注： 论文选读转载自Annals of GIS微信订阅号。

1. 我们可以使用推特上的数据预测总统大选吗? 一种综合建模方法

Can We Forecast Presidential Election Using Twitter Data? An Integrative Modelling Approach

Ruowei Liu, Xiaobai Yao, Chenxiao Guo & Xuebin Wei

政治选举预测已经获得广泛关注。传统的政治学选举预测模型一般将民意调查中的偏好和国家经济增长作为预测因素，然而，在空间或时间上密集的投票也是重要的影响因素。近几十年来，指数级增长的社交媒体数据吸引了众多学科的研究兴趣。现有研究表明，社交媒体数据极有可能反映政治格局。尤其是推特数据，可以被广泛用于民众情感分析，以此来预测世界各地的选举结果。然而，以往的研究通常是数据驱动的，缺乏扎实的理论基础，推理过程过于简单化。这些研究大多将推特情感简单、直接地与选举结果联系起来，实际上这很难被视为预测。本研究利用政治学预测模型，并从两个方面对其进行修正，制定了更加合理可信的理论方法。首先，我们使用推特情感来代替投票数据；第二，我们将传统政治学模型从国家尺度转变为县级尺度——最优的投票空间尺度。本研究提出的模型使用了基于推特情感的独立支持率变量和经济增长相关变量，因变量为实际投票结果。使用了乔治亚州2016年的美国总统选举数据测试该模型，结果表明初步的模型真实有效，准确率达到81%，基于推特情感的支持率是第二重要的因素。

关键词：选举预测、情感分析、推特、政治学、机器学习、基于位置的社交媒体数据

To cite this article:

Ruowei Liu, Xiaobai Yao, Chenxiao Guo & Xuebin Wei. 2020. Can We Forecast Presidential Election Using Twitter Data? An Integrative Modelling Approach. Annals of GIS. doi：10.1080/19475683.2020.1829704

Abstract

Forecasting political elections has attracted a lot of attention. Traditional election forecasting models in political science generally take preference in poll surveys and economic growth at the national level as the predictive factors. However, spatially or temporally dense polling has always been expensive. In the recent decades, the exponential growth of social media has drawn enormous research interests from various disciplines. Existing studies suggest that social media data have the potential to reflect the political landscape. Particularly, Twitter data have been extensively used for sentiment analysis to predict election outcomes around the world. However, previous studies have typically been data-driven and the reasoning process was oversimplified without robust theoretical foundations. Most of the studies correlate twitter sentiment directly and solely with the election results which can hardly be regarded as predictions. To develop a more theoretically plausible approach this study draws on political science prediction models and modifies them in two aspects. First, our approach uses Twitter sentiment to replace polling data. Second, we transform traditional political science models from the national level to the county level, the finest spatial level of voting counts. The proposed model has independent variables of support rate based on Twitter sentiment and variables related to economic growth. The dependent variable is the actual voting result. The 2016 U.S. presidential election data in Georgia is used to train the model. Results show that the proposed modely is effective with the accuracy of 81% and the support rate based on Twitter sentiment ranks the second most important feature.

Keywords: election forecasting; sentiment analysis; Twitter; political science; machine learning; location-based social media date

2. 使用轨迹相似性来预测船舶位置和海上交通量

摘要

海上交通预测是提高港口作业效率和安全性的关键任务，尤其在拥挤的地区。大量包含船只运动和特征信息的自动识别系统（AIS）数据不断地从船舶传输到接收者。这些历史AIS数据可用于船只的运动分析。本文提出了一种新颖的基于点的模型，从而根据AIS测量数据提取船舶轨迹来进行位置和交通预测。位置预测程序是基于对历史AIS数据的相似性分析设置的。该模型已应用于美国佐治亚州海峡的数百条船舶轨迹真实数据集。在10分钟，20分钟和30分钟的相关结果分别为0.9976、0.9887和0.9794，这表明预测坐标与实际坐标之间具有足够的对应关系。交通量预测程序考虑了在不同时间间隔内新船出现在感兴趣区域（AoI）内的可能性。并将 Sorenson相似性指数（SSI）用于衡量流量预测模型的准确性。 10、20和30分钟时间间隔的SSI分别为70％，66％和59％，这证实了该模型在预测AoI内部热点时的稳定性。

