Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area

The main objective of this research is to determine the capacity of land cover classification combining spec- tral and textural features of Landsat TM imagery with ancillary geographical data in wetlands of the Sanjiang Plain, Heilongjiang Province, China. Semi-variograms and Z-test value were calculated to assess the separability of grey-level co-occurrence texture measures to maximize the difference between land cover types. The degree of spatial autocorrelation showed that window sizes of 3×3 pixels and 11×11 pixels were most appropriate for Landsat TM im- age texture calculations. The texture analysis showed that co-occurrence entropy, dissimilarity, and variance texture measures, derived from the Landsat TM spectrum bands and vegetation indices provided the most significant statistical differentiation between land cover types. Subsequently, a Classification and Regression Tree (CART) algorithm was applied to three different combinations of predictors: 1) TM imagery alone (TM-only); 2) TM imagery plus image texture (TM+TXT model); and 3) all predictors including TM imagery, image texture and additional ancillary GIS in- formation (TM+TXT+GIS model). Compared with traditional Maximum Likelihood Classification (MLC) supervised classification, three classification trees predictive models reduced the overall error rate significantly. Image texture measures and ancillary geographical variables depressed the speckle noise effectively and reduced classification error rate of marsh obviously. For classification trees model making use of all available predictors, omission error rate was 12.90% and commission error rate was 10.99% for marsh. The developed method is portable, relatively easy to im- plement and should be applicable in other settings and over larger extents.

Integrating geographical data and phenological characteristics derived from MODIS data for improving land cover mapping

The study developed a feasible method for large-area land cover mapping with combination of geographical data and phenological characteristics, taking Northeast China （NEC） as the study area. First, with the monthly average of precipitation and temperature datasets, the spatial clustering method was used to divide the NEC into four ecoclimate regions. For each ecoclimate region, geographical variables （annual mean precipitation and temperature, elevation, slope and aspect） were combined with phenological variables derived from the moderate resolution imaging spectroradiometer （MODIS） data （enhanced vegetation index （EVI） and land surface water index （LSWI））, which were taken as input variables of land cover classification. Decision Tree （DT） classifiers were then performed to produce land cover maps for each region. Finally, four resultant land cover maps were mosaicked for the entire NEC （NEC_MODIS）, and the land use and land cover data of NEC （NEC_LULC） interpreted from Landsat-TM images was used to evaluate the NEC_MODIS and MODIS land cover product （MODIS_IGBP） in terms of areal and spatial agreement. The results showed that the phenological information derived from EVI and LSWI time series well discriminated land cover classes in NEC, and the overall accuracy was significantly improved by 5.29% with addition of geographical variables. Compared with NEC_LULC for seven aggregation classes, the area errors of NEC_MODIS were much smaller and more stable than that of MODIS_IGBP for most of classes, and the wall-to-wall spatial comparisons at pixel level indicated that NEC_MODIS agreed with NEC_LULC for 71.26% of the NEC, whereas only 62.16% for MODIS_IGBP. The good performance of NEC_MODIS demonstrates that the methodology developed in the study has great potential for timely and detailed land cover mapping in temperate and boreal regions.

Land Cover Classification with Multi-source Data Using Evidential Reasoning Approach

Land cover classification is the core of converting satellite imagery to available geographic data.However,spectral signatures do not always provide enough information in classification decisions.Thus,the application of multi-source data becomes necessary.This paper presents an evidential reasoning (ER) approach to incorporate Landsat TM imagery,altitude and slope data.Results show that multi-source data contribute to the classification accuracy achieved by the ER method,whereas play a negative role to that derived by maximum likelihood classifier (MLC).In comparison to the results derived based on TM imagery alone,the overall accuracy rate of the ER method increases by 7.66% and that of the MLC method decreases by 8.35% when all data sources (TM plus altitude and slope) are accessible.The ER method is regarded as a better approach for multi-source image classification.In addition,the method produces not only an accurate classification result,but also the uncertainty which presents the inherent difficulty in classification decisions.The uncertainty associated to the ER classification image is evaluated and proved to be useful for improved classification accuracy.

Rural Habitation Multistage Nature Boundary Extraction Based on Geographic Name Database

In order to extract the boundary of rural habitation, based on geographic name data and basic geographic information data, an extraction method that use polygon aggregation is raised, it can extract the boundary of three levels of rural habitation consists of town, administrative village and nature village. The method first extracts the boundary of nature village by aggregating the resident polygon, then extracts the boundary of administrative village by aggregating the boundary of nature village, and last extracts the boundary of town by aggregating the boundary of administrative village. The related methods of extracting the boundary of those three levels rural habitation has been given in detail during the experiment with basic geographic information data and geographic name data. Experimental results show the method can be a reference for boundary extraction of rural habitation.

