Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks

ABSTRACT

Road intersection data have been used across a range of geospatial analyses. However, many datasets dating from before the advent of GIS are only available as historical printed maps. To be analyzed by GIS software, they need to be scanned and transformed into a usable (vector-based) format. Because the number of scanned historical maps is voluminous, automated methods of digitization and transformation are needed. Frequently, these processes are based on computer vision algorithms. However, the key challenges to this are (1) the low conversion accuracy for low quality and visually complex maps, and (2) the selection of optimal parameters. In this paper, we used a region-based deep convolutional neural network-based framework (RCNN) for object detection, in order to automatically identify road intersections in historical maps of several cities in the United States of America. We found that the RCNN approach is more accurate than traditional computer vision algorithms for double-line cartographic representation of the roads, though its accuracy does not surpass all traditional methods used for single-line symbols. The results suggest that the number of errors in the outputs is sensitive to complexity and blurriness of the maps, and to the number of distinct red-green-blue (RGB) combinations within them.     

The use of digital map data in the segmentation and classification of remotely-sensed images

Abstract

Remotely-sensed data constitute a major potential source of input to geographical information systems (GIS)However, these data often have a relatively poor classification accuracy compared with that of the cartographic data from maps with which they may be combined in the course of GIS analysis. The possibility exists of using data sets (in the form of digital maps) resident within a GIS in order to improve this accuracy, before the classified image is incorporated into the GIS. Results are discussed from a British Alvey Information Technology project to develop a system for the knowledge-based segmentation and classification of remotely-sensed terrain images, in which the knowledge contained in digital map     

Improvement of GIS graphics for analysis and decision-making

Abstract

Current geographical information systems (GIS) include functions to create cartographic output interactively or automatically. However, none of the systems presently incorporates mechanisms to ensure correct application of graphic functions. Many of today's users of GIS are not trained in the design and production of graphics and may create maps that confuse or mislead map users. Poorly-designed maps may obliterate the patterns in displayed information.

This article investigates ways to improve the quality of GIS graphical displays and increase their effectiveness for decision-making. Alternatives are presented for improving map design in GIS, ranging from non-technical efforts to enhancement of software functionality. Suggestions propose augmenting users' abilities to create maps in an automated environment, using an approach termed amplified intelligence: key decisions default explicitly to users, whose knowledge is amplified by a range of high-level tools to carry out map design operations automatically.     

The Trade and Industries of Western South America

Abstract

This research was based on an instructional module developed and used to investigate whether GIS can be used to enhance fourth grade students' geographic knowledge and map skills. Another goal was to identify challenges the teachers and the students face using GIS.

Findings from the study suggest that using GIS in the classroom helps students improve their geographic knowledge and maps skills. In addition, this study found that the students' geographic content knowledge tended to improve gradually and the knowledge transferred to the subsequent lessons, while certain map skills tended to develop in a more specific manner.     

The California Electric Power Crisis: Lessons for Other States

Distinguishing forested wetland from dry forest using aerial photographs is handicapped because photographs often do not reveal the presence of water below tree canopies. Radar images obtained by the Seasat satellite reveal forested wetland as highly reflective patterns on the coastal plain between Maryland and Florida. Seasat radar images may complement aerial photographs for compiling maps of wetland. A test with experienced photointerpreters revealed that interpretation accuracy was significantly higher when using Seasat radar images than when using only conventional sources.     

Research Article. Modelling inside GIS: Part 1. Model structures,exploratory spatial data analysis and aggregation

Abstract

This is the first of two papers elaborating a framework for embedding urban models within GIS. This framework is based upon using the display capabilities of GIS as the user interface to the conventional modelling process, beginning with data selection and analysis, moving to model specification and calibration, and thence to prediction. In this paper, we outline how various stages in this process based on purpose-built software outside the system, are accessed and operated through the GIS. We first deal with display based on thematic maps, surfaces, graphs and linked windows, standard to any data from whatever source, be it observations, model estimates or predictions. We then describe how various datasets are selected, how the spatial system can be partitioned or aggregated, and how rudimentary exploratory spatial data analysis enables scatterplots to be associated with thematic maps. We illustrate all these functions and operations using the proprietary GIS ARC-INFO applied to population data at the tract level in the Buffalo region. In the second part of the paper, various residential location models are outlined and the full modelling framework is assembled and demonstrated.     

