Geospatial Data Analysis Research Articles

GIS-based modeling of landslide susceptibility zonation by integrating the frequency ratio and objective–subjective weighting approach: a case study in a tropical monsoon climate region

Accurate detection of landslide spatial patterns is vital in susceptibility, hazard, and risk disaster mapping. Geographic Information System (GIS)-based quantitative approaches provide a rigorous procedure for gaining deep insight into natural and anthropogenic landslides from different scales. This study aims to implement a comprehensive solution for retrieving the landslide susceptibility index. For that purpose, a landslide inventory was performed in a tropical monsoon climate region, with a magnitude of elevation spanning from −65 m to 1,900 m above the sea, considering 15 fundamental causative factors belonging to the groups of topography, hydrology, geology, land cover conditions and anthropogenic activities, and weather. The frequency ratio (FR) was implemented to rank subclasses in each causative factor. For factor weight estimation, different approaches were applied, including the subjective-based analytic hierarchy process (AHP), objective-based Shannon entropy (SE), and a synergy of both methods (AHP–SE), built on these two approaches. Out of the 271 identified landslide locations, 70% (196 points) were used for training and the remaining 30% (71 points) were applied for validation. The results showed that the integrated AHP–SE outperformed the two individual approaches, with the area under the receiver operating characteristic curve (AUC) reaching 0.876, following SE (AUC = 0.848) and AHP (AUC = 0.818). In the synergy approach, the climate pattern under tropical monsoons was confirmed as the most crucial landslide-predisposing factor. The research contributes to a novel discussion by integrating knowledge-based consultation and statistical data analysis of accurate geospatial data, incorporating significant explanatory factors toward a reliable landslide-prone zonation over space and time dimensions.

A New Approach to Estimate Fuel Budget and Wildfire Hazard Assessment in Commercial Plantations Using Drone-Based Photogrammetry and Image Analysis

Increased demand for sustainable timber products has resulted in large investments in agroforestry in Australia, with plantations growing various Pinus species, selected to suit a plantation’s environment. Juvenile Pinus species have a low fire tolerance. With Australia’s history of wildfires and the likelihood of climate change exacerbating that risk, the potential for a total loss of invested capital is high unless cost-effective targeted risk minimisation is part of forest management plans. Based on the belief that the understory profiles within the juvenile plantations are a major factor determining fuel hazard risks, an accurate assessment of these profiles is required to effectively mitigate those risks. At present, assessment protocols are largely reliant on ground-based observations, which are labour-intensive, time consuming, and expensive. This research project investigates the effectiveness of using geospatial analysis of drone-derived photographic data collected in the commercial pine plantations of south-eastern Queensland as a cost-saving alternative to current fuel hazard risk assessment practices. Understory composition was determined using the supervised classification of orthomosaic images together with derivations of canopy height models (CHMs). The CHMs were subjected to marker-controlled watershed segmentation (MCWS) analysis, isolating and removing the plantation pine trees, enabling the quantification of understory fuel profiles. The method used proved highly applicable to immature forest environments with minimal canopy closure, but became less reliable for close canopied older plantations.

Hydrogeochemical Study and Geospatial Analysis of Water Quality Using GIS based Water Index and Multivariate Statistics in Kombolcha City, Ethiopia

