Development and Evaluation of Geostatistical Methods for Non-Euclidean-Based Spatial Covariance Matrices

Davis, Benjamin J. K.; Curriero, Frank C.

doi:10.1007/s11004-019-09791-y

Cited by 13 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comparison of Euclidean and Non-Euclidean water distances between these Chesapeake Bay monitoring stations has been described previously (Davis and Curriero, 2019). A total of nine statistically significant spatial Euclidean clusters were identified across the entire sampling period, compared to ten significant non-Euclidean clusters (Table 1).…”

Section: Resultsmentioning

confidence: 99%

“…Euclidean and non-Euclidean distances were calculated between all sample locations. Distances were restricted to surface tidal waters and thus were only calculated across two dimensions (Davis and Curriero, 2019). In order to calculate non-Euclidean distances, a polygon shapefile of the Chesapeake Bay was rasterized into 1km pixels.…”

Section: Methodsmentioning

confidence: 99%

“…This procedure was performed using the gdistance package (van Etten, 2017) from the R (version 3.4.4.) statistical software (R Development Core Team, 2018) and has been previously described in more detail (Murphy et al, 2015;Davis and Curriero, 2019).…”

Section: Methodsmentioning

confidence: 99%

“…Future applications of non-Euclidean cluster detection could also circumvent this limitation by being applied to interpolated surfaces of V. parahaemolyticus and related water quality measures. Efforts to use kriging in the Chesapeake Bay based upon non-Euclidean distances have already been investigated (Davis and Curriero, 2019), and future work could expand on this effort by performing space-time kriging in tidal waters. Such statistical interpolations could also be informed by mechanistic models that can account for flow and the hydrodynamics of the estuary based upon seasonal trends and morphometric differences in Bay regions.…”

Section: Articlementioning

confidence: 99%

“…Therefore, a non-Euclidean proximity measure, such as distances travelling by water only, rather than Euclidean distances that can cross both water and land, would more accurately represent the dynamics of the bacterium. This distinction is particularly important in the Chesapeake Bay due to its complex shoreline geography with many parallel tributaries (Davis and Curriero, 2019) (Figure 1). To observe the impact of this proximity metric disparity on cluster detection in marine environments, the following study compares the Euclidean and non-Euclidean distance-based spatial and spatiotemporal clusters of V. parahaemolyticus identified in the Chesapeake Bay between 2007 and 2010, and examines the impact of adjusting for well-known environmental determinants of the bacterium on the identified clusters.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Adjusted, non-Euclidean cluster detection of Vibrio parahaemolyticus in the Chesapeake Bay, USA

et al. 2019

Self Cite

View full text Add to dashboard Cite

Vibrio parahaemolyticus (V. parahaemolyticus) is a naturallyoccurring bacterium found in estuaries, such as the Chesapeake Bay (USA), that can cause vibriosis, a food - and waterborne illness, in humans. Tracking the spatial and temporal distribution of V. parahaemolyticus in the Chesapeake Bay, which varies in part due to water temperature, salinity, and other environmental variables, can help identify areas and time periods of high risk. These observations can support interventions used to reduce the burden of vibriosis. Spatial and spatiotemporal clusters of high V. parahaemolyticus abundance were identified among surface water samples in the Chesapeake Bay between 2007 and 2010. While Euclidean distances between geographic points in spatial analyses are often used for cluster detection, non-Euclidean distances should be considered for cluster detection due to the complex nature of the Chesapeake Bay shoreline. Comparison of both methods consistently showed the non-Euclidean cluster detection providing unique and more reasonable clusters than the Euclidean approach. Residuals from univariate and multivariate models were used to identify how clusters changed after controlling for environmental variables. Most clusters tended to decrease in space, time, or significance after adjustment, suggesting these covariates contributed to the original formation of the clusters and as such are useful observation tools for vibriosis risk managers. Clusters that remained after adjustment suggest areas for further study and intervention. These findings reinforce the importance of using non-Euclidean distances when tracking the spatiotemporal variation of V. parahaemolyticus as well as the benefits of cluster detection methods for V. parahaemolyticus risk management in estuaries.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Articlementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations