基于特征的城市交通网络非平面数据模型

本文通过分析交通网络特征,提出了一种适合城市交通网络数据表达与操作、基于完整交交通特征的ＧＩＳ数据模型,以弥补传统基于弧段－节点的ＧＩＳ数据模型在城市交通网络建模中的不足,并在此基础上将传统的交通网络平面图表达模式升华到非平面模式,设计了基于特征的交通网络非平面数据模型的概念建模与逻辑建模方法,为相应的数据结构与数据库实现奠定了基础。     

基于层次空间推理的交通网络行车最优路径算法

讨论了如何在贪心策略及方向策略的基础上 ,利用人类思维的层次空间推理方法建立空间启发式搜索策略 ,以提高交通网络最短路径算法的效率和适用性 ,并使行车最优路径的选择更符合人类的思维特点     

适于城市交通时序空间数据预测的层叠泛化模型

受地理过程的动态随机性影响,时序空间数据建模普遍存在先验知识缺乏与模型参数设置问题,导致单一模型难以有效地反映地理系统的整体运行状态。本文提出了一个普适性的集成学习框架,设计了基于异态集成学习的层叠泛化模型,按照组合模型最大化减小原始预测误差原则改进了层叠泛化模型平均输出的混合策略,并基于error-ambiguity decomposition对提出的层叠泛化模型的有效性进行了数学证明。基于北京市交通路网通行状态数据的实验结果表明,层叠泛化模型的均方根误差与平均绝对误差均小于单一模型;平均绝对误差方差均小于基于数理统计的混合模型,验证了层叠泛化模型在时序空间数据预测方面的优越性。     

地缘环境系统模拟研究（英文）

Geographical circumstances are the fundamental background for all kinds of geopolitical events. The geopolitical environment system(GES) refers to a system that combines both physical and anthropogenic subsystems. Research on the geopolitical environment system simulation is a key to understanding the international geopolitical phenomenon. The theory of GES arose from the integration of the traditional geopolitics and earth system sciences. As an interdisciplinary system composed of many different fields, integrated reviews and a metadata study of GES are urgently needed. This paper presents a comprehensive view into the origination and advance of the GES theory. The conceptual framework of the GES is described in detail. The methodology for simulating and forecasting geopolitical events is also provided. It is proposed that the core topics of the GES science may include, but are not limited to, issues as data acquisition technologies; principles on the interactions between multiple subsystems(or factors) at different scales; evaluating and mitigating the global geopolitical risks, including the political risks, economic risks, the social risks, the environmental risks and the technological risks; and forecasting the geopolitical events with machine learning and artificial intelligence techniques.     

重大事件发生前后的海运网络动态分析（英文）

Investigating the influence of international events on global maritime networks is a challenging task that must comprehensively incorporate geographical, political, and maritime sciences. Understanding global maritime network dynamics is an initial and critical step in this investigation. This study proposes an automatic identification system(AIS)-based approach to understanding maritime network dynamics before and after international events. In this approach, a spatiotemporal modeling method is introduced to measure the similarity in shipping trends before and after international events. Then, a spatiotemporal analytic framework is proposed to understand the maritime network dynamics by grouping similar situation, and assessing possible indirect effects within a network. Finally, three case studies of international events, military conflict, lifted economic sanctions, and government elections, were used to investigate the observed network dynamics possibly affected by international events. The results indicate that container, tanker, and bulk shipping between India and its connected countries all declined more than 69% after military conflicts between India and Pakistan in August 2015. Tanker shipping between Iran and the United Arab Emirates increased 51% after economic sanctions on Iran were lifted. Container shipping between Sri Lanka and Singapore, Malaysia, and India increased more than 74% after the general election in Sri Lanka. These investigations demonstrate the feasibility of the proposed approach in assessing the possible effects of international events on maritime network dynamics.     

新年寄语

新年伊始,万象更新。伴着祖国大江南北的漫天瑞雪和北京冬奥的轻盈脚步,2022年如期而至。作为地球信息科学学术思想交流的优秀平台,《地球信息科学学报》已走过25个春秋。多年以来,学报始终秉承"理论方法技术创新+地理综合分析应用"的办刊宗旨,挺立潮头,努力营造宽松的地球信息科学新思想、新理论、新方法交流环境,侧重以地球信息科学理论方法创新驱动多学科发展,发挥中国科学院地理科学与资源研究所的多学科综合优势,推动地理学、测绘科学、计算机科学等学科的交叉与融合,形成鲜明的办刊特色。