关键词：位置预测；交通预测；轨迹；相似性度量；自动识别系统数据

Prediction of vessels locations and maritime traffic using similarity measurement of trajectory

ABSTRACT

Maritime traffic prediction is a crucial task for increasing the efficiency of port operations and safety, especially in congested regions. A huge amount of automatic identification system (AIS) data is constantly transmitting from vessels to receivers that contain information about vessels’ movements and characteristics. These historical AIS data can be utilized in movement analyses of vessels. This paper proposes a novel pointbased model for location and traffic prediction using vessels’ trajectories adapted from AIS measures.The location prediction procedure is setup based on similarity analysis of historical AIS data. The model is applied to a real dataset of hundreds of vessels’ trajectories in the Strait of Georgia, USA. The correlation results of 0.9976, 0.9887, and 0.9794 for the next 10, 20, and 30 minutes, respectively, imply sufficient correspondence between predicted and actual coordinates. The traffic prediction procedure considers the probability of the appearance of new vessels inside an area of interest (AoI) at different time intervals. The Sorenson similarity index (SSI) is used to measure the accuracy of the traffic prediction model. The SSIs for time intervals of 10, 20, and 30 minutes are 70%, 66%, and 59%, respectively, which show the robustness of the model to predict hot spots inside the AoI.

KEYWORDS: location prediction; traffic prediction; trajectory; similarity measurement; AIS data

Drivers’ range anxiety and cost of new EV chargers in Amsterdam: a scenario-based optimization approach

3. 用于解决阿姆斯特丹驾驶员对于电动汽车里程的焦虑和新充电桩建设成本问题的一种基于情景的优化方法

To cite this article：

Bardia Mashhoodi & Nils van der Blij. 2020. Drivers’ range anxiety and cost of new EV chargers in Amsterdam: a scenario-based optimization approach. Annals of GIS.

https://doi.org/10.1080/19475683.2020.1848921

由于荷兰电动汽车（EV）数量的急剧增长，并且《荷兰气候协议》的目标是鼓励人们使用电动汽车出行，因此在未来几十年中，需要新增大量的EV充电设施。对于即将成为EV驾驶员的人们来说，他们对于EV充电基础设施的有效规划和汽车里程的焦虑十分严重。本研究旨在评估在阿姆斯特丹东部的五种里程焦虑情景下建设新充电基础设施的成本。基于有关汽车登记、现有电动汽车充电桩和变电站的地理数据，使用线性整数规划优化模型，可以得出以下结论：如果驾驶员在使用充电设施之前使用了90％的电量，则现有的充电基础设施仅需增加31％即可满足近七倍电动汽车的充电需求，这是欧盟（EU）通过立法对替代燃料基础设施部署设定的门槛；如果驾驶员仅使用了30％的电量，那么充电基础设施的增长将不可避免地达到167％（成本将近500万欧元）。另一方面，在任何里程焦虑情景下，如果两次充电时间间隔增加1天，则总成本将降低30％以上。我们对这些发现进行了讨论，并提出了两种政策方法：（1）信息技术方法；（2）基于欧盟关于能源效率和替代燃料基础设施部署立法的需求响应方法。

