Geocoding Process Research Articles

Unveiling the impact of machine learning algorithms on the quality of online geocoding services: a case study using COVID-19 data

AbstractIn today's era, the address plays a crucial role as one of the key components that enable mobility in daily life. Address data are used by global map platforms and location-based services to pinpoint a geographically referenced location. Geocoding provided by online platforms is useful in the spatial tracking of reported cases and controls in the spatial analysis of infectious illnesses such as COVID-19. The first and most critical phase in the geocoding process is address matching. However, due to typographical errors, variations in abbreviations used, and incomplete or malformed addresses, the matching can seldom be performed with 100% accuracy. The purpose of this research is to examine the capabilities of machine learning classifiers that can be used to measure the consistency of address matching results produced by online geocoding services and to identify the best performing classifier. The performance of the seven machine learning classifiers was compared using several text similarity measures, which assess the match scores between the input address data and the services' output. The data utilized in the testing came from four distinct online geocoding services applied to 925 addresses in Türkiye. The findings from this study revealed that the Random Forest machine learning classifier was the most accurate in the address matching procedure. While the results of this study hold true for similar datasets in Türkiye, additional research is required to determine whether they apply to data in other countries.

Geocoding processes in cohort studies: methods applied in the EpiFloripa Aging.

To describe the process and epidemiological implications of georeferencing in EpiFloripa Aging samples (2009-2019). The EpiFloripa Aging Cohort Study sought to investigate and monitor the living and health conditions of the older adult population (≥ 60) of Florianópolis in three study waves (2009/2010, 2013/2014, 2017/2019). With an automatic geocoding tool, the residential addresses were spatialized, allowing to investigate the effect of the georeferencing sample losses regarding 19 variables, evaluated in the three waves. The influence of different neighborhood definitions (census tracts, Euclidean buffers, and buffers across the street network) was examined in the results of seven variables: area, income, residential density, mixed land use, connectivity, health unit count, and public open space count. Pearson's correlation coefficients were calculated to evaluate the differences between neighborhood definitions according to three variables: contextual income, residential density, and land use diversity. The losses imposed by geocoding (6%, n = 240) caused no statistically significant difference between the total sample and the geocoded sample. The analysis of the study variables suggests that the geocoding process may have included a higher proportion of participants with better income, education, and living conditions. The correlation coefficients showed little correspondence between measures calculated by the three neighborhood definitions (r = 0.37-0.54). The statistical difference between the variables calculated by buffers and census tracts highlights limitations in their use in the description of geospatial attributes. Despite the challenges related to geocoding, such as inconsistencies in addresses, adequate correction and verification mechanisms provided a high rate of assignment of geographic coordinates, the findings suggest that adopting buffers, favored by geocoding, represents a potential for spatial epidemiological analyses by improving the representation of environmental attributes and the understanding of health outcomes.

TopoRadio

This article analyzes the construction of TopoRadio (toporadio.org), an interactive map that showcases publications and archives about Spanish-language radio in the U.S. The map aims to promote a more inclusive and comprehensive representation of U.S. radio history by improving the visibility of contributions from Latinx broadcasters. The article addresses how map-making historically suppressed Spanish-language radio programs and proposes using critical cartography as a framework for mapping back this history. The technical elements of TopoRadio, including publication selection criteria, metadata design, geocoding process, and the appraisal of Geographic Information Systems (GIS) software, are described to provide scholars with a reproducible method for creating interactive mapping projects. The article concludes with an assessment of the map's effectiveness as a research tool and an analysis of the publications in the field of Spanish-language radio studies included on the map.

A two-step process to increase successful geocoding in publicly available police stop data

ABSTRACT Many police departments are meeting calls for transparency by releasing publicly accessible data. High-quality address locations are critical for successful and accurate geocoding, though the content and quality of that data can drastically vary across datasets. In this study, we showcase a two-step geocoding process that helps convert low-quality address locations into geo-locatable addresses using traditional geocoding and Jaro-Winkler edit distance methods with police stop data from the San Diego Police Department. For reference, only 83% of stops were geocoded when using traditional geocoding methods. By employing the Jaro-Winkler edit distance to clean the stop address strings, we were able to geocode 99% of stops. We further discuss data creation practices and solutions for data quality-related issues for police departments and researchers when using publicly available policing data.

