Abstract
The concept of spatial interpolation is important in the soil sciences. However, the use of a single global interpolation model is often limited by certain conditions (e.g., terrain complexity), which leads to distorted interpolation results. Here we present a method of adaptive weighting combined environmental variables for soil properties interpolation (AW-SP) to improve accuracy. Using various environmental variables, AW-SP was used to interpolate soil potassium content in Qinghai Lake Basin. To evaluate AW-SP performance, we compared it with that of inverse distance weighting (IDW), ordinary kriging, and OK combined with different environmental variables. The experimental results showed that the methods combined with environmental variables did not always improve prediction accuracy even if there was a strong correlation between the soil properties and environmental variables. However, compared with IDW, OK, and OK combined with different environmental variables, AW-SP is more stable and has lower mean absolute and root mean square errors. Furthermore, the AW-SP maps provided improved details of soil potassium content and provided clearer boundaries to its spatial distribution. In conclusion, AW-SP can not only reduce prediction errors, it also accounts for the distribution and contributions of environmental variables, making the spatial interpolation of soil potassium content more reasonable.
Highlights
The continuous spatial distribution of the soil plays a significant role in the fields of agriculture and environmental management[1,2]
Existing spatial interpolation methods can be largely classified into three groups3: 1) deterministic or non-geostatistical methods; 2) stochastic or geostatistical methods; and 3) combined methods
Machine learning methods have been applied to the fields of data mining and spatial interpolation and have demonstrated their predictive accuracy, e.g., artificial neural networks (ANN), support vector machine (SVM), 1Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing, People’s Republic of China. 2School of Geodesy and Geometrics, Jiangsu Normal University, Xuzhou, People’s Republic of China
Summary
The continuous spatial distribution of the soil plays a significant role in the fields of agriculture and environmental management[1,2]. Non-geostatistical interpolation methods such as IDW interpolation, which assume that each sampling point on the local impact with the increase in distance gradually disappears, do not have the statistical advantage despite its simple operation Such methods are often data- or even variable-specific, and their performance depends on many factors[4]. AW-SP, a machine learning paradigm in which multiple learners are trained to solve the same problem, originated from Hansen and Salamon’s work[23], which showed that the generalization ability of a model system can be significantly improved through use of a number of models, i.e. training many models and combining their predictions. As in the axiom ‘many hands make light work’, the predictive ability of the ensemble is usually significantly better than that of a single model[24]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call