A GIS evaluation of land use dynamics and forest soil fertility in a watershed in Nepal

Abstract

A geographical information system (GIS) based study was carried out in a densely-populated watershed in Nepal. An evaluation of land use change between 1972 and 1990 indicated that there has been an increase in forest and agricultural land area and a decrease in shrubland and grassland area. GIS techniques were used to produce single and composite fertility index maps, which can be used for problem identification and planning. These maps indicate that forest soil fertility is generally poor in the watershed. GIS was found to be very beneficial in addressing critical resource issues in small watersheds in developing countries.     

Mapping the physiography of Michigan with GIS

Abstract

We present a new physiographic map of Michigan, that is also available interactively, online. Only four, small-scale physiographic maps of Michigan had been previously published. Our mapping project made use of a wide variety of spatial data, in a GIS environment, to visualize and delineate the physical landscape in more detail than has been done previously. We also examined many of the unit boundaries in the field, using a GIS running on a GPS-enabled laptop. Unlike previous physiographic maps, the online version of the map enables users to query the criteria used to define each of the 224 boundaries of its 10 major and 91 minor physiographic units. The interactive nature of the online version of the map is a unique enhancement to physiographic maps and mapping. Our study also provides data on the number and types of criteria used to define each of the 224 unit boundaries within the map. Most of our unit boundaries are based on data derived from 10-m raster elevation data and NRCS soils data, e.g., relief, soil wetness, escarpments, landscape fabric, and parent material characteristics. Data gleaned from NRCS SSURGO county-scale soil maps were a strength of the project. [Key words: Michigan, physiography, landforms, soils, GIS, mapping]     

Monitoring grasshopper and locust habitats in Sahelian Africa using GIS and remote sensing technology†

Abstract

Development programmes in Sahelian Africa are beginning to use geographic information system (GIS) technology. One of the GIS and remote sensing programmes introduced to the region in the late 1980s was the use of seasonal vegetation maps made from satellite data to support grasshopper and locust control. Following serious outbreaks of these pests in 1987, the programme addressed a critical need, by national and international crop protection organizations, to monitor site-specific dynamic vegetation conditions associated with grasshopper and locust breeding. The primary products used in assessing vegetation conditions were vegetation index (greenness) image maps derived from National Oceanic and Atmospheric Administration satellite imagery. Vegetation index data were integrated in a GIS with digital cartographic data of individual Sahelian countries. These near-real-time image maps were used regularly in 10 countries for locating potential grasshopper and locust habitats. The programme to monitor vegetation conditions is currently being institutionalized in the Sahel.     

Why Geography Still Needs Pen and Ink Cartography

Abstract

Maps are fundamental in geographic explanation and education, but as map-making becomes firmly entrenched in the GIS lab, it becomes harder for students to imagine how they can make maps for their papers. Students need to illustrate papers with maps: among other things, maps provide clarity, links to real places, and insights into patterns and context of phenomena discussed in student papers. A simple, quick, and aesthetically satisfying method for students to make their own maps is presented. This map making method can help students can think more creatively and geographically about their topics.     

Resource use in manual digitization A case study of the Patuxent basin geographical information system database

Abstract

In the face of limited and declining budgets, the estimation of costs involved in implementing a geographical information system (GIS) deserves attention. One of the major procedures inherent in the use of GIS is the task of digitizing existing maps. This step is not only the first but may also occur at various stages of the implementation. There is, however, a lack of information on the cost of digitizing. This paper identifies the costs of an intensive effort at manual digitizing over a period of eleven months using the ARC/INFO GIS on a Prime 9650 mini-computer. General costs for digitizing one layer of information from a U.S. Geological Survey 1:24 000 quadrangle are derived. Although the results are based on factors which are unique to this study, the author believes that the findings provide useful bases for estimating costs of digitizing.     

Free and open source GIS in South America: political inroads and local advocacy

ABSTRACT

Geographical information systems (GIS) practitioners worldwide enjoy a growing array of free and open source software (FOSS) options. This software has expanded the accessibility of GIS in economically developing countries while fostering local technical expertise. This article reviews FOSS GIS uptake and advocacy in South America, especially how it relates to a climate of political friendliness toward FOSS in the region. The use or absence of FOSS GIS is assessed in public-facing web maps in South America, first at the national government level, and then at the provincial level using Argentina as a country of study. Local technical support groups and software development initiatives surrounding FOSS GIS in South America are then summarized. Finally, three case studies are presented of notable efforts to build FOSS GIS technical communities at the local level: the FOSSGIS Brasil online magazine, the Geoinquietos Argentina professional network, and the FOSS.4GIS.GOV conference in Brazil. A study of the leaders, dynamics, and practices of these groups can inform others in similar circumstances around the world who are trying to promote FOSS GIS adoption, development, skills, and services.     