The study was carried out to evaluate hydro geochemistry and the risk of groundwater and surface water pollution in the Kombolcha area. To achieve this, hydrogeochemical analysis, water heavy metal, geospatial data analysis, ion ratio, correlation matrix, principal component analysis, Heavy metal Pollution Index (HPI), and Water Quality Index (WQI) methodologies were employed. A total of 36 samples (both water and effluent samples) had been collected and assessed for major physicochemical variables and heavy metals and samples were taken from hand dug wells, Borehole, springs, and rivers in the area. Hydrogeochemical methods showed groundwater mineralization due to (1) silicate weathering, (2) cation exchange processes, and (3) anthropogenic sources (i.e., contaminated discharge of sulphate, carbonate, and trace metal effluents). The study result revealed that major ions dominating the area are Ca2+ >Na+ > Mg2+ >K+, HCO3- >SO4 2- > Cl- > NO3-, and Fe> Mn >Pb> Cr> Cd for cations, anions and trace metals respectively with all heavy netals had mean concentrations above the WHO recommended limits. Calculated Pollution indices revealed 50.7% of the sample belongs to a low level of pollution, while 35% and 14.3% belong to a medium and high level of pollution respectively which consequently translating the area into high groundwater pollution zones. The correlation matrix revealed that no significant correlation exists between the water quality variables (Cl and NO3- with Fe, Pb, Cr, Mn, and Cd). PCA was applied on the data set to identify the spatial sources of pollution in groundwater and in the first principal component analysis, Mn, Fe, Cr, Pb, and Cd (in descending order) were found in amounts greater than 0.5, confirming that these metals were from anthropogenic sources. The combined assessments based on WQI and HPI, the study showed that water samples in the proximity of industrial sites are polluted by factories effluent and uncontrolled waste disposal due to urbanization.

The Impact of Opioid Prescribing Limits on Drug Usage in South Carolina: A Novel Geospatial and Time Series Data Analysis.

The opioid crisis in the United States has had devastating effects on communities across the country, leading many states to pass legislation that limits the prescription of opioid medications in an effort to reduce the number of overdose deaths. This study investigates the impact of South Carolina's prescription limit law (S.C. Code Ann. 44-53-360), which aims to reduce opioid overdose deaths, on opioid prescription rates. The study utilizes South Carolina Reporting and Identification Prescription Tracking System (SCRIPTS) data and proposes a distance classification system to group records based on proximity and evaluates prescription volumes in each distance class. Prescription volumes were found to be highest in classes with pharmacies located further away from the patient. An Interrupted Time Series (ITS) model is utilized to assess the policy impact, with benzodiazepine prescriptions as a control group. The ITS models indicate an overall decrease in prescription volume, but with varying impacts across the different distance classes. While the policy effectively reduced opioid prescription volumes overall, an unintended consequence was observed as prescription volume increased in areas where prescribers were located at far distances from patients, highlighting the limitations of state-level policies on doctors. These findings contribute to the understanding of the effects of prescription limit laws on opioid prescription rates and the importance of considering location and distance in policy design and implementation.

Mapping rabies distribution in China: a geospatial analysis of national surveillance data

ObjectivesDog-mediated human rabies remains an important public health problem in China. In this study, we aimed to understand the spatiotemporal variation of rabies and examine its nonmedical ecological factors. MethodsIn this study, we used the annual incidence data for rabies at the province level in China to describe the incidence trends for the period 2004-2019 and used a Bayesian hierarchical spatiotemporal model to determine the impacts of environmental, economic, and demographic factors. ResultsFrom 2004 to 2019, there were 26,593 cases reported in 31 provinces in Mainland China, and the annual incidence increased from 0.02 per 100,000 in 2004 to 0.14 in 2007, substantially decreased in 2008, and was gradually declining thereafter. Guizhou, Guangxi, Hunan, and Hainan were four high-risk provinces, and Yunnan and Anhui provinces showed an increased risk in 2018 and 2019. Temperature and per capita gross domestic product were significantly positively correlated with the disease risk. The standardized morbidity ratio of rabies is likely to increase by 28% (relative risk: 1.28, 95% credible interval: 1.13-1.36) for every 1°C rise in temperature, and 17% (relative risk: 1.17, 95% credible interval: 1.01-1.34) for every 10,000 yuan increase in per capita gross domestic product. ConclusionIn most provinces in China, the risk of rabies has been reduced to a persistently low level. However, the progress of rabies control in six provinces have been less than satisfactory. The study highlights interventions, such as enhancing animal vaccination need to be implemented in these priority areas.