Abstract PO-073: Using spatial analysis to identify environmental stressors that affected women with gynecological cancer in Puerto Rico during and after Hurricane María

Abstract Socially vulnerable communities, such as women, cancer patients, and minorities, are at a high risk of poor health outcomes after a disaster. This ongoing study analyzes specific environmental stressors that affected women with gynecological (gyn) cancer during and after Hurricane María (HM) in Puerto Rico (PR) in September 2017. To do this, we recruited and interviewed 271 women aged ≥ 21 years diagnosed with gyn cancer between Sept 2016 and Sept 2018, from which only 195 met all the selection criteria. Some sections in the interview were divided into two different time periods: 3 months before and 3 months after HM. To carry-out a geospatial analysis, physical addresses 3 months before and after HM were geocoded using ArcGIS World Geocoding Service, in ArcMap 10.8.1. The software provided “automatically matched addresses” and “matched addresses with tied candidates”. The addresses identified as “matched addresses with tied candidates” were verified during the rematch process while also confirmed with Google Earth. Environmental hazards information and risk exposure were based on existing Earth Observation Data and Geodatabases from multiple agencies: flood from the Federal Emergency Management Agency (FEMA), HM's eye track from the National Oceanic and Atmospheric Administration (NOAA), social vulnerability index from the Centers for Disease Control and Prevention (CDC), and landslides from United States Geological Survey (USGS). 100 (51.3%) women were diagnosed with gyn cancer before HM, and 95 (48.7%) were diagnosed with gyn cancer after HM. Hazards such as floods and landslides were some of the primary environmental stressors experienced by the participants during and after HM. Geocoding process provided 247 (91%) automatically matched addresses and 24 (9%) tied addresses. Spatial analysis suggests that 12.3% of the participants were living in areas with the highest indices of social vulnerability. Some differences were identified for flood exposure. Geospatial analysis using FEMA-Flood Maps, suggests 18.5% of women were living in flood prone areas. Interview results suggested 54.4% gyn cancer patients suffered floods. Consistent with the characteristic of the storm, most of the participants (62.6%) were inside HM's eye track. 12.8% of the participants were living in areas that suffered landslides. Gyn cancer patients in this study suffered severe environmental stressors as a result of HM. Diminishing environmental health issues to cancer patients is key to support their access to care and quality of life. Oncology care approaches should be included on emergency plans for disasters, to guarantee access to care and health equity of cancer patients. Our preliminary findings and results are suggesting that FEMA-Flood Maps were underestimating flood risk in PR. Providing the most accurate geospatial information is essential for Risk Management. This information is crucial since it will allow citizens and communities to be better prepared and to take adaptation measures before the event. NCI Grants (R25CA240120 & R21CA239457-02) Citation Format: Camila V. Elías, Pablo A Méndez, Liz M. Martínez, Ana P. Ortiz. Using spatial analysis to identify environmental stressors that affected women with gynecological cancer in Puerto Rico during and after Hurricane María [abstract]. In: Proceedings of the AACR Virtual Conference: 14th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2021 Oct 6-8. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2022;31(1 Suppl):Abstract nr PO-073.

Automated geoimage generation of Arctic industrial and natural complexes for regional management information support systems

The problem of monitoring and management of industrial and natural complexes in the Arctic is an important problem, without solving which the effective development of the Arctic zones of the Russian Federation is impossible. Specialized information systems are actively used to support decision-making on planning and managing various types of activities in the Arctic, as well as the socio-economic development of the Arctic territories of the Russian Federation. Spatial information visualization tools are an important part of such systems. Visual representation of data is one of the most convenient types of information representation for human processing. This paper describes a method of automated geoimage generation for decision support systems based on the analysis of natural language texts. The use of such geoimages reduces the complexity of decision making for the management tasks of spatially distributed bio-socio-economic systems of the region. The paper describes the formulation of the research problem, review of geocoding tools and services, the original technology of automated geoimages (digital maps) generation based on the use of cloud geoservices. Particular attention is paid to the problem of recognition of named entities in natural language text. The recognition results are used as input data for geocoding and geovisualization process. As a result of the method, the text is converted into a geoimage (map) which can be used to support decision-making by a decision maker. In the final part of the paper, plans for further work are described to develop the capabilities of the automated geoimage generation method for decision support systems based on the analysis of natural language texts.

