基于多源数据的主体功能区划分方法——以广州市为例     

罗伟玲  王艳阳  张恒 《热带地理》2020,40(1):110-118

以广州市为例,基于城市感知数据、遥感影像等多源数据,采用卷积神经网络对遥感影像进行了语义提取,将提取结果与兴趣点（Points of Interest）样方密度的功能用地识别结果进行补充校验,根据政策和规划文件建立功能用地与主体功能区之间的关联,利用信息熵分析广州市功能用地混合程度,以辅助判别主体功能区,最终得到广州市主体功能区划分结果。将划分结果与《广州市主体功能区规划（2008—2020年）》和《广州市城市总体规划（2017—2035年）》草案对比验证,结果表明文章所提出的方法精准度较高,并能体现广州市空间格局形态,反映主体功能区实际分布情况。  相似文献   

新冠肺炎疫情扩散与人口流动的空间关系及对中国城市公共卫生分类治理启示     

向云波  王圣云 《热带地理》2020,40(3):408-421

人口流动影响新冠肺炎疫情传播与风险扩散。基于百度迁徙大数据和各省市区卫生健康委员会数据，结合地理信息技术，研究了2020年1月1日至3月5日136个城市新冠肺炎疫情扩散与武汉市人口流出的空间关系及其对我国城市公共卫生治理启示。研究表明：1）中国新冠肺炎疫情扩散过程具有阶段性特征，经历了疫情发生与隐性扩散、快速扩散与暴发、扩散遏制和扩散衰减4个阶段。2）研究时间段武汉市人口主要流向湖北省境内以及周边省市和北京、上海、广州、深圳等一线城市，具有地理邻近性和倾向区域中心城市的人口流入特征。受地理距离、时间成本、社会经济联系、境外输入等因素的影响，新冠肺炎疫情空间分布的不平衡性明显，长江中游城市群、京津冀城市群、长三角城市群、粤港澳大湾区和成渝城市群成为新冠肺炎疫情集中分布的重点区域，一些重点出入境口岸城市的新冠疫情扩散风险较大。3）新冠肺炎疫情扩散与人口流出之间具有较强的正向等级相关性。两者之间的空间关系可以分为8种调控类型，近90%的城市具有人口流入多、确诊病例数高或人口流入少、确诊病例数低的特征。其中，人口流入多、确诊病例数高的城市主要集中分布在湖北省境内以及中国重点城市群的中心城市，其防控压力来自人口流入多、确诊病例数高带来的疫情扩散风险；而人口流入少、确诊病例数低的城市分布较为分散，其防控的难点在于提高防控对策的精准性。我国疫情防控取得了显著成效，但随着时间的演进全球疫情形势反弹的不确定性仍然存在，外防输入、内防反弹的压力依然很重，现阶段乃至未来一段时期，疫情防控将伴随中国经济社会发展成为新常态。建议针对8种调控类型，从人口流动、交通和资源等引导与管控方面分类提出精细化的疫情防控策略，提升城市公共卫生治理能力。  相似文献   

功能疏解背景下京津冀中部核心区产业投资网络演化研究     

刘骁啸  吴康 《地理科学进展》2020,39(12):1972-1984

非首都功能疏解作为京津冀协同发展战略的核心,对解决北京大城市病、实现京津冀可持续发展具有重要意义。论文构建了一个“四位一体”的产业投资网络演化分析框架,以京津冀中部核心区为研究对象,利用工商企业投资大数据测度了非首都功能的3类重点行业在2010、2014、2018年的资本流动特征,并从“节点—路径—格局”3个层面分析了功能疏解背景下产业投资网络演化过程。研究结果表明,非首都功能疏解背景下,北京市各行业对外投资增强,投资集聚中心逐渐向外围转移,但不同行业演化格局存在差异。制造业呈现由邻近扩散向等级扩散转变的演化路径,并向着多中心格局发展;批发零售业在资本净流动层面显示出扩散特征,在骨干路径层面呈现集聚现象,分布格局由北京单极放射状向京津双核联动演化;交通运输仓储和物流业向郊区物流园区所在地集聚,但网络整体发育滞后。研究结果能够为科学认识首都功能疏解情况、了解中部核心区产业结构及产业发展的变动态势提供参考。  相似文献   

Correspondence between the large volcanic eruptions and ENSO events over AD 1525–2000     

Fang  Xiuqi  Zheng  Xue  Zhang  Xing 《地理学报(英文版)》2020,30(1):103-118

ENSO is an interannual mode which may be affected by external forcing, such as volcanic eruptions. Based on the reconstructed volcanic eruptions chronology and ENSO sequences, both 195 large volcanic eruptions(VEI≥4) and 398 ENSO(El Ni?o and La Ni?a) events were extracted from 1525 to 2000. An analysis of the correspondence between the large volcanic eruptions and ENSO events was performed by matching the large volcanic eruptions with the types and magnitudes of ENSO events present in the 0–2 years after the eruptions. The results show the following:(1) The percentages of ENSO events within the 3 years after the large eruptions had increased to 68.3% from 31.7% compared with those with no-eruptions in the previous 0–2 years. In addition, the ratio of El Ni?o to La Ni?a events turned from 2:3 to 1:1, and more El Ni?o events occurred in the 0 year after eruptions in the low-latitudes of the Northern Hemisphere and in the tropics but more La Ni?a events occurred in the 0 year after in the high-latitudes of the Northern Hemisphere and the Southern Hemisphere.(2) After the eruptions, the weak(W) El Ni?o events had increased by 8 percentage points and the very strong(VS) El Ni?o events had decreased by 10 percentage points; conversely, there was a decrease by 15 percentage points of the weak La Ni?a events and an increase by 11.4 percentage points of the very strong La Ni?a events. Specifically, the percentages of strong La Ni?a events increased to a peak at 1(+1) year after the eruptions.(3) The percentage of eruptions followed by single-year ENSO was the greatest. The percentage of ENSO events that occurred in the consecutive 2 years following an eruption was approximately equal to the percentage of events that occurred consecutively 3 years following an eruption, and both sets of ENSO magnitudes showed a decreasing trend.  相似文献   