Time-based Geospatial Analysis of Night-Time Light Data and Citizen Movement Restriction During Covid-19 Period

Restrictions on community activities or in some areas also called lockdowns have been carried out by many countries in order to reduce the spread of Covid-19. Various methods are used to monitor the implementation of these restrictions, this study uses a new approach by using satellite imagery at night commonly called Night-Time Light (NTL) Data. This research using a sample of 381 coordinate points was taken in public places in Jakarta. The data was collected using the VIIRS Stray Light Corrected Nighttime Day/Night Band Composites Version 1 dataset from Q1 2019 to Q2 2022. The results of these satellite photos were then converted into numerical form and correlated with the timeline for the restriction of community activities in the Jakarta area. The result is there is a slightly decreasing in light intensity when entering a period of Covid-19 at the beginning of 2020 until 2022 with a percentage of around 1% - 16% in various sectors. This decreasing light intensity has a slight correlation with mobility data for several sectors. The mobility data show a huge difference at the beginning of Covid-19, which shows a decrease in the activity of up to 60%.

Seasonal Variations of Dissolved Organic Matter in Urban Rivers of Northern China

Dissolved organic matter (DOM) is ubiquitously present in aquatic environments, playing an important role in the global carbon cycle and water quality. It is necessary to reveal the potential sources and explore spatiotemporal variation of DOM in rivers, especially in urban zones impacted by human activities. It was designed to aim to explore spatiotemporal variations of DOM in urban rivers and ascertain the influencing factors. In this study, dissolved organic carbon (DOC) concentrations, UV-Vis absorption spectroscopy, and 3D fluorescence spectroscopy combined with parallel factor analysis were utilized to characterize DOM composition in urban rivers (the Jiyun, Chaobai, and Yongding rivers) in Tianjin city, northern China. The results showed that DOC (1.28 to 25.85 mg·L−1), generally, was at its highest level in spring, followed by summer, and lowest in autumn and winter, and that the absorption parameters E250:365 (condensation degree/molecular weight, 7.88), SUVA254 (aromaticity, 3.88 L mg C−1 m−1), a355 (content of chromophores, 4.34 m−1), a260 (hydrophobicity, 22.02 m−1), and SR (molecular weight, 1.08) of CDOM (chromophoric DOM) suggested that DOM is mainly composed of low-molecular-weight fulvic acid and protein-like moieties, and had the capability of participating in pollutant migrations and transformations. The results demonstrated significant seasonal differences. Generally, high DOC content was detected in rivers in urban suburbs, due to anthropogenic inputs. Three fluorescence components were identified, and the fluorescence intensity of the protein class reached the highest value, 294.47 QSU, in summer. Different types of land use have different effects on the compositions of riverine DOM; more protein-like DOM was found in sections of urban rivers. The correlation between DOC concentration and the CDOM absorption coefficient was found to be unstable due to deleterious input from industrial and agricultural wastewater and from domestic sewage from human activities. HIX and BIX elucidated that the source of CDOM in three river watersheds was influenced by both terrestrial and autochthonous sources, and the latter prevailed over the former. Geospatial data analysis indicated that CDOM in autumn was sourced from plant detritus degradation from forest land or from the urban green belt; construction land had a great influence on DOC and CDOM in riparian buffer areas. It was revealed that DOM in the watershed is highly impacted by nature and human activities through land use, soil erosion, and surface runoff/underground percolation transport; domestic sewage discharge constituted the primary source and was the greatest determiner among the impacts.