COVID-19 hastalarının izlenmesinde çevrimiçi coğrafi kodlama servislerinin karşılaştırmalı analizi

Address and location information are the fundamental elements that facilitate mobility. Location-based applications serving in areas such as health, logistics and transportation management employ address information that points to a geographic referenced location. Global map platforms such as ArcGIS Online, Bing Maps, Google Maps, HERE Maps and Yandex Maps serve users by performing the geocoding process, which is the between addresses and geographic locations. Geocoding services play a vital role in the rapid display of epidemic information, spatial tracking of reported cases and control processes in the spatial analysis of infectious diseases such as COVID-19 around the world. Therefore, the objective of this study is to reveal the quality of outcome products offered by online geocoding service providers that can be used for monitoring COVID-19 patients. The comparison of the services was carried out using experimental methods, depending on the match rate, positional accuracy and error sources offered by the services. The results revealed that Yandex Maps online geocoding service was more successful than other services and was a reliable source for public health issues.

A dynamic GIS space-time diffusion model to tackle COVID-19 emergency

BackgroundSurveillance and containment of the spread of COVID-19 requires the use of advanced geographic information science and technology (GIS&T) to map the spread and eventually to guide interventions. A dynamic space-time diffusion model in a GIS environment was developed and succesfully tested in Rome, Italy.MethodsInformation on cases of SARS-CoV-2 infection confirmed by molecular diagnostics from Feb 25 to Sep 26 2020 (collected by a large Local Health Unit of Rome, Italy) was used to test a GIS simulator model able to monitor the spatial diffusion and temporal evolution of the spread of the disease. Data included information on: sex, date and place of birth, healthcare facility of hospitalization, date of notification, start date and end date of isolation, date of recovery (both clinical and laboratory confirmed), residence address.ResultsGlobally, 3,056 cases were geocoded and analysed. The spatio-temporal analysis of the first 45 days since 25 Feb 2020 shows that the spread of COVID-19 was very fast (1,230 cases recorded on 11 Apr) and spatially widespread. Number of cases was highest in the city centre with clusters, thickets and axes in different sub-municipal areas. A slowdown occurred the following month, confirming the positive effect of the lockdown. This effect continued until 11 Jun with a small increase in the number of cases (+10.9%). The period up to 26 Sep is paradigmatic of the second wave, with a continuous increase in cases that spread from the city centre to the suburbs.ConclusionsUsing geocoding process and a detailed GIS mapping it is possible to identify streets, buildings and census sections where the number of cases is high and tends to increase rapidly and, at the same time, it is possible to distinguish clusters and axes that should be kept immediately under special observation as potential pools of super-diffusion. Development of its use in near-real time could bring significant advantages in controlling the spread of COVID-19.Key messages The use of GIS technology is fundamental for mapping the spread of COVID-19.A greater effort should be made by institutions to increase the digitisation of health data and the possibility of using them for both research and surveillance purposes.

Spatial Errors in Automated Geocoding of Incident Locations in Australian Suicide Mortality Data.

There is increasing interest in the spatial analysis of suicide data to identify high-risk (often public) locations likely to benefit from access restriction measures. The identification of such locations, however, relies on accurately geocoded data. This study aims to examine the extent to which common completeness and positional spatial errors are present in suicide data due to the underlying geocoding process. Using Australian suicide mortality data from the National Coronial Information System for the period of 2008-2017, we compared the custodian automated geocoding process to an alternate multiphase process. Descriptive and kernel density cluster analyses were conducted to ascertain data completeness (address matching rates) and positional accuracy (distance revised) differences between the two datasets. The alternate geocoding process initially improved address matching from 67.8% in the custodian dataset to 78.4%. Additional manual identification of nonaddress features (such as cliffs or bridges) improved overall match rates to 94.6%. Nearly half (49.2%) of nonresidential suicide locations were revised more than 1,000 m from data custodian coordinates. Spatial misattribution rates were greatest at the smallest levels of geography. Kernel density maps showed clear misidentification of hotspots relying solely on autogeocoded data. Suicide incidents that occur at nonresidential addresses are being erroneously geocoded to centralized fall-back locations in autogeocoding processes, which can lead to misidentification of suicide clusters. Our findings provide insights toward defining the nature of the problem and refining geocoding processes, so that suicide data can be used reliably for the detection of suicide hotspots. See video abstract at, http://links.lww.com/EDE/B862.

