Detecting and Visualizing Observation Hot-Spots in Massive Volunteer-Contributed Geographic Data across Spatial Scales Using GPU-Accelerated Kernel Density Estimation

Volunteer-contributed geographic data (VGI) is an important source of geospatial big data that support research and applications. A major concern on VGI data quality is that the underlying observation processes are inherently biased. Detecting observation hot-spots thus helps better understand the bias. Enabled by the parallel kernel density estimation (KDE) computational tool that can run on multiple GPUs (graphics processing units), this study conducted point pattern analyses on tens of millions of iNaturalist observations to detect and visualize volunteers’ observation hot-spots across spatial scales. It was achieved by setting varying KDE bandwidths in accordance with the spatial scales at which hot-spots are to be detected. The succession of estimated density surfaces were then rendered at a sequence of map scales for visual detection of hot-spots. This study offers an effective geovisualization scheme for hierarchically detecting hot-spots in massive VGI datasets, which is useful for understanding the pattern-shaping drivers that operate at multiple spatial scales. This research exemplifies a computational tool that is supported by high-performance computing and capable of efficiently detecting and visualizing multi-scale hot-spots in geospatial big data and contributes to expanding the toolbox for geospatial big data analytics.

Download Full-text

A GPU-accelerated adaptive kernel density estimation approach for efficient point pattern analysis on spatial big data

International Journal of Geographical Information Science ◽

10.1080/13658816.2017.1324975 ◽

2017 ◽

Vol 31 (10) ◽

pp. 2068-2097 ◽

Cited By ~ 13

Author(s):

Guiming Zhang ◽

A-Xing Zhu ◽

Qunying Huang

Keyword(s):

Big Data ◽

Density Estimation ◽

Kernel Density Estimation ◽

Pattern Analysis ◽

Kernel Density ◽

Point Pattern Analysis ◽

Point Pattern ◽

Efficient Point ◽

Adaptive Kernel ◽

Spatial Big Data

Download Full-text

Schistosoma japonicum infected sentinel mice surveillance and spatial point pattern analysis in Hubei province, China, 2010-2018

10.21203/rs.3.rs-22516/v1 ◽

2020 ◽

Author(s):

Yan-Yan Chen ◽

Si Liu ◽

Xiao-Wei Shan ◽

Hui Wang ◽

Bo Li ◽

...

Keyword(s):

High Risk ◽

Schistosoma Japonicum ◽

Density Estimation ◽

Kernel Density Estimation ◽

Kernel Density ◽

Hubei Province ◽

Point Pattern Analysis ◽

Point Pattern ◽

Infection Pattern ◽

Risk Areas

Abstract Background Progress in national schistosomiasis control in China has successfully reduced disease transmission in many districts. However, a low transmission rate hinders conventional snail surveys in identifying areas at risk. In this study, Schistosoma japonicum infected sentinel mice surveillance was conducted to identify high risk areas of schistosomiasis transmission in Hubei province, China. Methods The risk of schistosomiasis transmission was assessed using sentinel mice monitoring in Hubei province from 2010 to 2018. Field detections were carried out in June and September and the sentinel mice were kept for approximately 35 days in a laboratory. Then they were dissected to determine whether schistosome infection was present. Ripley’s K-function and kernel density estimation were applied to analyze the spatial distribution and positive point pattern of schistosomiasis transmission. Results A total of 190 sentinel mouse surveillance sites were selected to detect areas of schistosomiasis infection from 2010 to 2018, with 29 sites showing infected mice (15.26%).A total of 4723 mice were dissected and112 infected mice containing 256 adult worms were detected. The infection rate was 2.37% and an average of 2.28 worms was detected per infected mouse. Significantly more infected mice were detected in June samples than in September samples (x2 = 12.11, P < 0.01).Ripley's L(d) index analysis showed that, when distance was less than or equal to 34.52 km, the sentinel mice infection pattern showed aggregation, with the strongest aggregation occurring at 7.86 km. Three hotspots were detected using kernel density estimation, namely: at the junction of Jingzhou District, Gong’an County and Shashi District in Jingzhou City; in Wuhan city at the border of the Huangpi and Dongxihu Districts and in the Hanan and Caidian Districts. Conclusion The results showed sentinel mice surveillance was useful in identifying high-risk areas and could provide valuable information for schistosomiasis prevention and control, especially concerning areas along the Yangtze River such as the Fu-Lun, Dongjing-Tongshun and Juzhang River basins.