Информационные ресурсы для оценки экологического потенциала геосистем (на примере территории Енисейского севера)

The experience of using open data to create thematic maps for the territory of the Yenisey Siberia on the most important components of the ecological assessment of landscapes is considered. An assessment of the ecologically significant properties of landscapes, revealing their environmental role, is the basis for substantiating the protection of nature and ethnoecosystems in the face of increasing anthropogenic impact. In this regard, the possibilities of using geospatial data for solving problems of this type in the boreal cryolithozone (on the example of the territory of the Yenisei Siberia) are discussed. To achieve this goal, taking into account the availability of open data, the most informative indicators (continuity and temperature of permafrost, net primary production, latent heat flux, uniformity of the habitat of plants and animals) characterizing the ecologically significant properties of the landscape were selected. The permafrost continuity characteristics determine not only the inertia of the state of permafrost landscapes under external influences, but also the potential for the activity of cryogenic processes. The temperature of frozen rocks diagnoses the nature of the response of permafrost geosystems to climatic influences. The environmental protection potential of landscapes is estimated using the combined accounting of net primary production and latent heat flux. Bioproduction characteristics make it possible to compare territories in terms of their vulnerability to external influences and their ability to recover. The calculated values of the latent heat flux largely indicate the homeostatic function of forests. The homogeneity of the habitat of plants and animals is considered as an indirect indicator of the diversity of natural resource conditions for traditional nature management. Mapping of geocryological conditions was made using vector data presented in the information system “Land Resources of Russia”. Processed data from the MODIS spectroradiometer were used to create maps of net primary production and latent heat fluxes. Mapping of the homogeneity of biogeocenotic conditions was made based on the results of calculating statistical patterns in the distribution of the improved vegetation index (EVI) from the Global Habitat Heterogeneity database. The results of comparing the homogeneity of biogeocenotic conditions with the geomorphological features of the region under study are considered. The inconsistency of the conclusions obtained solely on the basis of the analysis of geospatial data without involving the results of field studies is shown. The difficulties of using geospatial data for landscape-ecological analysis of territories with a layered relief structure (the Central Siberian Plateau, the Yenisei Ridge, etc.) are discussed.

Geospatial Data Analysis Using Fuzzy Analytical Hierarchy Process to Delineate Groundwater Potential Zone in a Semi-arid Hard Rock Terrain

Abstract Delineation of groundwater potential zone (GWPZ) is the fundamental need to achieve sustainable development/management of groundwater resources. The hybrid approach of geospatial data analysis using fuzzy analytical hierarchy process (FAHP) is a very potent application which can effectively delineate GWPZ. The present research is carried out with an aim to evaluate the applicability of this hybrid method towards groundwater sustainability in semi-arid hard rock terrain of South Indian shield region, Mahabubnagar district of Telangana. Geomorphology, lineament density (LD), lithology, landuse, slope, soil texture, drainage density (DD) and rainfall are used as controlling thematic variables. The derived result classified the study area into five distinct GWPZ namely, very poor, poor, moderate, good and very good GWPZ. Around 70% of the study area falls under moderate to very poor GWPZ, whereas only around 30% of the study area is falling under good to very good GWPZ. Research authenticity is carried out by comparing well yield data with GWPZ index (GWPZI). Critical parameter overall quality percentage (OQP) (81.75%) value demonstrated very good prediction accuracy.

METHODOLOGICAL BASIS FOR BUILDING ENERGY EFFICIENT TERRITORIAL COMMUNITIES

The work is devoted to the topical issue of the energy security of the territorial community, namely, the identification of promising local resources for the widespread use of biogas reactors. The development of methodological foundations for the introduction of territorial energy complexes based on local raw materials for urbanized areas is the goal of the work. Traditional approaches to the analysis of possible raw materials are hardly acceptable for urbanized territories, therefore, a hypothesis was put forward about the expediency of its identification by indirect signs, namely, methane emissions, which were estimated from satellite monitoring data. The concentration of gases in the atmosphere was measured by continuous scanning with the TROPOMI spectrometer in the ultraviolet, visible, near and short-wave infrared spectra. Thanks to the use of the Google Earth Engine cloud platform for geospatial data analysis, it was possible to create a web application for displaying spatial and temporal changes in the content of greenhouse gases in the atmosphere with the ability to determine their concentration. For the first time, it was possible to identify the presence in the Kyiv region of significant seasonal methane emissions, the peak of which occurs in October. Based on the results of the experiment, which can be interpreted as indirect measurements of the amount of the above organic waste, there is a significant resource for the production on an industrial scale of specialized pellets for biogas reactors of an energy efficient community.

