SAMPLING DESIGN FOR SOIL-MOISTURE MEASUREMENTS IN LARGE FIELD TRIALS

For the Long Term Research for Agricultural Systems (LTRAS) project at the University of California, Davis, sampling design and soil moisture variability between experimental plots were evaluated by geostatistical techniques. Three set of soil moisture data measured with a neutron probe in 72 0.36-ha plots were analyzed to estimate the spatial distribution of soil water storage. A cross-validation procedure involving gradual removal of measurement sites in each plot was used to examine the influence of reduced sampling density on sampling efficiency. Sampling efficiency was quantified by the Relative Information Criterion (RIC), block-kriged estimates obtained from the original sampling density and those obtained from reduced sampling densities. The RIC criterion was applied to evaluate the influence of sampling pattern and spatial variability on sampling efficiency. The results showed that a secondary regular sampling pattern with half of the original sampling locations yielded a higher efficiency than an irregular pattern. Using 144 instead of the original 288 sampling points, more than 90% of the original information was maintained. Also, soil water moisture storage appeared not only dominated by soil variation but was also influenced by irrigation regime and root water uptake. As the spatial continuity of soil water storage increased, so did sampling efficiency. Root water uptake caused a small decrease of spatial continuity, thereby reducing the sampling efficiency. Block-kriged estimates of soil water storage were used to eliminate plots with extreme soil water storage values, to improve the agricultural treatment design of the overall field experiment.