Limits...
Fast inverse distance weighting-based spatiotemporal interpolation: a web-based application of interpolating daily fine particulate matter PM2:5 in the contiguous U.S. using parallel programming and k-d tree.

Li L, Losser T, Yorke C, Piltner R - Int J Environ Res Public Health (2014)

Bottom Line: These studies have highlighted the public concerns about health effects of particulate air pollution.Traditionally, when handling spatiotemporal interpolation, researchers tend to treat space and time separately and reduce the spatiotemporal interpolation problems to a sequence of snapshots of spatial interpolations.Finally, a web-based spatiotemporal IDW-based interpolation application is designed and implemented where users can visualize and animate spatiotemporal interpolation results.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Sciences, Georgia Southern University, Statesboro, GA 30460, USA. lli@georgiasouthern.edu.

ABSTRACT
Epidemiological studies have identified associations between mortality and changes in concentration of particulate matter. These studies have highlighted the public concerns about health effects of particulate air pollution. Modeling fine particulate matter PM2.5 exposure risk and monitoring day-to-day changes in PM2.5 concentration is a critical step for understanding the pollution problem and embarking on the necessary remedy. This research designs, implements and compares two inverse distance weighting (IDW)-based spatiotemporal interpolation methods, in order to assess the trend of daily PM2.5 concentration for the contiguous United States over the year of 2009, at both the census block group level and county level. Traditionally, when handling spatiotemporal interpolation, researchers tend to treat space and time separately and reduce the spatiotemporal interpolation problems to a sequence of snapshots of spatial interpolations. In this paper, PM2.5 data interpolation is conducted in the continuous space-time domain by integrating space and time simultaneously, using the so-called extension approach. Time values are calculated with the help of a factor under the assumption that spatial and temporal dimensions are equally important when interpolating a continuous changing phenomenon in the space-time domain. Various IDW-based spatiotemporal interpolation methods with different parameter configurations are evaluated by cross-validation. In addition, this study explores computational issues (computer processing speed) faced during implementation of spatiotemporal interpolation for huge data sets. Parallel programming techniques and an advanced data structure, named k-d tree, are adapted in this paper to address the computational challenges. Significant computational improvement has been achieved. Finally, a web-based spatiotemporal IDW-based interpolation application is designed and implemented where users can visualize and animate spatiotemporal interpolation results.

Show MeSH

Related in: MedlinePlus

The web application GUI dialog where the user selects the exponent, the number of nearest neighbors, the maximum Euclidean distance and the maximum time difference.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4199009&req=5

f23-ijerph-11-09101: The web application GUI dialog where the user selects the exponent, the number of nearest neighbors, the maximum Euclidean distance and the maximum time difference.

Mentions: There are two steps involved in performing interpolation using the web application. The first step to interpolate a dataset is to run a 10-fold cross-validation or LOOCV in order to explore a good combination of the exponent p and the number of neighbors N. Running the 10-fold cross-validation or the LOOCV function first requires the user to select a data file. If the format of the file is valid and the file is successfully loaded, the user presses the “10 Fold Cross Validation” or the “LOOCV Validation” button, as shown in Figure 22. The user is then presented with a dialog asking to select the exponent, the number of nearest neighbors, the maximum Euclidean distance and the maximum time difference, as shown in Figure 23. The maximum Euclidean distance is the maximum distance between the nearest neighbors and the point being interpolated. The maximum time difference is the maximum time difference between the nearest neighbors and the point being interpolated. Once the validation is complete, the error statistic MARE in Equation (7) and the error statistic RMSPE in Equation (8) along with some other error statistics are displayed on the GUI screen and written to a text file. The user will be responsible for choosing the optimal exponent, the number of nearest neighbors, the maximum Euclidean distance and the maximum time difference based on the error statistics results.


Fast inverse distance weighting-based spatiotemporal interpolation: a web-based application of interpolating daily fine particulate matter PM2:5 in the contiguous U.S. using parallel programming and k-d tree.

Li L, Losser T, Yorke C, Piltner R - Int J Environ Res Public Health (2014)

The web application GUI dialog where the user selects the exponent, the number of nearest neighbors, the maximum Euclidean distance and the maximum time difference.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4199009&req=5

f23-ijerph-11-09101: The web application GUI dialog where the user selects the exponent, the number of nearest neighbors, the maximum Euclidean distance and the maximum time difference.
Mentions: There are two steps involved in performing interpolation using the web application. The first step to interpolate a dataset is to run a 10-fold cross-validation or LOOCV in order to explore a good combination of the exponent p and the number of neighbors N. Running the 10-fold cross-validation or the LOOCV function first requires the user to select a data file. If the format of the file is valid and the file is successfully loaded, the user presses the “10 Fold Cross Validation” or the “LOOCV Validation” button, as shown in Figure 22. The user is then presented with a dialog asking to select the exponent, the number of nearest neighbors, the maximum Euclidean distance and the maximum time difference, as shown in Figure 23. The maximum Euclidean distance is the maximum distance between the nearest neighbors and the point being interpolated. The maximum time difference is the maximum time difference between the nearest neighbors and the point being interpolated. Once the validation is complete, the error statistic MARE in Equation (7) and the error statistic RMSPE in Equation (8) along with some other error statistics are displayed on the GUI screen and written to a text file. The user will be responsible for choosing the optimal exponent, the number of nearest neighbors, the maximum Euclidean distance and the maximum time difference based on the error statistics results.

Bottom Line: These studies have highlighted the public concerns about health effects of particulate air pollution.Traditionally, when handling spatiotemporal interpolation, researchers tend to treat space and time separately and reduce the spatiotemporal interpolation problems to a sequence of snapshots of spatial interpolations.Finally, a web-based spatiotemporal IDW-based interpolation application is designed and implemented where users can visualize and animate spatiotemporal interpolation results.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Sciences, Georgia Southern University, Statesboro, GA 30460, USA. lli@georgiasouthern.edu.

ABSTRACT
Epidemiological studies have identified associations between mortality and changes in concentration of particulate matter. These studies have highlighted the public concerns about health effects of particulate air pollution. Modeling fine particulate matter PM2.5 exposure risk and monitoring day-to-day changes in PM2.5 concentration is a critical step for understanding the pollution problem and embarking on the necessary remedy. This research designs, implements and compares two inverse distance weighting (IDW)-based spatiotemporal interpolation methods, in order to assess the trend of daily PM2.5 concentration for the contiguous United States over the year of 2009, at both the census block group level and county level. Traditionally, when handling spatiotemporal interpolation, researchers tend to treat space and time separately and reduce the spatiotemporal interpolation problems to a sequence of snapshots of spatial interpolations. In this paper, PM2.5 data interpolation is conducted in the continuous space-time domain by integrating space and time simultaneously, using the so-called extension approach. Time values are calculated with the help of a factor under the assumption that spatial and temporal dimensions are equally important when interpolating a continuous changing phenomenon in the space-time domain. Various IDW-based spatiotemporal interpolation methods with different parameter configurations are evaluated by cross-validation. In addition, this study explores computational issues (computer processing speed) faced during implementation of spatiotemporal interpolation for huge data sets. Parallel programming techniques and an advanced data structure, named k-d tree, are adapted in this paper to address the computational challenges. Significant computational improvement has been achieved. Finally, a web-based spatiotemporal IDW-based interpolation application is designed and implemented where users can visualize and animate spatiotemporal interpolation results.

Show MeSH
Related in: MedlinePlus