An explainable spatial interpolation method considering spatial stratified heterogeneity
2
Citation
48
Reference
10
Related Paper
Citation Trend
Abstract:
Spatial interpolation is essential for handling sparsity and missing spatial data. Current machine learning-based spatial interpolation methods are subject to the statistical constraints of spatial stratified heterogeneity (SSH), normally involving separate modeling of each stratum and simple weighted averaging to integrate intra-stratum and inter-strata features. However, these models overlook the different contributions of inter-strata features to different locations within a stratum (heterogeneous inter-strata associations, HIA) and the explanation of spatial effects on the interpolation process, leading to suboptimal and unreliable interpolation outcomes. This article proposes a novel explainable spatial interpolation method considering SSH (X-SSHM). Spatial and environmental features are utilized to describe intra-stratum and inter-strata information, which are fed into random forest-based learners to achieve high-level semantic feature mapping. Geographically weighted regression is employed to integrate intra-stratum and inter-strata features to achieve a unified expression of SSH and HIA, obtaining the final interpolation result. Geographically weighted Shapley (GSHAP) is proposed to decompose the marginal contributions of intra-stratum and inter-strata features. Model performance is evaluated on simulated and soil organic matter datasets. X-SSHM outperformed five baselines regarding interpolation accuracy. Moreover, statistical methods validated X-SSHM's ability to elucidate the mechanisms by which SSH, spatial autocorrelation and HIA affect the model interpolation process.Keywords:
Interpolation
Spatial heterogeneity
Inverse distance weighting
Interpolation
Cite
Citations (0)
The quality of huge scale spatial data is specified with interpolation.Based on the analysis of normal spatial data interpolation methods,a new method of multi-level spatial data interpolation is proposed with algorithm in details.The result of experiment based on 3D geoscience modeling shows that it can heep more modeling features.
Interpolation
Cite
Citations (0)
Rainfall data is useful in many fields such as urban management, agriculture, and so on. Spatial interpolation is widely used to interpolation continue rainfall data from discrete rainfall gauges. The uncertainty in spatial interpolation is change in different region. Paper focus on urban small area of Beijing city, Xicheng District and analyses uncertainty of spatial interpolation from four aspects: rainfall gauge number, density, position, spatial interpolation methods. RMSE and cross-validation is adopted to evaluate the accuracy of interpolation and the lowest RMSE is taken as optimal. The results suggest that more gauges can get a good performance with low error compared to little stations; and dense gauges network gets high accuracy than sparse station. Ordinary kriging is simple than other method and has a good estimation (except co-kriging) in small area spatial interpolation. Co-kriging has a high accuracy in interpolation but complex in computation and must be considering in the other variables.
Interpolation
Cite
Citations (3)
A variation of the reduction-based approach to spatiotemporal interpolation (STI), in which time is treated independently from the spatial dimensions, is proposed in this paper. We reviewed and compared three widely-used spatial interpolation techniques: ordinary kriging, inverse distance weighting and the triangular irregular network. We also proposed a new distribution-based distance weighting (DDW) spatial interpolation method. In this study, we utilised one year of Tasmania's South Esk Hydrology model developed by CSIRO. Root mean squared error statistical methods were performed for performance evaluations. Our results show that the proposed reduction approach is superior to the extension approach to STI. However, the proposed DDW provides little benefit compared to the conventional inverse distance weighting (IDW) method. We suggest that the improved IDW technique, with the reduction approach used for the temporal dimension, is the optimal combination for large-scale spatiotemporal interpolation within environmental modelling applications.
Inverse distance weighting
Interpolation
Cite
Citations (37)
With the increasing need of spatial precipitation information,spatial interpolation method of precipitation is widely used.Different interpolation methods applied in different areas will produce different results.The best interpolation method should be obtained by comparing different interpolation methods in various areas.Using precipitation data of January from 1999 to 2008 of 12 cities of Jiangsu Province,like Nanjing,Wuxi etc.,we interpolate the precipitation data of Yangzhou of the same period with Ordinary Kriging and Inverse Distance Weighting.The result showed that Ordinary Kriging method is more suitable than Inverse Distance Weighting in the whole analysis.
Inverse distance weighting
Interpolation
Cite
Citations (0)
Abstract Spatial interpolation algorithm is based on known data to predict the study area, its accuracy is of great significance to research. In different application scenarios, the interpolation method with higher accuracy should be selected. Based on ArcGIS, this paper conducts experimental analysis on inverse distance weighting method and Kriging method, so as to provide a reference for the selection of interpolation method in different application scenarios.
Inverse distance weighting
Interpolation
Cite
Citations (11)
Interpolation
Cite
Citations (1)
Interpolation
Cite
Citations (2)
Spatial interpolation is important and fundamental to graphing, analysing and understanding of spatial data. In this paper, we introduce some spatial interpolation methods which are suited to 3D geological modeling. We have designed the framework of interpolation algorithm, and encapsulate API to GeoSIS system which provides an interface for easily accessing various interpolations. By calling API, the interpolated values can be calculated out based on the given samples, and then triangle irregular network surfaces can be constructed and visualized in 3D. The results of application show that the methods designed can to produce smooth surfaces which pass through all or most of the given samples and minimize error.
Interpolation
Interface (matter)
Cite
Citations (5)
Spatial interpolation is the procedure of estimating the value of properties at unsampled sites within the area covered by existing observations. In a broad sense, spatial interpolation includes point interpolation and areal interpolation. Several spatial interpolation methods were discussed in this paper including the base theory and the arithmetic of the methods. There is no absolutely optimal spatial interpolation method. There is only relatively optimal method in special situation. Hence, the best spatial interpolation method should be selected in according with the qualitative analysis of the data, exploratory spatial data analysis and repeated experiments. In addition, the result of spatial interpolation should be strictly examined for its validity. How to adapt the basic interpolation methods and create some new methods for special purpose to applied in different studies is the most important thing should be done in the spatial interpolation.
Interpolation
Cite
Citations (5)