地理大数据挖掘——目标、内涵与研究问题     

裴韬  宋辞  郭思慧  舒华  刘亚溪  杜云艳  马廷  周成虎 《地理学报(英文版)》2020,30(2):251-266

  相似文献   

Identifying primary public transit corridors using multi-source big transit data     

Tong Zhang  Yicong Li  Hui Yang  Chenrong Cui  Jing Li  Qinghua Qiao 《International journal of geographical information science》2020,34(6):1137-1161

ABSTRACT

Effective public transit planning needs to address realistic travel demands, which can be illustrated by corridors across major residential areas and activity centers. It is vital to identify public transit corridors that contain the most significant transit travel demand patterns. We propose a two-stage approach to discover primary public transit corridors at high spatio-temporal resolutions using massive real-world smart card and bus trajectory data, which manifest rich transit demand patterns over space and time. The first stage was to reconstruct chained trips for individual passengers using multi-source massive public transit data. In the second stage, a shared-flow clustering algorithm was developed to identify public transit corridors based on reconstructed individual transit trips. The proposed approach was evaluated using transit data collected in Shenzhen, China. Experimental results demonstrated that the proposed approach is a practical tool for extracting time-varying corridors for many potential applications, such as transit planning and management.  相似文献   

Pedestrian network generation based on crowdsourced tracking data     

Xue Yang  Chang Ren  Yang Chen  Zhong Xie  Qingquan Li 《International journal of geographical information science》2020,34(5):1051-1074

ABSTRACT

Pedestrian networks play an important role in various applications, such as pedestrian navigation services and mobility modeling. This paper presents a novel method to extract pedestrian networks from crowdsourced tracking data based on a two-layer framework. This framework includes a walking pattern classification layer and a pedestrian network generation layer. In the first layer, we propose a multi-scale fractal dimension (MFD) algorithm in order to recognize the two different types of walking patterns: walking with a clear destination (WCD) or walking without a clear destination (WOCD). In the second layer, we generate the pedestrian network by combining the pedestrian regions and pedestrian paths. The pedestrian regions are extracted based on a modified connected component analysis (CCA) algorithm from the WOCD traces. We generate the pedestrian paths using a kernel density estimation (KDE)-based point clustering algorithm from the WCD traces. The pedestrian network generation results using two actual crowdsourced datasets show that the proposed method has good performance in both geometrical correctness and topological correctness.  相似文献   

An overview of clustering methods for geo-referenced time series: from one-way clustering to co- and tri-clustering     

Xiaojing Wu  Raul Zurita-Milla  Changqing Song 《International journal of geographical information science》2020,34(9):1822-1848

  相似文献   

无定河下游全新世古洪水研究          下载免费PDF全文

李晓刚  黄春长  庞奖励 《干旱区地理》2020,43(2):380-387

对无定河流域野外考察，在其下游苏家圪坨（SJGT）地点发现夹有古洪水滞流沉积物（SWD）的全新世剖面。古洪水SWD厚度30 cm，具有平行微薄层理特征，且直接覆盖在东汉文化层之上。室内分析结果表明古洪水SWD有着与2012年洪水SWD相似的沉积学特征，以粗粉沙为主，分选良好，磁化率和烧失量较小，说明它记录了一次无定河下游的大洪水事件。文化层光释光（OSL）测年结果显示该次古洪水事件发生在1 900~1 700 a BP。古洪水洪峰水位和洪峰流量分别为765.9 m和10 530 m³·s^-1。同时利用2012年洪水洪痕水位验证，在同一断面用相同参数恢复洪峰流量为1 030 m³·s^-1，实测洪峰流量为1 000 m³·s^-1，误差为3.09%，说明古洪水洪峰流量恢复结果合理可靠。研究结果延长了无定河下游洪水数据序列，对水资源、水能源的开发利用提供了科学依据。  相似文献   

ARIMA-LSTM组合模型在基于SPI干旱预测中的应用——以青海省为例          下载免费PDF全文

张建海  张棋  许德合  丁严 《干旱区地理》2020,43(4):1004-1013

开展干旱预测是有效应对干旱风险的前提基础。利用1958—2017年青海省38个气象站点逐日降水量数据计算多尺度标准化降水指数（SPI）,并建立了SPI序列自回归移动平均模型（ARIMA）、长短时记忆神经网络模型（LSTM）和基于二者优点提出的ARIMA-LSTM组合模型;对模型参数进行率定和验证后,利用所建立的模型,以西宁站点为例,对多尺度SPI值进行预测,借助均方根误差（RMSE）、平均绝对百分比误差（MAPE）和决定系数R²对所有预测模型的有效性进行判定。结果表明：ARIMA-LSTM组合模型在SPI1和SPI12的RMSE值分别为0.159 7和0.181 0,均低于ARIMA模型的1.265 4和0.293 3,说明ARIMA模型与ARIMA-LSTM组合模型对SPI的预测精度都与时间尺度有关,ARIMA模型的预测精度随着时间尺度的增加而逐渐提高;结合GIS并利用实测数据与模型的预测数据相比较说明ARIMA-LSTM组合模型相比于单一ARIMA模型的预测精度更高,且能够很好拟合不同时间尺度的SPI值。  相似文献