随面层导热系数和面板厚度增大而减小,导热系数和面板厚度每增加1 kcal.m-1.h-1.℃-1和1 cm,最大温度梯度分别减小约0.2～0.3 ℃.cm-1和0.025～0.052 ℃.cm-1。沙漠地区最大温度梯度设计值推荐为1.01～1.09 ℃.cm-1。     

铣刨机在高速公路养护维修工程中的应用

近年来高等级公路正在我国迅速发展,养护与维修路面是一项迫切任务。以2000 DC型铣刨机为例介绍其在维修路面中的作用,以及这种铣刨机的结构、技术参数、主要性能及现场应用注意事项。      

车辆导航系统中地图匹配新算法

根据网格思想将道路网络进行分块并融合GPS所提供的定位数据,利用车辆行驶的位置、方向和实际道路网络的拓扑特性,提出一种快速实用地图匹配算法。使GPS数据实时地与G IS地图数据匹配,有效地提高车辆导航的定位精度。     

结合规划矢量的高分辨率遥感道路施工进度监测

为了有效监测道路修建项目的工程进度,提出了一种结合规划矢量的高分辨率遥感道路施工进度监测方案。首先,将矢量与高分遥感影像配准,建立道路规划缓冲区;然后,使用双边滤波增强道路信息,基于图割理论从缓冲区中提取出道路区域;最后,使用k-mean++算法得到道路分类图,并和规划矢量叠置分析,获得道路施工进度图。实验结果表明,所提方案充分结合了矢量数据和遥感影像,有效地监测道路项目的施工进度。