关键词：电动汽车；充电基础设施；线性整数规划；里程焦虑；空间优化；荷兰

Abstract

Due to the sharp growth in the adaptation of electric vehicles (EV) in the Netherlands and the objectives of the Dutch Climate Accord is to encourage electric mobility, in the coming decades a substantial number of new EV charging facilities needs to be provided. Efficient planning of EV charging infrastructure is coupled with the notion of range anxiety, which is likely to be severely high in case of soon-to-be EV drivers. This study aims to estimate the cost of developing a new charging infrastructure under five scenarios of range anxiety in Amsterdam East. Employing a Linear Integer Programming optimization model, on the basis of geographic data on car registration, existing EV chargers, and electricity substations, it is obtained that if drivers use 90% of their battery before using a charging facility, the existing charging infrastructure needs to be expanded by only 31% to accommodate almost seven times larger number of EVs – the threshold set by the European Union (EU) legislation on the deployment of alternative fuel infrastructure. If drivers use only 30% of the batteries; however, an increase of 167% in infrastructure is inevitable (accounting for almost five million euro of cost). Second, at any point along the range anxiety spectrum, if the interval between charging session increases for 1 day, the overall cost decreases by more than 30%. These findings are discussed, and two policy approaches are proposed: (1) information technology approach; (2) demand-response approach, on the basis of EU legislation on energy efficiency and deployment of alternative fuel infrastructure.

KEYWORDS: Electric vehicle; Charging infrastructure; Linear integer programming; Range anxiety; Spatial optimization; Netherlands

4. GIS-BASED MULTI-CRITERIA ANALYSIS OF THE SUITABILITY OF WESTERN SIBERIAN FOREST-STEPPE LANDS

基于GIS对西伯利亚西部森林草原土地适宜性进行多尺度分析

本项工作的主要目的是评估西伯利亚西部种植其主要农作物春小麦的土地适宜性。以新西伯利亚地区科切内夫斯基区米尔内市土地利用试验田为研究对象，建立了土地适宜性评估算法。为了在专家知识的基础上评估土地的适宜性，我们选取了已知且具体的与地势和土壤相关的标准作为评估依据。由于缺少有关所研究土地的地势和地形的资料，我们基于无人机(UAV)高分辨率数字航空摄影的结果建立地理空间数据库。利用GIS工具确定了微地形层次的基本面。分析了两种最常用的获得标准权重的方法:层次分析法和直接排序法，并在一定条件下建立了这两种方法之间的联系。为了评估土地适宜性，我们使用GIS-MCDA (Multiple-Criteria Decision Analysis)方法的加权线性组合，对所选土地的适宜性指标进行了计算。根据适宜性指标值，将所有土地按照联合国粮食及农业组织所确定的类别进行划分，并绘制了一幅土地适宜性图，对春小麦播种适宜性进行了评估。

关键词：地理信息系统、春小麦、空间数据库、多尺度分析、土地适宜性

https://doi.org/10.1080/19475683.2020.1848920

Abstract

The main purpose of this work is to assess the suitability of land for cultivation of the main agricultural crop of Western Siberia, namely spring wheat. The algorithm of land suitability assessment was developed on the territory of the test plot of land-use of CJSC Mirny, Kochenevsky District, Novosibirsk Region. For assessment of land suitability on the basis of expert knowledge, criteria related to relief and soil, not only known but also specific, inherent in the area under consideration, have been identified. In the absence of information on the topography and relief of the territory under consideration, the spatial database of geodata was created based on the results of high-resolution digital aerial photography from an unmanned aerial vehicle (UAV). Elementary surfaces (ESs) at the micro-relief level have been drmined with the help of GIS tools. Two most popular methods of obtaining criterion weights have been analysed: Analytic Hierarchy Process and the direct ranking method, and under certain conditions, a connection between these methods have been established. To assess the land suitability, the land suitability indices of selected ESs were calculated using GIS-MCDA (Multiple-Criteria Decision Analysis) method Weighted linear combination. Based on the value of land suitability index for all ESs, belonging to a certain suitability class according to FAO classification has been established. A map of land suitability with an assessment of spring wheat sowing expediency was obtained.

Keywords: Geographic information systems; spring wheat; spatial database; multi-criteria analysis; land suitability

5. 对加纳中部金塔姆波健康和人口监测区疟疾死亡情况的地理空间分析

Geospatial analysis of malaria mortality in the kintampo health and demographic surveillance area of central Ghana

Kenneth Wiru, Felix Boakye Oppong, Stephaney Gyaase, Oscar Agyei, Sulemana Watara Abubakari,  Seeba Amenga-Etego,  Charles Zandoh & Kwaku Poku Asante

