Abstract
One important method to obtain the continuous surfaces of soil properties from point samples is spatial interpolation. In this paper, we propose a method that combines ensemble learning with ancillary environmental information for improved interpolation of soil properties (hereafter, EL-SP). First, we calculated the trend value for soil potassium contents at the Qinghai Lake region in China based on measured values. Then, based on soil types, geology types, land use types, and slope data, the remaining residual was simulated with the ensemble learning model. Next, the EL-SP method was applied to interpolate soil potassium contents at the study site. To evaluate the utility of the EL-SP method, we compared its performance with other interpolation methods including universal kriging, inverse distance weighting, ordinary kriging, and ordinary kriging combined geographic information. Results show that EL-SP had a lower mean absolute error and root mean square error than the data produced by the other models tested in this paper. Notably, the EL-SP maps can describe more locally detailed information and more accurate spatial patterns for soil potassium content than the other methods because of the combined use of different types of environmental information; these maps are capable of showing abrupt boundary information for soil potassium content. Furthermore, the EL-SP method not only reduces prediction errors, but it also compliments other environmental information, which makes the spatial interpolation of soil potassium content more reasonable and useful.
Highlights
High quality soil property maps based on spatial patterns of soil variability are needed for agricultural planning, risk assessments, and decision making in regards to environmental management and conservation
The specific objectives of this study are (1) to describe spatial distributions of soil properties accurately based on soil types, geology types, land use types, and slope by applying ensemble learning with ancillary environmental information for improved interpolation of soil properties and (2) to compare the performance of the EL-SP method with inverse distance weighting (IDW), universal kriging (UK), ordinary kriging (OK), and a method that combines OK with different types of geographic information
We found that the interpolators that were combined with environmental information, i.e., EL-SP and OK-Geo, were the most accurate methods
Summary
High quality soil property maps based on spatial patterns of soil variability are needed for agricultural planning, risk assessments, and decision making in regards to environmental management and conservation. Such maps are usually not readily available and they are often difficult and expensive to acquire, especially for mountainous and high altitude regions. Sampling points for soil potassium content are typically sparse and the available data may be insufficient to characterize the highly variable soil potassium content and its PLOS ONE | DOI:10.1371/journal.pone.0124383. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript
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