Flood Velocity Prediction Using Deep Learning Approach

Floods are one of the most serious natural disasters that can cause huge societal and economic losses.Extensive research has been conducted on topics like flood monitoring,prediction,and loss estimation.In these research fields,flood velocity plays a crucial role and is an important factor that influences the reliability of the outcomes.Traditional methods rely on physical models for flood simulation and prediction and could generate accurate results but often take a long time.Deep learning technology has recently shown significant potential in the same field,especially in terms of efficiency,helping to overcome the time-consuming associated with traditional methods.This study explores the potential of deep learning models in predicting flood velocity.More specifically,we use a Multi-Layer Perceptron(MLP)model,a specific type of Artificial Neural Networks(ANNs),to predict the velocity in the test area of the Lundesokna River in Norway with diverse terrain conditions.Geographic data and flood velocity simulated based on the physical hydraulic model are used in the study for the pre-training,optimization,and testing of the MLP model.Our experiment indicates that the MLP model has the potential to predict flood velocity in diverse terrain conditions of the river with acceptable accuracy against simulated velocity results but with a significant decrease in training time and testing time.Meanwhile,we discuss the limitations for the improvement in future work.

Impacts of Bus Lane on Bus Travel Time Reliability:a Case Study in Shenzhen

The aim of the paper is to evaluate the impacts of bus lane on bus travel time reliability.The data used are the Geographic Positioning System(GPS) data of two bus lines running parallel streets in Shenzhen,China,one of which is a bus lane and the other is a regular lane.Two linear regression models are developed to evaluate the influence of bus lane which has a separated right of way.Other factors including running direction,day of week,time of day,dwell time,and delay at the start point are also considered in the model.Without published time tables,coefficient of variance(CV) of travel time is employed to explore the impacts of bus lane.The results indicate that bus lane can save 22.0% of travel time,reduce 11.5% of the CV of travel time,and decrease the variance of headway by 17.4%.The analysis on bus travel time reliability could help operators and drivers improve the quality of transit service.It also sheds light on how to assess the effectiveness of bus lane for transit planners and service operators.

A cross-analysis framework formulti-source volunteered, crowdsourced, and authoritative geographic information: The case study of volunteered personal traces analysis against transport network data

The paper discusses the need of a high-level query language to allow analysts,geographers and,in general,non-programmers to easily cross-analyze multi-source VGI created by means of apps,crowd-sourced data from social networks and authoritative geo-referenced data,usually represented as JSON data sets(nowadays,the de facto standard for data exported by social networks).Since an easy to use high-level language for querying and manipulating collections of possibly geo-tagged JSON objects is still unavailable,we propose a truly declarative language,named J-CO-QL,that is based on a well-defined execution model.A plug-in for a GIS permits to visualize geo-tagged data sets stored in a NoSQL database such as MongoDB;furthermore,the same plug-in can be used to write and execute J-CO-QL queries on those databases.The paper introduces the language by exemplifying its operators within a real study case,the aim of which is to understand the mobility of people in the neighborhood of Bergamo city.Cross-analysis of data about transportation networks and VGI from travelers is performed,by means of J-CO-QL language,capable to manipulate and transform,combine and join possibly geo-tagged JSON objects,in order to produce new possibly geo-tagged JSON objects satisfying users’needs.

Modeling potential wetland distributions in China based on geographic big data and machine learning algorithms

Climate change and human activities have reduced the area and degraded the functions and services of wetlands in China.To protect and restore wetlands,it is urgent to predict the spatial distribution of potential wetlands.In this study,the distribution of potential wetlands in China was simulated by integrating the advantages of Google Earth Engine with geographic big data and machine learning algorithms.Based on a potential wetland database with 46,000 samples and an indicator system of 30 hydrologic,soil,vegetation,and topographic factors,a simulation model was constructed by machine learning algorithms.The accuracy of the random forest model for simulating the distribution of potential wetlands in China was good,with an area under the receiver operating characteristic curve value of 0.851.The area of potential wetlands was 332,702 km^(2),with 39.0%of potential wetlands in Northeast China.Geographic features were notable,and potential wetlands were mainly concentrated in areas with 400-600 mm precipitation,semi-hydric and hydric soils,meadow and marsh vegetation,altitude less than 700 m,and slope less than 3°.The results provide an important reference for wetland remote sensing mapping and a scientific basis for wetland management in China.