在大多数情况下，疟疾仍然是对人类生存的一种威胁。疟疾死亡的地理空间分析对于确定高疾病负担群集以及难以获得疟疾护理的地区至关重要，便于对其进行有针对性的控制并采取补救措施。本研究对2005年至2017年记录的1301例疟疾死亡病例及其发生地点的全球定位系统（GPS）位置进行分析，从而确定了加纳中部金塔姆坡地区疟疾死亡情况的空间和时空群集。我们使用了Geoda（版本1.12.1.161）中的空间经验贝叶斯平滑方法对疟疾死亡风险进行了平滑和映射，并使用SaTScan（版本9.6）进行了空间和时空群集分析。该地区的所有年龄段的人口疟疾死亡率在1.2‰至2.4‰之间，五岁以下儿童的疟疾死亡率在3.3‰至6.0‰之间。在对所有年龄段疟疾死亡情况的空间分析中检测到两个空间群集，但只有主要群集（RR = 1.42，p = 0.001）具有统计学意义。我们在该空间群集中还发现了两个具有统计学意义的全年龄段疟疾死亡时空群集。主要群集包含2006年至2011年之间的五个分区，相对危险度为2.12（p <0.001），而相对危险度为2.47（p <0.001）的次要群集则包含2005年至2010年之间的四个分区。同样，五岁以下疟疾死亡情况只有主要空间群集具有统计学意义（RR = 1.36，p = 0.024），在该空间群集中发现了三个五岁以下疟疾死亡时空群集。主要和次要群集具有统计学意义，而第一个次要群集具有临界意义。主要群集（RR = 4.49，p = 0.002）包含2006年至2007年之间的两个分区。第一个次要群集（RR = 2.21，P = 0.005）覆盖了2006年至2011年之间的四个分区，而第二个次要群集（RR = 2.51，p = 0.003）涵盖了2008年至2013年之间的两个分区。最终，我们的分析确定了研究背景下大量疟疾死亡的空间和时空群集，这有助于制定和实施针对性的疟疾控制干预措施。

Abstract

Malaria remains a menace to the existence of humanity in most contexts. Geospatial analysis of malaria mortality is crucial to identifying clusters of high disease burden and areas with limited access to malaria care for targeted control and remedial interventions. This study identified spatial and space-time clusters of malaria mortality in the Kintampo area of central Ghana. We used 1301 malaria deaths archived from 2005 to 2017 and Global Positioning System (GPS) point locations of the sub-districts in which these deaths occurred for our analysis. Mortality risks were smoothed and mapped using the Spatial Empirical Bayesian smoothing technique in Geoda (version 1.12.1.161) whereas spatial and spatio-temporal clustering analysis was done using SaTScan (version 9.6). Malaria mortality risks ranged between 1.2 and 2.4 deaths per 1000 population for persons of all ages and between 3.3 and 6.0 deaths per 1000 population for children under five years of age by sub-district.

Two spatial clusters were detected for all-age malaria mortality with only the primary cluster (RR = 1.42, p = 0.001) being statistically significant. Also, two statistically significant space-time clusters were detected for all-age malaria mortality in the study area. The most likely cluster occurred between 2006 and 2011 in five sub-districts with a relative risk of 2.12 (p < 0.001) whilst the secondary cluster which had a relative risk of 2.47 (p < 0.001) occurred between 2005 and 2010 in four sub-districts. Similarly, only the most likely spatial cluster of under-five malaria mortality was statistically significant (RR = 1.36, p = 0.024). Furthermore, three spatio-temporal clusters of under-five malaria mortality were detected in the study area. The primary and second secondary clusters were statistically significant whilst the first secondary cluster had borderline significance. The primary cluster (RR = 4.49, p = 0.002) occurred in two sub-districts between 2006 and 2007. The first secondary cluster (RR = 2.21, P = 0.005) covered four sub-districts and was detected between 2006 and 2011 whereas the second secondary cluster (RR = 2.51, p = 0.003) covered two sub-districts between 2008 and 2013. Ultimately, our analysis identified a number of substantial spatial and space-time clusters of malaria mortality in the study context, which could aid in the strategic planning, implementation and monitoring of targeted malaria control interventions.