Geospatial Big Data Analytics for Quality Control of Surveys

Geospatial big data analytics allows survey quality control analysts to draw important conclusions about survey data quality that otherwise would take excessive time and resources. In this work, we explored two algorithmic methods that can help ensure reliability of survey interviews by detecting geospatial outliers. Focusing on geospatial data collected from surveys, we implemented outlier detection techniques with two different distance metrics to identify statistical anomalies in real-world datasets that may have qualitative interpretations. We found that one algorithm, which considers the local distribution of points in a dataset, identifies a different set of outliers when compared to another method, which considers the global distribution of points. Since there was a small overlap (10-19%) of flagged points between the two algorithms implemented, it may be helpful for analysts to focus on the fewer “outlier” points that are flagged by both methods rather than all the “outlier” points that are flagged by each algorithm. Finally, analysts should consider the computational costs, as the algorithms differ significantly.

The timescape of the city: Example of spatial interactions based on big data

The paper develops the concept of a timescape of a city based on empirical analysis of geospatial big data. We understand the timescape as the temporal shape of a city, which reflects temporal dynamics of a city structure and rhythms based on aggregated time-space behaviour of individuals. The paper uses the concepts of rhythmanalysis and spatial interactions as theoretical basis. We analyse two data types: mobile phone location data and taxi trajectory data, and the city of Prague is taken as the example. The data capture the population mobility peak before the Covid-19 pandemic has burst out. We examine both the temporal (weekly and daily rhythms) and spatial (intra urban and ‘extra’ urban flows) hierarchies of the city time-space. We have confirmed the existence of distinct differences between workdays and weekend days. It has also been shown that the mobility based on taxi trajectories has specific temporal distribution. Based on ‘extra’ urban flows, rhythms and thus on the present population of the city we have identified two hierarchically different time waves, long (weekly) and short (daily), when the latter has opposite amplitude and span during workdays and during weekend days.

Multi-Scale Flood Mapping under Climate Change Scenarios in Hexagonal Discrete Global Grids

Among the most prevalent natural hazards, flooding has been threatening human lives and properties. Robust flood simulation is required for effective response and prevention. Machine learning is widely used in flood modeling due to its high performance and scalability. Nonetheless, data pre-processing of heterogeneous sources can be cumbersome, and traditional data processing and modeling have been limited to a single resolution. This study employed an Icosahedral Snyder Equal Area Aperture 3 Hexagonal Discrete Global Grid System (ISEA3H DGGS) as a scalable, standard spatial framework for computation, integration, and analysis of multi-source geospatial data. We managed to incorporate external machine learning algorithms with a DGGS-based data framework, and project future flood risks under multiple climate change scenarios for southern New Brunswick, Canada. A total of 32 explanatory factors including topographical, hydrological, geomorphic, meteorological, and anthropogenic were investigated. Results showed that low elevation and proximity to permanent waterbodies were primary factors of flooding events, and rising spring temperatures can increase flood risk. Flooding extent was predicted to occupy 135–203% of the 2019 flood area, one of the most recent major flooding events, by the year 2100. Our results assisted in understanding the potential impact of climate change on flood risk, and indicated the feasibility of DGGS as the standard data fabric for heterogeneous data integration and incorporated in multi-scale data mining.

Exploration of spatial clustering in maternal health continuum of care across districts of India: A geospatial analysis of demographic and health survey data.