地理大数据挖掘——“水-能源-粮食”纽带研究的新机遇

Since the Bonn 2011 conference,the“water-energy-food”(WEF)nexus has aroused global concern to promote sustainable development.The WEF nexus is a complex,dynamic,and open system containing interrelated and interdependent elements.However,the nexus studies have mainly focused on natural elements based on massive earth observation data.Human elements(e.g.,society,economy,politics,culture)are described insufficiently,because traditional earth observation technologies cannot effectively perceive socioeconomic characteristics,especially human feelings,emotions,and experiences.Thus,it is difficult to simulate the complex WEF nexus.With the development of earth observation sensor technologies and human activity perception methods,geographical big data covering both human activities and natural elements offers a new opportunity for in-depth WEF nexus analysis.This study proposes a five-step framework by leveraging geographical big data mining to dig for the hidden value in the data of various natural and human elements.This framework can enable a thorough and comprehensive analysis of the WEF nexus.Some application examples of the framework,major challenges,and possible solutions are discussed.Geographical big data mining is a promising approach to enhance the analysis of the WEF nexus,strengthen the coordinated management of resources and sectors,and facilitate the progress toward sustainable development.

Exploring point zero:a study of 20 Chinese cities

A point zero represents a central geographical location of a city,which is essential for not only measuring distances,but also understanding the historical and/or cultural origin of a city.Although extensive studies have focused on delineating city centers,to our knowledge,no studies have paid attention to determining the location for a point zero.Here,our goal is to investigate various potential approaches for identifying such a location.Specifically,three typical approaches,geometric-based,topological-based,and thematic-based,are proposed to recommend point zeros and different scales,administrative divisions,kernel density sur-faces,and regions enclosed by ring roads are used for analysis.The effectiveness of different approaches and scales are evaluated and compared by calculating an offset distance between recommended and actual point zero locations in 20 Chinese cities.Using the different approaches,the average offset distance for most Chinese cities is 2-4 km,and the thematicbased approach performs best.Both the topological-based and thematic-based approaches are less sensitive to the analyzed scale than the geometric-based approach.The results indicate that it is possible to determine the approximate location for a point zero from geographical data.Based on the buffer zone of such a location,an actual point zero may further be recommended.

Matching authority and VGI road networks using an extended node-based matching algorithm

The amount of volunteered geographic information(VGI)has increased over the past decade,and several studies have been conducted to evaluate the quality of VGI data.In this study,we evaluate the completeness of the road network in the VGI data set OpenStreetMap(OSM).The evaluation is based on an accurate and efficient network-matching algorithm.The study begins with a comparison of the two main strategies for network matching:segment-based and nodebased matching.The comparison shows that the result quality is comparable for the two strategies,but the node-based result is considerably more computationally efficient.Therefore,we improve the accuracy of node-based algorithm by handling topological relationships and detecting patterns of complicated network components.Finally,we conduct a case study on the extended node-based algorithm in which we match OSM to the Swedish National Road Database(NVDB)in Scania,Sweden.The case study reveals that OSM has a completeness of 87%in the urban areas and 69%in the rural areas of Scania.The accuracy of the matching process is approximately 95%.The conclusion is that the extended node-based algorithm is sufficiently accurate and efficient for conducting surveys of the quality of OSM and other VGI road data sets in large geographic regions.

Disciplinary structure and development strategy of information geography in China

The advent of the information era has resulted in exceptional advances in geographic science.The domain of geographic science has expanded from traditional physical and human geography to physical,human,and information geography,resulting in the emergence of the field of information geography.Three subdisciplines have gradually formed,i.e.,geographic remote sensing science,geographic information science,and geographic data science.With a view towards preparing a description of the disciplinary structure of geographic science for the“Development Strategy of Discipline and Frontier Research in China(2021-2035)”,this article summarizes the history,definition,and disciplinary structure of information geography.The strategic layout of the discipline,along with the goals and key directions of priority development fields,are also highlighted.The insights into this new discipline provided in this paper will promote the development and application of remote sensing and geographic information within the framework of geographic science,advancing the synthesis of geographic research and the integrated development of geographic science.

Evaluating current ethical values of OpenStreetMap using value sensitive design

The crowdsourced OpenStreetMap mapping platform is utilized by countless stakeholders worldwide for various purposes and applications.Individuals,researchers,governments,commercial,and humanitarian organizations,in addition to the engineers,professionals,and technical developers,use OpenStreetMap both as data contributors and consumers.The storage,usage,and integration of volunteered geographical data in software applications often create complex ethical dilemmas and values regarding the relationships between different categories of stakeholders.It is therefore common for moral preferences of stakeholders to be neglected.This paper investigates the integration of ethical values in OpenStreetMap using the value sensitive design methodology that examines technical,empirical,and conceptual aspects at each design stage.We use the Humanitarian OpenStreetMap Team,an existing volunteered geographic information initiative,as a case study.Our investigation shows that although OpenStreetMap does integrate ethical values in its organizational structure,a deeper understanding of its direct and indirect stakeholders’perspectives is still required.This study is expected to assist organizations that contribute to or use OpenStreetMap in recognizing and preserving existing and important ethical values.To the best of our knowledge,this is the first attempt to evaluate ethical values methodically and comprehensively in the design process of the OpenStreetMap platform.