https://www.tandfonline.com/doi/full/10.1080/19475683.2020.1853231

6. 以河漫滩可持续管理为背景的河流景观动态预测模型：一种地理空间方法

Prediction modelling of riverine landscape dynamics in the context of sustainable management of floodplain: a Geospatial approach

河漫滩作为一个多元的河流景观元素，其可持续性为研究人为干扰与生态环境恶化的复杂相互作用提供了理想的研究环境。如今，由于部分不可持续的土地利用方式，这些河漫滩正在不断地退化和碎片化。本研究使用监督分类法（极大似然估计法）分析了从1998至2018年土地利用及土地覆盖的时空变化情况，并使用元胞自动机-人工神经元网络（CA-ANN）模型以及QGIS软件的土地利用变化评价模块（MOLUSCE）插件，对从2018至2038年恒河下游土地利用和土地覆盖的动态变化情况进行了模拟和预测，以分析各种自然和社会经济因素对未来河流景观动态的影响。研究结果表明：从1998至2018年，农用地、沙地和内河水体面积呈现降低的趋势，分别减少了15.75%、5.71%和1.95%，而果树林、农休耕地和裸地面积在同期呈上升趋势，分别增加了7.94%、7.92%和5.69%。我们使用模拟模型预测了一个直到2038年都与之前相似的趋势。农业用地和沙土面积的显著减少在很大程度上归因于水文状况的改变造成的河漫滩退化，而河漫滩景观的水文形态变化、人口压力增加和农业集约化是影响如今土地利用及土地覆盖变化的主要驱动力。对未来的预测表明如果不实施适当的可持续发展策略，恒河研究区目前的土地利用及土地覆盖变化趋势会一直持续下去，更为严重的河漫滩退化将随之而来。本研究为在局地和区域尺度上理解因人类活动而导致的长期环境退化和气候变化对河漫滩景观的影响提供了一种整体方法。

关键词：河流景观；土地利用及土地覆盖变化；CA-ANN模型；土地利用变化评价模块；恒河

Abstract

Presently, sustainability of floodplain, a diverse element of the riverine landscape, provides an ideal research setting for investigating complex interaction between anthropogenic disturbance and eco-environmental degradation. Nowadays, these floodplains are continually degraded and fragmented on account of unsustainable land use. To analyse the spatial and temporal changes of landuse/landcover, a supervised classification (maximum likelihood algorithm) method has been made for the period 1998 to 2018. Present research simulates and predicts landuse/landcover dynamics of lower stretch of the Ganges river up to 2038 to analyse future riverine landscape dynamics stressed by various natural and socio-economic factors based on Cellular Automata-Artificial Neuron Network (CA-ANN) model clubbed with Modules for Land Use Change Evaluation (MOLUSCE) plugin of QGIS software. Outcome of research reveals that the trend of agriculture land, sand, and inland waterbody areas is reduced by 15.75, 5.71, and 1.95%, whereas, for orchard, agricultural fallow and bare land areas increased by 7.94, 7.92, and 5.69% for the period from 1998 to 2018. The simulation model predicted a continuation of the similar trend till 2038. The significant reduction of agricultural land and sand areas is largely an attribute to floodplain degradation in an altered hydrological regime. Ultimately, hydro-morphological changes, increasing population pressure, and agriculture intensification in floodplain landscape were identified as main driving forces in temporal landuse/landcover changes. The prediction of future forecast indicates that if the present rate of landuse/landcover trend persists in the study stretch of Ganges river without appropriate sustainable development practice, severe floodplain degradation will ensue. This study provides a holistic measure for understanding long-term environmental degradation related to anthropogenic activities and impact of climate changes in floodplain landscape at local and regional scale.

KEYWORDS: Riverine landscape; landuse/landcover changes; CA-ANN model; MOLUSCE; river Ganga

ALAM, N., SAHA, S., GUPTA, S. & CHAKRABORTY, S. 2021. Prediction modelling of riverine landscape dynamics in the context of sustainable management of floodplain: a Geospatial approach. Annals of GIS. https://doi.org/10.1080/19475683.2020.1870558