Soil spatial information has traditionally been presented as polygon maps at coarse scales. Solving global and local issues, including food security, water regulation, land degradation, and climate change requires higher quality, more consistent and detailed soil information. Accurate prediction of soil variation over large and complex areas with limited samples remains a challenge, which is especially significant for China due to its vast land area which contains the most diverse soil landscapes in the world. Here, we integrated predictive soil mapping paradigm with adaptive depth function fitting, state-of-the-art ensemble machine learning and high-resolution soil-forming environment characterization in a high-performance parallel computing environment to generate 90-m resolution national gridded maps of nine soil properties (pH, organic carbon, nitrogen, phosphorus, potassium, cation exchange capacity, bulk density, coarse fragments, and thickness) at multiple depths across China. This was based on approximately 5000 representative soil profiles collected in a recent national soil survey and a suite of detailed covariates to characterize soil-forming environments. The predictive accuracy ranged from very good to moderate (Model Efficiency Coefficients from 0.71 to 0.36) at 0-5 cm. The predictive accuracy for most soil properties declined with depth. Compared with previous soil maps, we achieved significantly more detailed and accurate predictions which could well represent soil variations across the territory and are a significant contribution to the GlobalSoilMap.net project. The relative importance of soil-forming factors in the predictions varied by specific soil property and depth, suggesting the complexity and non-stationarity of comprehensive multi-factor interactions in the process of soil development.

Current methods of spatial prediction are based on either the First Law of Geography or the statistical principle or the combination of these two. The Second Law of Geography contributes to the revision of these methods so they are adaptive to local conditions but at the cost of increasing demand for samples. This paper presents a new thinking about spatial prediction based on the Third Law of Geography which focuses on the similarity of geographic configuration of locations. Under the Third Law of Geography, spatial prediction can be made on the basis of the similarity of geographic configurations between a sample and a prediction point. This allows the representativeness of a single sample to be used in prediction. A case study in predicting spatial variation of soil organic matter content was used to compare the spatial prediction based the Third Law of Geography with those based on the First Law and the statistical principle. It is concluded that spatial prediction based on the Third Law of Geography does not require samples to be over certain size nor to be of a particular spatial distribution to achieve a high quality prediction. The prediction uncertainty associated with spatial prediction based on the Third Law of Geography is more indicative to quality of the prediction, thus more effective in allocating error reduction efforts. These properties make spatial prediction based on the Third Law of Geography more suitable for prediction over large and complex geographic areas.