Covid Tracker for Medical Front-Liners- A Survey

This paper studies the need and suggests a centralized pandemic management system for monitoring and managing the Covid-19 positive patients. The initial process of the system will be data collection from a standard medical organization and performing suitable preprocessing. Following this, is the Geocoding process of the patient’s address and area wise sub clustering. Next is plotting the patient on a map for better visualization. After this the medical staff will access this data and field staff will fillup the patient’s symptoms and upload it to a database. A doctor can assign the type of treatment, ambulance and hospital to the patient. Finally, tracking the patient’s arrival to the hospital via ambulance and treating the patient will mark the end. Analysis and visualization on the patients live data will help the authorities in decision-making. Through all these steps, the monitoring of a Covid-19 positive patient will become very easy and convenient for the medical front liners and other concerned authorities

Creating open source composite geocoders: Pitfalls and opportunities

AbstractGeocoding, the process of converting a street address into a pair of coordinates that facilitate mapping, is a perennial challenge for researchers. Both technical and practical barriers exist to geocoding itself and creating reproducible workflows that string multiple geocoders together (so‐called “composite” geocoders). This article presents a suite of open‐source tools designed to standardize American addresses and geocode them. These tools culminate in a composite geocoder for the city of St. Louis, Missouri, which serves as a proof‐of‐concept for developing sophisticated geocoding processes. We test this geocoder on a data set of 1,822 homicides for St. Louis between 2008 and 2018, comparing the results of our tools to a range of commercial providers. We find varying levels of efficiency and accuracy across the available commercial platforms and demonstrate that our in‐house tools provide high positional accuracy with significant efficiency increases.

Spatial Heterogeneity in Positional Errors: A Comparison of Two Residential Geocoding Efforts in the Agricultural Health Study.

Geocoding is a powerful tool for environmental exposure assessments that rely on spatial databases. Geocoding processes, locators, and reference datasets have improved over time; however, improvements have not been well-characterized. Enrollment addresses for the Agricultural Health Study, a cohort of pesticide applicators and their spouses in Iowa (IA) and North Carolina (NC), were geocoded in 2012–2016 and then again in 2019. We calculated distances between geocodes in the two periods. For a subset, we computed positional errors using “gold standard” rooftop coordinates (IA; N = 3566) or Global Positioning Systems (GPS) (IA and NC; N = 1258) and compared errors between periods. We used linear regression to model the change in positional error between time periods (improvement) by rural status and population density, and we used spatial relative risk functions to identify areas with significant improvement. Median improvement between time periods in IA was 41 m (interquartile range, IQR: −2 to 168) and 9 m (IQR: −80 to 133) based on rooftop coordinates and GPS, respectively. Median improvement in NC was 42 m (IQR: −1 to 109 m) based on GPS. Positional error was greater in rural and low-density areas compared to in towns and more densely populated areas. Areas of significant improvement in accuracy were identified and mapped across both states. Our findings underscore the importance of evaluating determinants and spatial distributions of errors in geocodes used in environmental epidemiology studies.

A multi-agent-based approach for address geocoding in poorly mapped areas through public company data

In this study, we present an original method that enhances geocoding systems in poorly mapped areas thanks to public company data and a multi-agent system. In contrast with industrialized countries, many developing countries lack formal postal address systems assignments and usage, making the operation of translating text-based addresses to absolute spatial coordinates, known as geocoding, a big challenge. We recreated a standard of address as it is perceived and used by local people, a kind of non-official national address standard since there is no official one in these areas. Then, we designed a multi-agent system in which agents are assigned different tasks of geocoding process and can perform negotiation to achieve a global objective: find the best possible match or approximation of a location-based on current knowledge. Verification of the usefulness of the proposed approach is made in comparison with Google Geocoding API which shows that the proposed approach has great potential to geocode addresses considering local context semantic issues.

Improving geocoding matching rates of structured addresses in Rio de Janeiro, Brazil.

