Integration of Spatial Interpolation Techniques and Association Rules for Estimation of Missing Precipitation Data

Deterministic and stochastic weighting methods are the most frequently used methods for estimating missing rainfall values at a gage based on values recorded at all other available recording gages. These methods may not always provide accurate estimates due to spatial and temporal variability of rainfall available at point measurements in space and also due to limitations of spatial interpolation techniques. Since an interpolated value of a variable at a point in space depends on observed values at all other points in space, temporal associations among observations in space can be beneficial in interpolation. An association rule mining (ARM) based spatial interpolation approach is proposed and investigated in the current study to estimate missing precipitation values at a gaging station. A stochastic spatial interpolation technique and three deterministic weighting methods are used in the current study. Historical daily precipitation data obtained from 15 rain gauging stations from temperate climatic region, Kentucky, USA, are used to test this approach and derive conclusions about its efficacy for estimating missing precipitation data. Results suggest that the use of association rule mining in conjunction with any spatial interpolation technique can improve the precipitation estimates and help to address one of the major limitations of any spatial interpolation technique.