The continuum of care (CoC) throughout pregnancy, delivery and post-delivery has recently been highlighted as an integrated intervention programme for maternal, new-born, and child health. Existing literature suggests the importance of continuum of care (CoC) for improved maternal and child health outcomes. However due to unavailability of data at the lowest administrative levels, literature on spatial pattern of uptake of full CoC is lacking. The present study attempts to focus on the spatial analysis of CoC in maternal health care in India. The study is based on the fourth round of National Family Health Survey data conducted in 2015-16 in India. The outcome variable used is maternal health continuum of care which includes- at least 4 ANC visits, delivery through skilled birth attendant and postnatal check-up within 48 hours of delivery. Univariate and bivariate Local Indicator of Spatial Association (LISA) maps have been generated to show the spatial pattern of CoC across 640 districts in India. We also employed spatial regression techniques to explore the determinants of CoC. Percentage of women who followed full CoC was observed to be least for East Kameng (0.0%) district of Arunachal Pradesh and highest in North Goa district (90.4%). Majority of districts where uptake of full CoC was more than 80 percent were found concentrated in southern region on India. Equivalently, findings indicated a strong spatial clustering of full CoC with high-high clusters mostly concentrated in southern districts. Low-low district clusters are concentrated in the states of Uttar Pradesh, Bihar and Madhya Pradesh. For complete CoC the global Moran's I is 0.73 indicating the spatial dependence. The spatial regression analysis suggested that modern contraceptive use, meeting with health worker, urbanization and secondary or above education for women have positive impact on the utilisation of CoC. The spatial pattern indicates district level clustering in uptake of CoC among women. The study suggests policymakers and stakeholders to implement comprehensive interventions at sub-regional levels for ensuring the completion of CoC for women which acts as a preventive measure for adverse outcomes such as-maternal and child mortality.

A deep-learning approach for modelling pedestrian movement uncertainty in large- scale indoor areas

• Indoor trajectory reconstruction model using limited reference points is proposed. • Uncertainty prediction model uses the combination of 1D-CNN and LSTM is proposed. • Enhanced training dataset contains sampling and measurement errors is generated. • Uncertainty region considers both sampling and measurement errors is established. Modelling pedestrian movement uncertainty in complex urban environments is regarded as a meaningful and challenging task regarding the promotion of geospatial data mining and analysis. However, the traditional uncertainty prediction model only takes the movement distance or speed into consideration and is not able to adapt well to time-varying measurement errors. In this paper, a deep-learning framework is proposed for modelling pedestrian movement uncertainty in large-scale indoor areas, in which a hybrid deep-learning model combines a one-dimensional Convolutional Neural Network (1D-CNN) with a long short-term memory (LSTM) network is proposed for enhancing feature extraction performance and reducing time correlation errors. The proposed framework takes human motion related measurement features into consideration, in which the moving step-length and heading information during a time period are also reconstructed and modelled as the input to the deep-learning model. Compared with state-of-art algorithms applied to different real-world trajectory datasets, the proposed deep-learning approach demonstrates much better performance of uncertainty region prediction, including the different indexes (Euclidean error distance, completeness and density) This study has leaded to the provision of an effective and practical framework for modelling trajectory uncertainty of the pedestrian in challenging urban environments, and which is expected to benefit smart city and spatial perception related applications.

A GIS Pipeline to Produce GeoAI Datasets from Drone Overhead Imagery

Drone imagery is becoming the main source of overhead information to support decisions in many different fields, especially with deep learning integration. Datasets to train object detection and semantic segmentation models to solve geospatial data analysis are called GeoAI datasets. They are composed of images and corresponding labels represented by full-size masks typically obtained by manual digitizing. GIS software is made of a set of tools that can be used to automate tasks using geo-referenced raster and vector layers. This work describes a workflow using GIS tools to produce GeoAI datasets. In particular, it mentions the steps to obtain ground truth data from OSM and use methods for geometric and spectral augmentation and the data fusion of drone imagery. A method semi-automatically produces masks for point and line objects, calculating an optimum buffer distance. Tessellation into chips, pairing and imbalance checking is performed over the image–mask pairs. Dataset splitting into train–validation–test data is done randomly. All of the code for the different methods are provided in the paper, as well as point and road datasets produced as examples of point and line geometries, and the original drone orthomosaic images produced during the research. Semantic segmentation results performed over the point and line datasets using a classical U-Net show that the semi-automatically produced masks, called primitive masks, obtained a higher mIoU compared to other equal-size masks, and almost the same mIoU metric compared to full-size manual masks.