The role of root-mean-square error in the geo-transformation of images in GIS

ABSTRACT

There is growing interest in the use of images in GIS applications. This paper examines the role of root-mean-square error in assessing the accuracy of digitisation and image–to–world transformation, The study employed Arc/Info software, using an aerial photograph of a small coastal settlement as the base image. The transformed image was overlayed onto a calibrated digital cadastre of the town to evaluate (visually) the geometric integrity of the image rectification. While not dismissing the relevance of rms error in the statistical appraisal of data quality in GIS, the study failed to confirm a workable association between rms error and the quality of image transformation. No apparent improvement in the quality of image transformation was achieved as a result of reducing rms error directly, by eliminating the control points with high residual error.     

The Geography of Fish: The Use of Remote Sensing and Spatial Analysis Tools in Fisheries Research

Rather than seeing the oceans as an expansive void, researchers using acoustic technologies can detect the heterogeneity of biological resources and view the marine environment as a three-dimensional landscape. Underwater remote sensing, using acoustics, provides high resolution maps of the spatial distribution of organisms in aquatic ecosystems. Analyzing the spatial pattern of species distribution within the water column and the impact of that organization on ecological processes bridges the fields of fisheries and spatial analysis. Tools and concepts familiar to geographers, such as remote sensing, GIS, and landscape ecology, contribute to the investigation of large lake and marine ecosystems.     

The Origin and Pattern Of Development Of Urban Black Social Areas

Abstract

This exercise has been used successfully by more than a thousand students is an introductory college course, and it probably could be equally successful with high school students. Census tract data are used in a simulated research project. Quality of housing in the dependent variable (whose distribution we wish to “explain”), with owner-occupancy and age of housing as independent (or “explanatory”) variables. The distribution of the three variables is compared visually (by maps) and statistically (by scattergrams). A regression line is placed on the better scattergram, and residual values are mapped to provide a basis for the formulation of better working hypotheses.     

Modelling alpine permafrost distribution,Val de Rechy,Valais Alps (Switzerland)

The spatial distribution of the alpine permafrost is modelled in the uppermost part of Val de Rechy (Valais Alps, Switzerland) with the use of a geographical information system (GIS). Two empirical-statistical models are compared and their validity tested by a set of bottom temperature of winter snow (BTS) measurements carried out in the field. One model can simulate the spatial distribution of the permafrost facing ground warming consecutive to climatic change. Local/regional maps of simulated permafrost distribution as presented in this paper can be useful in the context of a preventive approach for natural hazards management.     

Decisions of the U. S. Board of Geographic Names. June 5, 1900, To January 8, 1902 II

ABSTRACT

Spatial literacy is a new frontier in K–12 education. This article describes a place-based introductory GIS/GPS middle school curriculum unit in which students used measuring tools, GPS units, and My World GIS software to collect physical and spatial data of trees to create a schoolyard tree inventory. Maine students completed “memory maps” of their schoolyards as a pre/post exercise assessment. A statistically significant increase in students’ spatial awareness was documented. A technology-based curriculum can significantly increase students’ spatial awareness especially in a place and context relevant to each student.     

JAMGIS,the first Jamaican Government comprehensive multi-data geographical information system Achievements and problems

Abstract

JAMGIS, the first comprehensive multi-data geographical information system (GIS) in Jamaica, has been developed by the Ministry of Agriculture in cooperation with USAID and two universities in the U.S.A. The system and its database are described and a number of problems encountered in its development and practical application are discussed. The most valuable products to date have been the delineation of areas of crop suitability, two series of twelve land use/cover maps at 1:50000 scale and statistical analyses of soil and land resources.     

Comment on ‘Concerning “The economic evaluation of implementing a GIS‘”

Abstract

A fragmentation index has been implemented as a region based GIS operator to describe the spatial distribution of thematic classes in one data layer within map regions defined in another data layer. It has been applied to integrated analysis of digital maps and classified remote sensing data, for estimation of landscape complexity within watersheds and for detection of logged forest stands. The properties of the fragmentation index, when applied in this manner, are discussed. The fragmentation index is suggested as a valuable means of describing image characteristics of spectrally heterogeneous map regions.