Data enhancement, smoothing, reconstruction and optimization by kriging interpolation

Abstract

The performance of Kriging interpolation for enhancement, smoothing, reconstruction and optimization of a test data set is investigated. Specifically, the ordinary twodimensional Kriging and 2D line Kriging interpolation are investigated and compared with the well-known digital filters for data smoothing. We used an analytical 2D synthetic test data with several minima and maxima. Thus, we could perform detailed analyses in a well-controlled manner in order to assess the effectiveness of each procedure. We have demonstrated that Kriging method can be used effectively to enhance and smooth a noisy data set and reconstruct large missing regions (black zones) in lost data. It has also been shown that, with the appropriate selection of the correlation function (variogram model) and its correlation parameter, one can control the 'degree' of smoothness in a robust way. Finally, we illustrate that Kriging can be a viable ingredient in constructing effective global optimization algorithms in conjunction with simulated annealing.

Finite element model updating with quantified uncertainties using point cloud data

“…This contrasts to other forms such as simple kriging and universal kriging, which use a known constant trend value or a trend function, respectively, in their modeling assumptions. Researchers have made comparisons of the performance of these kriging models, and they have shown that universal kriging generally provides better results in cases where the underlying trend is understood and can be adequately captured (Zimmerman et al, 1999; Altman, 2000; Gunes et al, 2008). Within the context of structural deformations, it is possible to estimate the underlying trend of point cloud data in such cases as elastic flexure of beams.…”

Interpolation and mapping of the median k-factor for terrestrial link applications in South Africa

“…For example, in [6], the methods are used to estimate the average magnitude of the electromagnetic field in a pilot area in Caracas, Venezuela. In [7], kriging is used to smooth and enhance noisy data as well as construct missing data. In [8], inverse distance weighting is used in the determination of the geoclimatic factor for South Africa.…”

“…These methods are spatial in that they assume data continuity over space which allows the prediction of a variable at any location within a particular boundary [6]. Kriging depends on the spatial and statistical interdependence of data values to make predictions by employing semivariogram modeling [7]. IDW, on the other hand, uses the simple metric distance weights to make predictions and is therefore a simpler and faster method for few data points [8].…”

Reconstruction of daily chlorophyll-a concentrations in the transit of severe tropical cyclone Hudhud using the ExDINEOF method

“…While many studies investigate the reconstruction of environmental factors like sea surface temperature (SST) (Bignami et al, 2007;Zhao and He, 2012;Shropshire et al, 2016;Ji et al, 2018;Ma et al, 2021), wind field (Jayaram et al, 2014), turbidity (Alvera-Azcaŕate et al, 2015), sea surface salinity (SSS) (Alvera-Azcaŕate et al, 2016), and total suspended matter (NeChad et al, 2011)in ocean-color remote sensing, reconstruction methods for chlorophyll-a concentration data, crucial for global climate change and biogeochemical cycles, remain underdeveloped and warrant further exploration (Gunes et al, 2008;NeChad et al, 2011;Waite and Mueter, 2013). Most studies focus on regions with fewer missing data, such as the Mediterranean Sea (Alvera-Azcaŕate et al, 2005;Beckers et al, 2006;Antoine et al, 2008;Brando et al, 2015), the northern South China Sea (Ping et al, 2016;Ma et al, 2021), and the North Atlantic Ocean (Everson et al, 1996;Iida and Saitoh, 2007;Xiu et al, 2007;Zhao and He, 2012;Jouini et al, 2013;Waite and Mueter, 2013;Li and He, 2014;Wang and Liu, 2014;Liu and Wang, 2016;Shropshire et al, 2016;Hilborn and Costa, 2018;Wang et al, 2019).…”