Strategies for improving geocoded data often rely on interactive manual processes that can be time-consuming and impractical for large-scale projects. In this study, we evaluated different automated strategies for improving address quality and geocoding matching rates using a large dataset of addresses from death records in Rio de Janeiro, Brazil. Mortality data included 132,863 records with address information in a structured format. We performed regular expressions and dictionary-based methods for address standardization and enrichment. All records were linked by their postal code or street name to the Brazilian National Address Directory (DNE) obtained from Brazil's Postal Service. Residential addresses were geocoded using Google Maps. Records with address data validated down to the street level and location type returned as rooftop, range interpolated, or geometric center were considered a geocoding match. The overall performance was assessed by manually reviewing a sample of addresses. Out of the original 132,863 records, 85.7% (n = 113,876) were geocoded and validated, out of which 83.8% were matched as rooftop (high accuracy). Overall sensitivity and specificity were 87% (95%CI: 86-88) and 98% (95%CI: 96-99), respectively. Our results indicate that address quality and geocoding completeness can be reliably improved with an automated geocoding process. R scripts and instructions to reproduce all the analyses are available at https://github.com/reprotc/geocoding.

UAV IMAGE FAST GEOCODING METHOD FOR DISASTER SCENE MONITORING

Abstract. Recently, UAVs are being used in various fields such as photography, precision agriculture, remote monitoring, surveying, mapping, and disaster management. In particular, UAVs can acquire real-time data and access hard-to-reach areas, which is advantageous for rapid spatial information generation. Spatial information can be generated by mounting a camera on the UAV and performing the geocoding process of image data using the location/location information acquired from the GPS/INS sensor. The use of multiple GCPs during the geocoding process can increase the image position accuracy. However, since a lot of time is consumed for surveying, it is disadvantageous to be used in disaster fields that require urgent data generation. Therefore, in this study, fast geocoding process of UAV image using the minimum GCP is proposed. The results obtained through this process can be used as basic data for on-site monitoring and decision-making in disasters and emergencies.

The sensitivity of repeat and near repeat analysis to geocoding algorithms

PurposeTo determine if repeat and near repeat analysis is sensitive to the geocoding algorithm used for the underlying crime incident data. MethodsThe Indianapolis Metropolitan Police Department provided 2016 crime incident data for five crime types: (1) shootings, (2) robberies, (3) residential burglaries, (4) theft of automobiles, and (5) theft from automobiles. The incident data were geocoded using a dual ranges algorithm and a composite algorithm. First, descriptive analysis of the distances between the two point patterns were conducted. Second, repeat and near repeat analysis was performed. Third, the resulting repeat and near repeat patterns were compared across geocoding algorithms. ResultsThe underlying point patterns and repeat and near repeat analyses were similar across geocoding algorithms. ConclusionsWhile detailing geocoding processes increases transparency and future researchers can conduct sensitivity results to ensure their findings are robust, dual ranges geocoding algorithms are likely adequate for repeat and near repeat analysis.

A probabilistic framework for improving reverse geocoding output

AbstractReverse geocoding, which transforms machine‐readable GPS coordinates into human‐readable location information, is widely used in a variety of location‐based services and analysis. The output quality of reverse geocoding is critical because it can greatly impact these services provided to end‐users. We argue that the output of reverse geocoding should be spatially close to and topologically correct with respect to the input coordinates, contain multiple suggestions ranked by a uniform standard, and incorporate GPS uncertainties. However, existing reverse geocoding systems often fail to fulfill these aims. To further improve the reverse geocoding process, we propose a probabilistic framework that includes: (1) a new workflow that can adapt all existing address models and unitizes distance and topology relations among retrieved reference data for candidate selections; (2) an advanced scoring mechanism that quantifies characteristics of the entire workflow and orders candidates according to their likelihood of being the best candidate; and (3) a novel algorithm that derives statistical surfaces for input GPS uncertainties and propagates such uncertainties into final output lists. The efficiency of the proposed approaches is demonstrated through comparisons to the four commercial reverse geocoding systems and through human judgments. We envision that more advanced reverse geocoding output ranking algorithms specific to different application scenarios can be built upon this work.

Assessment of automatic geocoding tools in Temuco, Chile

TPS 651: Air pollution exposure modeling 1, Exhibition Hall, Ground floor, August 27, 2019, 3:00 PM - 4:30 PM Automatic geocoding process is carried out in many epidemiological studies. However, the quality of the process has been scarcely evaluated. The objective of this work is to compare the performance of three automatic online geocoding tools using addresses from hand-written hospital files. To do this, from an initial set of transcribed addresses a random sample was geocoded using a gold-standard approach, then the same addresses were geocoded using the three automatic approaches. Analyses were based on a retrospective pregnancy cohort study including 15,500 pregnant women who lived in two cities: Temuco and Padre Las Casas. A sampling design stratified by city was carried out. A sub-sample with 300 random addresses were selected: 200 from Temuco and 100 from Padre Las Casas. The geocoding process of the sub-sample was manually conducted. Every address was located in front of the house using Google Street View. If the address was not found, then a Global Positional System (GPS) receiver was used to obtain coordinates. Then the same addresses were geocoded using the three automatic approaches: Google using Qgis, Google Earth using R and Bing using R. Measures of assessment of performance included completeness, match agreement and positional error. Analyses showed 90% of manual gecoding success. Automated geocoding completeness were 90% for Google, 57% for Bing and 84% for Google Earth. It was observed differences between cities. Some neighborhoods have completeness lower than 75%. Bing was not able to find addresses in Padre Las Casas. Positional error was estimated 11m (SD: 13.9) for Bing; 80m (SD: 446.3) for Google Earth, and 83m (SD: 364.5) for Google. There are differences between cities: Temuco has the lower positional error. Analyses showed that quality of geocoding differs by city and neighborhood. Could be advisable to study locally geocoding performance before to apply it to epidemiological studies.

Evaluating a location distortion model to improve reverse geocoding through temporal semantic signatures

Reverse geocoding is a process that maps coordinates to a set of location identifiers such as addresses or toponyms. What makes the reverse geocoding process challenging is the uncertainty of the position being asked and the point features used to represent places. In recent years, due to advances in locating technologies, large amounts of location-based data have been produced in location-based social networks such as the Yelp, Foursquare, and Swarm. These data are a rich source of information about the patterns of people's behaviors in different places. In this paper, with the help of these data, the enhancement of spatial distance-only reverse geocoding has been attempted. The main purpose of this paper is to develop and validate an algorithm for matching categories in the Yelp and Swarm services. In this way, the data from the Yelp were used for generating temporal behavior data and the data from Swarm were used for collecting check-in data. Since the data from Yelp and Swarm services have different categorization structures, integrating these two structures was one of the main challenges of our study. After matching the categories of Yelp and Swarm services, the obtained temporal behavior data for all data sets of Yelp were used in the process of reverse geocoding for Swarm check-in data. In our study, linear, rational and sinusoidal functions were used for distorting the spatial distance with temporal check-in probability in the process of reverse geocoding. In addition, two sets of data include training and test data were used for determining the parameters of the model and validating the results. In this way, it was found that by combining a linear model with temporal behavior data, the results of spatial distance-only reverse geocoding can be improved by 29.96% for the Mean Reciprocal Rank index (a statistical measure for evaluating any process that produces a list of responses, ordered by probability of correctness) and 105.73% for the First Position index (which counts the number of correctly identified POIs). The findings of our study confirmed that the extended set of temporal probabilities of POI categories obtained from Yelp and Swarm gives better results than previous studies. The strengths of our method was demonstrated by validating it against a spatial distance only baseline by the Mean Reciprocal Rank and the First Position indices.

Using GIS to Advance Social Economics Research: Geocoding, Aggregation, and Spatial Thinking

The political, social, and economic conditions which lead to inequality, poverty, and health disparities have distinct spatial footprints. Geographic information systems (GIS) are a collection of tools that can aid the social economist in the investigation of such phenomena. Geocoding is a technical procedure that matches attribute data to spatial features in GIS. This analysis of social economy discusses the possibilities of spatial analysis and the technical process of geocoding. Using 15 years of address level pediatric data from a local children’s hospital, a novel iterative geocoding process is applied for the purpose of investigating the relationship between household environments and health outcomes. This procedure adheres to traditional standards for geocoding (positional accuracy, completeness, and repeatability) while producing multiple spatial data sets that can be associated with a range of environmental and socioeconomic variables related to human health. Describing this technical procedure contributes to a growing methodological toolbox for applying GIS to research in social economics.