The FAO Data Lab on statistical innovation and the use of big data for the production of international statistics

Data is an extremely important intangible good, but official data is not always available. It may be scarce for many reasons, among which: low statistical capacities, poor funding for data and statistics, weak data dissemination and use culture. A solution to fill data gaps needs to consider that there is data made available on the web, usually coming in an unstructured way, that can be combined with innovative methods to generate relevant information. National and international organisations need to engage with new data sources and methods considering the crisis of traditional data collection systems that causes data gaps. In this light, FAO created in 2019 the “Data Lab for statistical innovation” to fill such gaps by modernising the Organization’s statistical business, which means improving the timeliness and granularity of data collection, providing automated analysis, and capturing early warning signals. It does so through the use of cutting-edge technologies (such as web scraping, text mining, geo-spatial data analysis and artificial intelligence) and by introducing nonconventional data sources (social media, online newspaper articles). This article summarises the experience of the FAO Data Lab and how it has been useful for the Organization to fulfil its mandate.

Glottospace: R package for language mapping and geospatial analysis of linguistic and cultural data

Norder et al., (2022). glottospace: R package for language mapping and geospatial analysis of linguistic and cultural data. Journal of Open Source Software, 7(77), 4303, https://doi.org/10.21105/joss.04303

Drivers of Spatiotemporal Variability in Drinking Water Quality in the United States.

Approximately 10% of community water systems in the United States experience a health-based violation of drinking water quality; however, recently allocated funds for improving United States water infrastructure ($50 billion) provide an opportunity to address these issues. The objective of this study was to examine environmental, operational, and sociodemographic drivers of spatiotemporal variability in drinking water quality violations using geospatial analysis and data analytics. Random forest modeling was used to evaluate drivers of these violations, including environmental (e.g., landcover, climate, geology), operational (e.g., water source, system size), and sociodemographic (social vulnerability, rurality) drivers. Results of random forest modeling show that drivers of violations vary by violation type. For example, arsenic and radionuclide violations are found mostly in the Southwest and Southcentral United States related to semiarid climate, whereas disinfection byproduct rule violations are found primarily in Southcentral United States related to system operations. Health-based violations are found primarily in small systems in rural and suburban settings. Understanding the drivers of water quality violations can help develop optimal approaches for addressing these issues to increase compliance in community water systems, particularly small systems in rural areas across the United States.

RDQS: A Geospatial Data Analysis System for Improving Roads Directionality Quality

With the increasing availability of smart devices, billions of users are currently relying on map services for many fundamental daily tasks such as obtaining directions and getting routes. It is becoming more and more important to verify the quality and consistency of route data presented by different map providers. However, verifying this consistency manually is a very time-consuming task. To address this problem, in this paper we introduce a novel geospatial data analysis system that is based on road directionality. We investigate our Road Directionality Quality System (RDQS) using multiple map providers, including: Bing Maps, Google Maps, and OpenStreetMap. Results from the experiments conducted show that our detection neural network is able to detect an arrow’s position and direction in map images with >90% F1-Score across each of the different providers. We then utilize this model to analyze map images in six different regions. Our findings show that our approach can reliably assess map quality and discover discrepancies in road directionality across the different providers. We report the percentage of discrepancies found between map providers using this approach in a proposed study area. These results can help determine areas needs to be revised and prioritized to improve the overall quality of the data within maps.