High quality, agricultural nutrient distribution maps are necessary for precision management, but depend on initial soil sample analyses and interpolation techniques. To examine the methodologies for and explore the capability of interpolating soil properties based on neural network ensemble residual kriging, a silage field at Hayes, Northern Ireland, UK, was selected for this study with all samples being split into independent training and validation data sets. The training data set, comprised of five soil properties: soil pH, soil available P, soil available K, soil available Mg and soil available S,was modeled for spatial variability using 1) neural network ensemble residual kriging, 2) neural network ensemble and 3) kriging with their accuracies being estimated by means of the validation data sets. Ordinary kriging of the residuals provided accurate local estimates, while final estimates were produced as a sum of the artificial neural network (ANN)ensemble estimates and the ordinary kriging estimates of the residuals. Compared to kriging and neural network ensemble,the neural network ensemble residual kriging achieved better or similar accuracy for predicting and estimating contour maps. Thus, the results demonstrated that ANN ensemble residual kriging was an efficient alternative to the conventional geo-statistical models that were usually used for interpolation of a data set in the soil science area.
Two field experiments were conducted in Jiashan and Yuhang towns of Zhejiang Province, China, to study the feasibility of predicting N status of rice using canopy spectral reflectance. The canopy spectral reflectance of rice grown with different levels of N inputs was determined at several important growth stages. Statistical analyses showed that as a result of the different levels of N supply, there were significant differences in the N concentrations of canopy leaves at different growth stages. Since spectral reflectance measurements showed that the N status of rice was related to reflectance in the visible and NIR (near-infrared) ranges, observations for rice in 1 nm bandwidths were then converted to bandwidths in the visible and NIR spectral regions with IKONOS (space imaging) bandwidths and vegetation indices being used to predict the N status of rice. The results indicated that canopy reflectance measurements converted to ratio vegetation index (RVI) and normalized difference vegetation index (NDVI) for simulated IKONOS bands provided a better prediction of rice N status than the reflectance measurements in the simulated IKONOS bands themselves. The precision of the developed regression models using RVI and NDVI proved to be very high with R2 ranging from 0.82 to 0.94, and when validated with experimental data from a different site, the results were satisfactory with R2 ranging from 0.55 to 0.70. Thus, the results showed that theoretically it should be possible to monitor N status using remotely sensed data.