Download Full-text

Use of Spatial Analysis Techniques to Identify Statistically Significant Crash Hot Spots in Metropolitan Melbourne

Journal of Road Safety ◽

10.33492/jrs-d-19-00249 ◽

2020 ◽

Vol 31 (4) ◽

pp. 36-58

Author(s):

Elizabeth Hovenden ◽

Gang-Jun Liu

Keyword(s):

Land Use ◽

Density Estimation ◽

Kernel Density Estimation ◽

Hot Spots ◽

Hot Spot ◽

Kernel Density ◽

Spatial Dependency ◽

Moran's I ◽

Analysis Techniques ◽

Global Moran’S I

Understanding where, when, what type and why crashes are occurring can help determine the most appropriate initiatives to reduce road trauma. Spatial statistical analysis techniques are better suited to analysing crashes than traditional statistical techniques as they allow for spatial dependency and non-stationarity. For example, crashes tend to cluster at specific locations (spatial dependency) and vary from one location to another (non-stationarity). Several spatial statistical methods were used to examine crash clustering in metropolitan Melbourne, including Global Moran’s I statistic, Kernel Density Estimation and Getis-Ord Gi* statistic. The Global Moran’s I statistic identified statistically significant clustering on a global level. The Kernel Density Estimation method showed clustering but could not identify the statistical significance. The Getis-Ord Gi* method identified local crash clustering and found that 15.7 per cent of casualty crash locations in metropolitan Melbourne were statistically significant hot spots at the 95 per cent confidence level. The degree, location and extent of clustering was found to vary for different crash categories, with fatal crashes exhibiting the lowest level of clustering and bicycle crashes exhibiting the highest level of clustering. Temporal variations in clustering were also observed. Overlaying the results with land use and road classification data found that hot spot clusters were in areas with a higher proportion of commercial land use and with a higher proportion of arterial and sub-arterial roads. Further work should investigate network based hot spot analysis and explore the relationship between crash clusters and influencing factors using spatial techniques such as Geographically Weighted Regression.

Download Full-text

Identification of Vehicle-Pedestrian Collision Hotspots at the Micro-Level Using Network Kernel Density Estimation and Random Forests: A Case Study in Shanghai, China

Sustainability ◽

10.3390/su10124762 ◽

2018 ◽

Vol 10 (12) ◽

pp. 4762 ◽

Cited By ~ 3

Author(s):

Shenjun Yao ◽

Jinzi Wang ◽

Lei Fang ◽

Jianping Wu

Keyword(s):

Density Estimation ◽

Random Forests ◽

Kernel Density Estimation ◽

Hot Spots ◽

Kernel Density ◽

Pedestrian Safety ◽

Threshold Value ◽

The Difference ◽

Pedestrian Crashes ◽

Crash Reduction

The improvement of pedestrian safety plays a crucial role in developing a safe and friendly walking environments, which can contribute to urban sustainability. A preliminary step in improving pedestrian safety is to identify hazardous road locations for pedestrians. This study proposes a framework for the identification of vehicle-pedestrian collision hot spots by integrating the information about both the likelihood of the occurrence of vehicle-pedestrian collisions and the potential for the reduction in vehicle-pedestrian crashes. First, a vehicle-pedestrian collision density surface was produced via network kernel density estimation. By assigning a threshold value, possible vehicle-pedestrian hot spots were identified. To obtain the potential for vehicle-pedestrian collision reduction, random forests was employed to model the density with a set of variables describing vehicle and pedestrian flows. The potential for crash reduction was then measured as the difference between the observed vehicle-pedestrian crash density and the prediction produced by the random forests models. The final hotspots were determined by excluding those with a crash reduction value of no more than zero. The method was applied to the identification of hazardous road locations for pedestrians in a district in Shanghai, China. The result indicates that the method is useful for decision-making support.

Download Full-text